google ads
February 2024 Imaging Pearls - Educational Tools | CT Scanning | CT Imaging | CT Scan Protocols - CTisus
Imaging Pearls ❯ February 2024

-- OR --

3D and Workflow

  • “Medicine exists as a public trust, with the expectation that the profession will self-regulate. Today, in the wake of all harmful errors, bioethical principles require that clinicians and health care organizations demonstrate transparency, compassion, and accountability and proactively meet patient needs. These steps cannot only increase trust in the health care system, but also help it improve.”
    Responding to Medical Errors — Implementing the Modern Ethical Paradigm
    Thomas H. Gallagher, M.D., and Allen Kachalia
    n engl j med 390;3 2024
  • “While 10 %–20 % of SPTs demonstrate malignant behavior, the vast majority are indolent neoplasms that display excellent prognosis after surgical resection. Metastases, though rare, have also been reported in up to 2 % of cases, with the liver being the most common site of metastatic spread. Given their low malignant potential and excellent outcomes if appropriately treated, correct and timely radiological diagnosis is crucial in optimizing patient management and prognosis. Due to the rarity of SPTs however, in conjunction with the heterogeneity of their imaging features, establishing correct diagnosis has previously proven to be challenging. Prior studies have demonstrated that among cases of pathologically proven SPTs, preoperative suspicion of SPT based on imaging features was correctly raised in only 24 % of cases.”
    Cinematic rendering of solid pseudopapillary tumors: Augmenting diagnostics of an increasingly encountered tumor  
    Taha M. Ahmed, MD, Elliot K. Fishman, MD, Linda C. Chu, MD*
    Current Problems in Diagnostic Radiology (in press)
  • “Cinematic rendering is completed on an independent workstation equipped with Siemens Syngo Via (VB40) running cinematic rendering software. We have developed optimized rendering parameters for the pancreas which we have used for a range of pancreatic pathology. These pre-defined parameters are adjusted in real time to optimize output on a case-by-case basis. The final images are subsequently exported to PACS where they can be reviewed by the referring clinician.”
    Cinematic rendering of solid pseudopapillary tumors: Augmenting diagnostics of an increasingly encountered tumor  
    Taha M. Ahmed, MD, Elliot K. Fishman, MD, Linda C. Chu, MD*
    Current Problems in Diagnostic Radiology (in press)
  • “CT attenuation in cystic regions ranges from that of fluid attenuation equal to that of water to soft tissue attenuation of areas rich in blood. Internal hemorrhage, in the appropriate context of other imaging findings, is highly characteristic of these tumors and is present in between 29 and 88.9 % of cases. Calcifications are present in roughly one third of tumors and are more frequently encountered in larger tumors.19,20 Although peripheral curvilinear calcifications are most classic, calcification patterns may vary. The majority of SPTs (59.3 %) are located within the body and tail of the pancreas with a mean tumor size of 6.1 cm at the time of presentation.”
    Cinematic rendering of solid pseudopapillary tumors: Augmenting diagnostics of an increasingly encountered tumor  
    Taha M. Ahmed, MD, Elliot K. Fishman, MD, Linda C. Chu, MD*
    Current Problems in Diagnostic Radiology (in press)
  • “Differential diagnoses for predominantly solid SPTs consists of well differentiated pancreatic neuroendocrine tumor (PNET), pancreatic ductal adenocarcinoma (PDAC), serous adenoma (SCA) and metastases. For larger mixed solid and cystic SPTs, differential diagnoses consists of such as mucinous cystic neoplasm (MCN), SCA, intraductal papillary mucinous neoplasm (IPMN), cystic PNETs, calcified hemorrhagic pseudocyst, pancreatoblastoma in pediatric patients, and exophytic gastrointestinal stromal tumor (GIST) when arising in close relation to the pancreas.”
    Cinematic rendering of solid pseudopapillary tumors: Augmenting diagnostics of an increasingly encountered tumor  
    Taha M. Ahmed, MD, Elliot K. Fishman, MD, Linda C. Chu, MD*
    Current Problems in Diagnostic Radiology (in press)
  • “Computed tomography (CT) is the primary imaging modality used to assess SPT. At imaging, SPTs typically appear as well encapsulated mixed-density lesions composed of varying proportions of solid components and cystic components. Infrequently, they may be mostly solid or mostly cystic. SPTs are hypothesized to grow as solid tumors that outgrow their vascular supply and subsequently undergo cystic degeneration. As a result, cystic components tend to be centrally located while enhancing solid components are present peripherally. CT attenuation in cystic regions ranges from that of fluid attenuation equal to that of water to soft tissue attenuation of areas rich in blood. Internal hemorrhage, in the appropriate context of other imaging findings, is highly characteristic of these tumors and is present in between 29 and 88.9 % of cases.”
    Cinematic rendering of solid pseudopapillary tumors: Augmenting diagnostics of an increasingly encountered tumor  
    Taha M. Ahmed, MD, Elliot K. Fishman, MD, Linda C. Chu, MD*
    Current Problems in Diagnostic Radiology (in press)
  • “CR in these cases can better visualize internal septations, increase depth perception of cystic components and characterize the true cystic nature of the mass. Through this, the internal architecture of cystic components can be better appreciated which can help in differentiating between cystic neoplasms. In rare cases, SPT may also present as a purely cystic mass, making differentiation between SPT and MCNs challenging. In these equivocal cases, patient demographics, particularly age, may be used to help differentiate between the two entities.”
    Cinematic rendering of solid pseudopapillary tumors: Augmenting diagnostics of an increasingly encountered tumor  
    Taha M. Ahmed, MD, Elliot K. Fishman, MD, Linda C. Chu, MD*
    Current Problems in Diagnostic Radiology (in press)
  • “Vascular encasement, narrowing, occlusion and invasion in SPTs is rare and up to 95 % of SPT do not demonstrate any vascular involvement. CR in these cases can better characterize any vascular stretching, abutment, and compression from a large SPT and differentiate it from true vessel involvement from a PDAC or PNET. This can help rule in the correct diagnosis with more certainty. While most SPTs do not demonstrate vascular invasion, a small aggressive subset (4.6 %) of tumors can present with vascular involvement. Vascular invasion does not necessarily preclude surgical resection of SPT however, and previous reports have demonstrated long term improved outcomes when radical resection with vascular reconstruction is pursued. CR in such cases can better define the extent of vascular involvement through characterizing the length of involved vessel and degree of luminal narrowing."
    Cinematic rendering of solid pseudopapillary tumors: Augmenting diagnostics of an increasingly encountered tumor  
    Taha M. Ahmed, MD, Elliot K. Fishman, MD, Linda C. Chu, MD*
    Current Problems in Diagnostic Radiology (in press)
  • “Second, the display of CR images needs to be optimized to accurately depict the anatomy and pathology of interest. This requires the specialized expertise of radiologists who must tailor the display settings for each unique pathology. Utilization of incorrectly optimized parameters can hinder visualization and potentially lead to incorrect diagnoses. While this aspect of CR implementation may become more standardized and user-friendly in the future, and potentially automated with the help of artificial intelligence algorithms, currently radiologists must dedicate time to manually render each case. It takes an experienced radiologist approximately 5–7 min to render each case.”
    Cinematic rendering of solid pseudopapillary tumors: Augmenting diagnostics of an increasingly encountered tumor  
    Taha M. Ahmed, MD, Elliot K. Fishman, MD, Linda C. Chu, MD*
    Current Problems in Diagnostic Radiology (in press)
  • “Cinematic rendering has multiple applications in the abdomen and may serve as an important adjunct to standard CT images in the evaluation of a variety of abdominal conditions. Cinematic rendering offers the potential for comprehensive assessment of ileal NETs as it improves the appreciation of relationships between the tumor and surrounding organs, and delineation of the major vascular supply, which may influence surgical planning and help anticipate the radicality of associated ileal loop resection. Our findings provide additional evidence on the role of cinematic rendering for preoperative planning of ileal NETs compared to more traditional CT imaging.”
    Comprehensive preoperative assessment of ileal neuroendocrine tumor with cinematic rendering.  
    Pellat A, Terris B, Soyer P.  
    Diagn Interv Imaging. 2024 Jan;105(1):40-41. 
  • “Cinematic rendering is a 3D reconstruction technique inspired by the animated movie industry. It follows the same steps used for volume rendering in determining colour and opacity that models real-life physical propagation of light providing photorealistic 3D images with more surface details.2 The application of cinematic rendering in clinical practice has been described for pre-operative planning of tumours such as GIST. Originally clinical use of 3D imaging was confined to calculating organ volumes or orthopedic applications; however, the use of helical technology for the propagation of thin slice computed tomography (CT) in conjunction with advanced image reconstruction software has allowed this to be utilized for a variety of other applications.3 Applications for cinematic rendering have been reported to include lesion characterization, localization, and risk stratification in the pre-operative setting. This has been adopted in the literature to date for the assessment of liver masses, pancreatic cancer, gastric tumours, leiomyosarcomas, gastrointestinal bleeding and GIST, to name a few.”
    Utilization of Cinematic Rendering for Evaluation of Gastrointestinal Stromal Tumours (GIST).  
    O’Brien C.
    Canadian Association of Radiologists Journal. 2023;0(0). doi:10.1177/08465371231221936
  • “Cinematic rendering of GIST helps demonstrate the submucosal origin of the mass and visualize the dynamic enhancement pattern within the tumour allowing for better anatomical evaluation of the lesion providing more information on areas of necrosis and enhancement. Additionally, there is increased information regarding the growth pattern, vascular supply, adjacent anatomic structures, and blood vessels which improves pre-operative planning. Active bleeding from a small bowel tumour is difficult to characterize on conventional CT. Cinematic rendering can more easily detect if there is bleeding from a small bowel tumour. It also provides increased information to differentiate GIST form other gastrointestinal tumours, especially at the ampulla and in the pelvis where anatomical detail is limited on conventional CT. The use of cinematic rendering in GIST is particularly useful as this technique provides exquisite mucosal detail which increases sensitivity for assessment of gastrointestinal mucosal fold changes. Lastly, the ability to produce vascular mapping of a GIST with cinematic rendering allows localization of the feeding vessel in a preoperative setting. Many of the features described are also used to risk stratify GISTs from very low to high risk for recurrence; the added value of cinematic rendering for assessment of GIST may provide a future role for imaging estimation of risk.”
    Utilization of Cinematic Rendering for Evaluation of Gastrointestinal Stromal Tumours (GIST).  
    O’Brien C.
    Canadian Association of Radiologists Journal. 2023;0(0). doi:10.1177/08465371231221936
  • “As Barat et al discuss, there are limitations to adopting cinematic rendering into clinical practice. However, the scope for future developments is an exciting avenue for improving management of GIST including investigating gene mutations, and incorporating it into a hybrid imaging tool such as positron emission tomography/CT. This technique also has other potential applications including teaching anatomy with more photorealistic images simulating cadaveric specimens. Patient education could be improved with illustration of pathologic diseases in the pre-treatment setting and in the future to be used as an alternative to three-dimensional printing. Cinematic rendering is an exciting new technique currently in its infancy that has the potential to add great value to our practice. To fulfill the advice of Dr Brady: to move forward and keep up, the next step should be to investigate how to implement cinematic rendering into our day-to-day practice.
    Utilization of Cinematic Rendering for Evaluation of Gastrointestinal Stromal Tumours (GIST).  
    O’Brien C.
    Canadian Association of Radiologists Journal. 2023;0(0). doi:10.1177/08465371231221936
  • “Cinematic rendering is an exciting new technique currently in its infancy that has the potential to add great value to our practice. To fulfill the advice of Dr Brady: to move forward and keep up, the next step should be to investigate how to implement cinematic rendering into our day-to-day practice.”
    Utilization of Cinematic Rendering for Evaluation of Gastrointestinal Stromal Tumours (GIST).  
    O’Brien C.
    Canadian Association of Radiologists Journal. 2023;0(0). doi:10.1177/08465371231221936
  • “Non-traumatic thoracic aorta emergencies are acute conditions associated with substantial morbidity and mortality. In the emergency setting, timely detection of aortic injury through radiological imaging is crucial for prompt treatment planning and favorable patient outcomes. 3D cinematic rendering (CR), a novel rendering algorithm for computed tomography (CT) image processing, allows for life-like visualization of spatial details and contours of highly complex anatomic structures such as the thoracic aorta and its vessels, generating a photorealistic view that not just adds to diagnostic confidence, but is especially useful for non-radiologists, including surgeons and emergency medicine physicians. In this pictorial review, we demonstrate the utility of CR in the setting of non-traumatic thoracic aorta emergencies through 10 cases that were processed at a standalone 3D CR station at the time of presentation, including its role in diagnosis and management.”
    Cinematic rendering of non-traumatic thoracic aorta emergencies: a new look at an old problem.  
    Yasrab M, Rizk RC, Chu LC, Fishman EK.  
    Emerg Radiol. 2024 Jan 18. doi: 10.1007/s10140-024-02204-6. Epub ahead of print.
  • “Routinely employed 3D post-processing tools include maximum intensity projection (MIP) and volume rendering (VR) that allow for the generation of angiographic images and a more intuitive and interactive representations of the spatial information in the dataset, respectively. Improving upon traditional VR, 3D cinematic rendering (CR) is a Food andDrug Administration (FDA)-approved technique that employs a novel lighting model to generate photorealistic images. CR involves global illumination and path tracing models whereby numerous light rays from all directions propagate through and interact with the volumetric data to generate a voxel. Complex anatomical relations are better evaluated and enhanced depth and shape perception is achieved as the technique considers a natural lighting environment and its effects (e.g., reflection, diffusion, refraction). Postprocessing windowing and the use of clip planes/masks allow cutting into the volume and isolation of the area/organ of interest.”
    Cinematic rendering of non-traumatic thoracic aorta emergencies: a new look at an old problem.  
    Yasrab M, Rizk RC, Chu LC, Fishman EK.  
    Emerg Radiol. 2024 Jan 18. doi: 10.1007/s10140-024-02204-6. Epub ahead of print.
  • “There are some limitations that come with 3D CR. Notably, shadows generated in the images might conceal certain pathologies when viewed from specific angles, necessitating meticulous optimization and assessment from diverse angles in conjunction with the multiplanar reformations. Thus, while an initial learning period to become adept in handling and familiarizing themselves with the CR process is required for radiologists, as demonstrated in our case studies, an experienced radiologist can efficiently execute the rendering process in under 5 min.”
    Cinematic rendering of non-traumatic thoracic aorta emergencies: a new look at an old problem.  
    Yasrab M, Rizk RC, Chu LC, Fishman EK.  
    Emerg Radiol. 2024 Jan 18. doi: 10.1007/s10140-024-02204-6. Epub ahead of print.
  • “Color mapping of different phases enhances visualization of the key pathology, such as the flow through the false and true lumens in a dissection that can be delineated by high contrast shading. CR rendering emphasizes textural changes attributable to inflammatory processes with realistic shadowing that is otherwise difficult to appreciate. The improved surface detail helps characterize an impending PAU or the nature of outpouchings suspicious for mycotic aneurysms and gives a clearer view of multiple plaques and sites of ulceration that could be otherwise missed.”
    Cinematic rendering of non-traumatic thoracic aorta emergencies: a new look at an old problem.  
    Yasrab M, Rizk RC, Chu LC, Fishman EK.  
    Emerg Radiol. 2024 Jan 18. doi: 10.1007/s10140-024-02204-6. Epub ahead of print.
  • “Another application of 3D CR is via the black blood cinematic rendering (BBCR) preset.. BBCR is a preset we specifically developed to visualize intraluminal contours and structures of the heart and great vessels, all through adjustments that can be madein under a minute. This is especially useful in the setting of visualizing various zones of thrombi and occlusion, the degree of obstruction, and the subtle irregularities and internal arrangement of the thrombus that can only be appreciateddue to enhanced depth perception and shadowing.”
    Cinematic rendering of non-traumatic thoracic aorta emergencies: a new look at an old problem.  
    Yasrab M, Rizk RC, Chu LC, Fishman EK.  
    Emerg Radiol. 2024 Jan 18. doi: 10.1007/s10140-024-02204-6. Epub ahead of print.
  • “The intrinsic features of 3D CR with its ability to provide a holistic field of view of the vascular map increases confidence in management and surgical planning. A global viewing angle of the thoracic aorta helps in tracking the dissection and its involvement of the aorta and the extent of mediastinal and pericardial bleeding where present .In cases where patients underwent thoracic endovascular aortic repair (TEVAR), coiling, or graft repairing, CR adds to surgical planning by improved depth perception, shadow effects, and realistic textures, demonstrating the anatomical relationships of the thoracic aorta, surrounding structures, and the pathology to be addressed, with photorealism providing the surgeon a familiar perspective to work with.”
    Cinematic rendering of non-traumatic thoracic aorta emergencies: a new look at an old problem.  
    Yasrab M, Rizk RC, Chu LC, Fishman EK.  
    Emerg Radiol. 2024 Jan 18. doi: 10.1007/s10140-024-02204-6. Epub ahead of print.
  • “3D cinematic rendering (CR) represents an important advancement in radiological imaging, particularly in enhancing the visualization of complex anatomical structures and systems such as the thoracic aorta and its vessels. CR provides detailed, photorealistic illustrations crucial for diagnosis and surgical planning as we have seen in several cases. Future research is needed to evaluate CR’s diagnostic accuracy, both prospectively and in head-to-head comparisons with other rendering methods, as well as its role in other domains such as patient education and medical training. CR, therefore, is emerging as a promising, evolving tool for radiologists, surgeons, and the patients they treat.”  
    Cinematic rendering of non-traumatic thoracic aorta emergencies: a new look at an old problem.  
    Yasrab M, Rizk RC, Chu LC, Fishman EK.  
    Emerg Radiol. 2024 Jan 18. doi: 10.1007/s10140-024-02204-6. Epub ahead of print.
Adrenal

  • OBJECTIVE. The purpose of our study was to evaluate the diagnostic utility of adrenal mass biopsy in patients without known or suspected extraadrenal primary malignancy.  
    CONCLUSION. Adrenal mass biopsy had low diagnostic yield, with low sensitivity and low specificity for malignancy. A biopsy result of adrenocortical neoplasm did not reliably differentiate benign and malignant adrenal masses.
    CLINICAL IMPACT. Biopsy appears to have limited utility for the evaluation of incidental adrenal masses in patients without primary extraadrenal malignancy.
    Adrenal Mass Biopsy in Patients Without Extraadrenal Primary Malignancy: A Multicenter Study
    Satheesh Krishna et al.
    AJR 2024; 222:e2329826
  • Key Finding
    - In patients without primary extraadrenal malignancy, adrenal mass biopsy had a diagnostic yield of 64% (44/69; 95% CI, 51–75%), concordance with the diagnosis from subsequent surgical resection of 100% (12/12), and sensitivity and specificity for detection of malignancy (by subsequent resection or imaging follow-up) of 73% (22/30) and 54% (21/39), respectively.
    Importance
    - Adrenal mass biopsy has limited diagnostic utility for theevaluation of incidental adrenal masses in patients without primary extraadrenal malignancy.
    Adrenal Mass Biopsy in Patients Without Extraadrenal Primary Malignancy: A Multicenter Study
    Satheesh Krishna et al.
    AJR 2024; 222:e2329826
  • “Incidental adrenal masses with macroscopic fat on imaging were historically considered to unequivocally represent myelolipomas. However, it has recently been recognized that adrenal adenomas can contain small amounts of macroscopic fat due to myelolipomatous degeneration and that ACC may also rarely contain small amounts of macroscopic fat. In the present study, among the 18 adrenal masses with macroscopic fat, only four were malignant; biopsy had a sensitivity of 50% for these malignancies.”  
    Adrenal Mass Biopsy in Patients Without Extraadrenal Primary Malignancy: A Multicenter Study
    Satheesh Krishna et al.
    AJR 2024; 222:e2329826
  • “In conclusion, this study identified that biopsy of adrenal masses in patients without a known or suspected primary extraadrenal malignancy was safe, without any significant immediate postprocedural complications. When diagnostic, adrenal mass biopsy had high sensitivity and specificity for malignancy. However, adrenal mass biopsy had a high nondiagnostic rate, and, when classifying nondiagnostic biopsies as false results, had low sensitivity and specificity for malignancy. In particular, adrenal mass biopsies were commonly reported as adrenocortical neoplasm, a result that could not reliably differentiate benign and malignant adrenal masses.”
    Adrenal Mass Biopsy in Patients Without Extraadrenal Primary Malignancy: A Multicenter Study
    Satheesh Krishna et al.
    AJR 2024; 222:e2329826
Cardiac

  • The applications of AI for imaging of CAD using CT span multiple arenas including plaque detection, plaque characterization, improving risk stratification, and clinical decision-making. AI has been applied to both CAC scoring and CCTA. Studies have shown the ability of AI to detect hemodynamically significant stenosis across a broad range of imaging parameters and its potential ability to decrease the time needed for analysis of images for stenosis. AI can significantly reduce the time to perform quantitative plaque analysis, an important barrier to its application in clinical practice.
    Coronary Artery Disease: Role of Computed Tomography and Recent Advances
    Elizabeth Lee et al
    Radiol Clin N Am - (2024 (in press)
  • “One trial of AI-based CCTA interpretation in patients with stable chest pain referred for ICA found a lower cost compared with conventional interpretation due to lower rates of referral for ICA, without impacting the occurrence of cardiac events. A comprehensive review of all potential applications for AI in CT imaging of CAD is beyond the scope of this review; however, AI is certain to change how imaging is ordered, performed, and interpreted in the near future.”  
    Coronary Artery Disease: Role of Computed Tomography and Recent Advances
    Elizabeth Lee et al
    Radiol Clin N Am - (2024 (in press)
  •   • Coronary computed tomography angiography (CCTA) has the highest level of evidence supporting its use in patients with acute and stable chest pain.  
    • CCTA can identify high-risk plaque features and quantify overall plaque burden, providing important prognostic information which has been incorporated into CADRADS 2.0.  
    • In asymptomatic patients, currently, there is no evidence for the use of CCTA; however, ongoing trials aim to determine whether CCTA can provide additional prognostic information above those from coronary calcium scoring and clinical risk factors.
    Coronary Artery Disease: Role of Computed Tomography and Recent Advances
    Elizabeth Lee et al
    Radiol Clin N Am - 2024 (in press)
Chest

  • Background: Chest radiography remains the most common radiologic examination, and interpretation of its results can be difficult.
    Purpose: To explore the potential benefit of artificial intelligence (AI) assistance in the detection of thoracic abnormalities on chest radiographs by evaluating the performance of radiologists with different levels of expertise, with and without AI assistance.
    Materials and Methods: Patients who underwent both chest radiography and thoracic CT within 72 hours between January 2010 and December 2020 in a French public hospital were screened retrospectively. Radiographs were randomly included until reaching 500 radiographs, with about 50% of radiographs having abnormal findings. A senior thoracic radiologist annotated the radiographs for five abnormalities (pneumothorax, pleural effusion, consolidation, mediastinal and hilar mass, lung nodule) based on the corresponding CT results (ground truth). A total of 12 readers (four thoracic radiologists, four general radiologists, four radiology residents) read half the radiographs without AI and half the radiographs with AI (ChestView; Gleamer). Changes in sensitivity and specificity were measured using paired t tests.
    Using AI to Improve Radiologist Performance in Detection of Abnormalities on Chest Radiographs
    Souhail Bennani et al.
    Radiology 2023; 309(3):e230860
  • Results: The study included 500 patients (mean age, 54 years Å} 19 [SD]; 261 female, 239 male), with 522 abnormalities visible on 241 radiographs. On average, for all readers, AI use resulted in an absolute increase in sensitivity of 26% (95% CI: 20, 32), 14% (95% CI: 11, 17), 12% (95% CI: 10, 14), 8.5% (95% CI: 6, 11), and 5.9% (95% CI: 4, 8) for pneumothorax, consolidation, nodule,  pleural effusion, and mediastinal and hilar mass, respectively (P < .001). Specificity increased with AI assistance (3.9% [95% CI: 3.2, 4.6], 3.7% [95% CI: 3, 4.4], 2.9% [95% CI: 2.3, 3.5], and 2.1% [95% CI: 1.6, 2.6] for pleural effusion, mediastinal and hilar mass, consolidation, and nodule, respectively), except in the diagnosis of pneumothorax (−0.2%; 95% CI: −0.36, −0.04; P = .01). The mean reading time was 81 seconds without AI versus 56 seconds with AI (31% decrease, P < .001).
    Conclusion: AI-assisted chest radiography interpretation resulted in absolute increases in sensitivity for all radiologists of various levels ofexpertise and reduced the reading times; specificity increased with AI, except in the diagnosis of pneumothorax.  
    Using AI to Improve Radiologist Performance in Detection of Abnormalities on Chest Radiographs
    Souhail Bennani et al.
    Radiology 2023; 309(3):e230860
  • Summary
    Artificial intelligence assistance can improve the detection accuracy of thoracic abnormalities on chest radiographs across radiologists with varying levels of expertise, leading to marked improvements in sensitivity and a reduction in interpretation time.
    Key Results
    ■ In a retrospective study of 500 patients who underwent chest radiography and thoracic CT for all abnormality types, artificial intelligence (AI)-assisted chest radiography interpretation resulted in increased sensitivity of 6%–26% (P < .001) for all readers, including thoracic radiologists, general radiologists, and radiology residents.
    ■ Mean reading time was 81 seconds without AI versus 56 seconds with AI (a decrease of 31%, P < .001), with a 17% reduction for radiographs with abnormalities versus a 38% reduction for radiographs with no abnormalities.
    Using AI to Improve Radiologist Performance in Detection of Abnormalities on Chest Radiographs
    Souhail Bennani et al.
    Radiology 2023; 309(3):e230860
  • Our results showed that AI assistance resulted in absolute increases in sensitivity for all readers of various levels of experience, including general radiologists and radiology residents, in detecting all five types of abnormalities on chest radiographs: from 5.3% for mediastinal and hilar mass to 25.3% for pneumothorax (P < .001). Specificity increased with AI assistance (from 2.1% [95% CI: 1.6, 2.6] for nodule to 3.9% [95% CI: 3.2, 4.6]), except in the diagnosis of pneumothorax (−0.2%; 95% CI: −0.36, −0.04; P = .01). Although unassisted thoracic radiologists outperformed unassisted general radiologists for the five abnormality types, assisted thoracic radiologists solely outperformed assisted general radiologists in the detection of consolidations (73.9% [95% CI: 67, 80] vs 70.5% [95% CI: 64, 77]; P = .01). Finally, the mean reading time was 81 seconds without AI versus 56 seconds with AI, for a 31% reduction (P < .001), with 17% reduction for radiographs with abnormalities and 38% reduction for radiographs with no abnormalities.
    Using AI to Improve Radiologist Performance in Detection of Abnormalities on Chest Radiographs
    Souhail Bennani et al.
    Radiology 2023; 309(3):e230860
  • ‘In regard to the impact of AI on reading time, there are conflicting data, with some reports citing a 10% reduction in reading time and others citing an increase of more than 100%. In our study, the 31% decrease in reading time was more important than previously reported. As in the study by Shin et al, we observed that the time saved in reading is greater for radiographs without abnormalities, which represent the majority of chest radiographs in clinical practice.”  
    Using AI to Improve Radiologist Performance in Detection of Abnormalities on Chest Radiographs
    Souhail Bennani et al.
    Radiology 2023; 309(3):e230860
  • “Routinely employed 3D post-processing tools include maximum intensity projection (MIP) and volume rendering (VR) that allow for the generation of angiographic images and a more intuitive and interactive representations of the spatial information in the dataset, respectively. Improving upon traditional VR, 3D cinematic rendering (CR) is a Food and Drug Administration (FDA)-approved technique that employs a novel lighting model to generate photorealistic images. CR involves global illumination and path tracing models whereby numerous light rays from all directions propagate through and interact with the volumetric data to generate a voxel. Complex anatomical relations are better evaluated and enhanced depth and shape perception is achieved as the technique considers a natural lighting environment and its effects (e.g., reflection, diffusion, refraction). Postprocessing windowing and the use of clip planes/masks allow cutting into the volume and isolation of the area/organ of interest.”
    Cinematic rendering of non-traumatic thoracic aorta emergencies: a new look at an old problem.  
    Yasrab M, Rizk RC, Chu LC, Fishman EK.  
    Emerg Radiol. 2024 Jan 18. doi: 10.1007/s10140-024-02204-6. Epub ahead of print.
  • “There are some limitations that come with 3D CR. Notably, shadows generated in the images might conceal certain pathologies when viewed from specific angles, necessitating meticulous optimization and assessment from diverse angles in conjunction with the multiplanar reformations. Thus, while an initial learning period to become adept in handling and familiarizing themselves with the CR process is required for radiologists, as demonstrated in our case studies, an experienced radiologist can efficiently execute the rendering process in under 5 min.”
    Cinematic rendering of non-traumatic thoracic aorta emergencies: a new look at an old problem.  
    Yasrab M, Rizk RC, Chu LC, Fishman EK.  
    Emerg Radiol. 2024 Jan 18. doi: 10.1007/s10140-024-02204-6. Epub ahead of print.
  • “Color mapping of different phases enhances visualization of the key pathology, such as the flow through the false and true lumens in a dissection that can be delineated by high contrast shading. CR rendering emphasizes textural changes attributable to inflammatory processes with realistic shadowing that is otherwise difficult to appreciate. The improved surface detail helps characterize an impending PAU or the nature of outpouchings suspicious for mycotic aneurysms and gives a clearer view of multiple plaques and sites of ulceration that could be otherwise missed.”
    Cinematic rendering of non-traumatic thoracic aorta emergencies: a new look at an old problem.  
    Yasrab M, Rizk RC, Chu LC, Fishman EK.  
    Emerg Radiol. 2024 Jan 18. doi: 10.1007/s10140-024-02204-6. Epub ahead of print.
  • “Another application of 3D CR is via the black blood cinematic rendering (BBCR) preset.. BBCR is a preset we specifically developed to visualize intraluminal contours and structures of the heart and great vessels, all through adjustments that can be madein under a minute. This is especially useful in the setting of visualizing various zones of thrombi and occlusion, the degree of obstruction, and the subtle irregularities and internal arrangement of the thrombus that can only be appreciateddue to enhanced depth perception and shadowing.”
    Cinematic rendering of non-traumatic thoracic aorta emergencies: a new look at an old problem.  
    Yasrab M, Rizk RC, Chu LC, Fishman EK.  
    Emerg Radiol. 2024 Jan 18. doi: 10.1007/s10140-024-02204-6. Epub ahead of print.
  • “The intrinsic features of 3D CR with its ability to provide a holistic field of view of the vascular map increases confidence in management and surgical planning. A global viewing angle of the thoracic aorta helps in tracking the dissection and its involvement of the aorta and the extent of mediastinal and pericardial bleeding where present .In cases where patients underwent thoracic endovascular aortic repair (TEVAR), coiling, or graft repairing, CR adds to surgical planning by improved depth perception, shadow effects, and realistic textures, demonstrating the anatomical relationships of the thoracic aorta, surrounding structures, and the pathology to be addressed, with photorealism providing the surgeon a familiar perspective to work with.”
    Cinematic rendering of non-traumatic thoracic aorta emergencies: a new look at an old problem.  
    Yasrab M, Rizk RC, Chu LC, Fishman EK.  
    Emerg Radiol. 2024 Jan 18. doi: 10.1007/s10140-024-02204-6. Epub ahead of print.
  • “3D cinematic rendering (CR) represents an important advancement in radiological imaging, particularly in enhancing the visualization of complex anatomical structures and systems such as the thoracic aorta and its vessels. CR provides detailed, photorealistic illustrations crucial for diagnosis and surgical planning as we have seen in several cases. Future research is needed to evaluate CR’s diagnostic accuracy, both prospectively and in head-to-head comparisons with other rendering methods, as well as its role in other domains such as patient education and medical training. CR, therefore, is emerging as a promising, evolving tool for radiologists, surgeons, and the patients they treat.”  
    Cinematic rendering of non-traumatic thoracic aorta emergencies: a new look at an old problem.  
    Yasrab M, Rizk RC, Chu LC, Fishman EK.  
    Emerg Radiol. 2024 Jan 18. doi: 10.1007/s10140-024-02204-6. Epub ahead of print.
  • “Non-traumatic thoracic aorta emergencies are acute conditions associated with substantial morbidity and mortality. In the emergency setting, timely detection of aortic injury through radiological imaging is crucial for prompt treatment planning and favorable patient outcomes. 3D cinematic rendering (CR), a novel rendering algorithm for computed tomography (CT) image processing, allows for life-like visualization of spatial details and contours of highly complex anatomic structures such as the thoracic aorta and its vessels, generating a photorealistic view that not just adds to diagnostic confidence, but is especially useful for non-radiologists, including surgeons and emergency medicine physicians. In this pictorial review, we demonstrate the utility of CR in the setting of non-traumatic thoracic aorta emergencies through 10 cases that were processed at a standalone 3D CR station at the time of presentation, including its role in diagnosis and management.”
    Cinematic rendering of non-traumatic thoracic aorta emergencies: a new look at an old problem.  
    Yasrab M, Rizk RC, Chu LC, Fishman EK.  
    Emerg Radiol. 2024 Jan 18. doi: 10.1007/s10140-024-02204-6. Epub ahead of print.
  • SVCS is a combination of signs and symptoms that result from the compression or occlusion of the superior vena cava, associated with a significant morbidity and mortality. While thoracic malignancy is the most common cause of SVCS accounting for more than 60% of the cases, benign causes are on the rise with the increasing use of central venous catheters and indwelling cardiac devices .Benign SVCS usually has a more insidious course compared to malignant causes, as there is time for the development of adequate collaterals to bypass the central venous occlusion.
    Superior vena cava syndrome with the hepatic ‘hot spot’ sign.  
    Koratala, A., Bhatti, V.  
    Intern Emerg Med 13, 293–294 (2018).
  • A CT scan of the chest with contrast excluded acute pulmonary embolism, but showed extensive chest wall venous collaterals with near-complete occlusion of the superior vena cava. In addition, it demonstrated the “focal hepatic hot spot sign,” which is an enhanced area in the segment IV or quadrate lobe of the liver, which results from the communication between superficial epigastric veins and left portal vein in cases of superior vena cava obstruction
    Superior vena cava syndrome with the hepatic ‘hot spot’ sign.  
    Koratala, A., Bhatti, V.  
    Intern Emerg Med 13, 293–294 (2018).
  • OBJECTIVE. The purpose of this article is to review the CT findings associated with superior  vena  cava  obstruction  and  to  illustrate  collateral  venous  pathways  bypassing  the  ob-struction as shown on MDCT.
    CONCLUSION. Multiple collateral venous pathways can form to bypass an obstruction of the superior vena cava. With its ability to acquire near isotropic data, MDCT allows high-quality reformations and thus exquisitely displays these venous collaterals and has the potential to aid in planning therapy to bypass the obstruction.    
    Superior Vena Cava Obstruction Evaluation With MDCT              
    Sheila Sheth, Mark D. Ebert, and Elliot K. Fishman              
    American Journal of Roentgenology 2010 194:4, W336-W346
  • “Obstruction  of  the  superior  vena  cava  re-sults  in  impaired  venous  drainage  of  the head  and  neck  and  upper  extremities.  Clinical  manifestations  include  facial  and  neck swelling, distended neck veins, headache due to  cerebral  edema,  dyspnea,  and,  in  severe cases, stridor and altered mental status. Cor-relation of imaging studies with clinical find-ings  suggests  that  the  severity  of  symptoms depends on the level of obstruction (above or below  the  level  of  the  azygos  arch)  and  the development of rich collateral network. In fact, CT can detect subclinical superior vena cava obstruction in patients who are relatively asymptomatic.”        
    Superior Vena Cava Obstruction Evaluation With MDCT              
    Sheila Sheth, Mark D. Ebert, and Elliot K. Fishman              
    American Journal of Roentgenology 2010 194:4, W336-W346
  • “The  radiologist  should  be  familiar  with findings  on  abdominal  CT  that  suggest  the presence  of  a  superior  vena  cava  obstruc-tion. In addition to enhancing round or tortu-ous vascular channels in the abdominal wall,  perfusion  abnormalities  in  the  liv-er  and  the  so-called  “hot  spot”  initially  de-scribed on nuclear medicine both result from communication  between  superficial  epigas-tric veins and left portal vein. On CT, there is intense opacification of the anterior quadrate  lobe.  The  area  of  enhancement  is  characteristic  in  its  position  as  well  as  its  shape and  should  not  be  mistaken  for  a  hypervascular mass.”
    Superior Vena Cava Obstruction Evaluation With MDCT
    Sheila Sheth, Mark D. Ebert, Elliot K. Fishman
    AJR 2010; 19 4:336–346 
  • “Fibrosing mediastinitis  is  a  rare  histologically  benign  disorder caused by proliferation of collagen tissue  and  fibrosis  in  the  mediastinum.  It  may be idiopathic, caused by an abnormal immunologic response to Histoplasma capsulatum infection or to tuberculosis, or it may be related  to  retroperitoneal  fibrosis,  particularly in its diffuse form. Radiation-induced fibro-sis is another potential cause of superior vena cava obstruction.”
    Superior Vena Cava Obstruction Evaluation With MDCT
    Sheila Sheth, Mark D. Ebert, Elliot K. Fishman
    AJR 2010; 19 4:336–346 
  • “The incidence of catheter-induced supe-rior vena cava obstruction is rapidly increasing. Large  central  venous  catheters,  such  as  dialysis catheters, Hickman catheters, and parenter-al nutrition catheters, have all been implicated in superior vena cava obstruction. Transvenous permanent  cardiac  pacemaker  implantation  is another  risk  factor,  particularly  after  an  atrio-ventricular node ablation procedure.”
    Superior Vena Cava Obstruction Evaluation With MDCT
    Sheila Sheth, Mark D. Ebert, Elliot K. Fishman
    AJR 2010; 19 4:336–346 
  • “The  azygos  and  hemiazygos veins  can  divert  blood  away  from  the  superior  vena  cava.  If  the  level  of  superior  vena cava  obstruction  is  above  the  azygos  arch, antegrade  flow  from  the  azygos  to  the  right atrium  is  seen,  with  abrupt  transition  between  a  densely  opacified  azygos  above  the arch and an unopacified inferior azygos vein. If  the  obstruction  is  below  the  arch,  the  entire azygos and hemiazygos veins are bright-ly  opacified  as  the  blood  flows  in  a  retro-grade  fashion  toward  the  inferior  vena  cava .”
    Superior Vena Cava Obstruction Evaluation With MDCT
    Sheila Sheth, Mark D. Ebert, Elliot K. Fishman
    AJR 2010; 19 4:336–346 
  • “Castleman disease is a rare lymphoproliferative disease commonly occurring as a benign localized mass of lymph nodes in the mediastinum. Given that Castleman disease presents as asymptomatic or through non-specific thoracic symptoms, detection is considered complex. Ultimately, surgical resection is the preferred course of action with a greater than 90% relapse-free survival and no malignant transformation reported.”
    CT of Castleman disease in the mediastinum.  
    Lugo-Fagundo E, Lugo-Fagundo C, Weisberg EM, Fishman EK.  
    Radiol Case Rep. 2023 Jan 11;18(3):1161-1163
  • “Castleman disease (CD), also known as angiofollicular lymph node hyperplasia or lymph node hyperplasia, was originally described as a benign lymph-node hyperplasia resembling thymoma by Benjamin Castleman in 1954 . With the majority of cases located in the chest (70%) along the tracheobronchial tree in the mediastinum or lungs, other common sites of presentation include the neck, pelvis, retroperitoneum, and muscle . Given that patients are usually asymptomatic or present with non-specific symptoms, and there is no significant sex predominance or distinguishable risk factor in its development, CD is considered a challenging preoperative diagnosis and a definite verdict is not established until after tumor resection.”
    CT of Castleman disease in the mediastinum.  
    Lugo-Fagundo E, Lugo-Fagundo C, Weisberg EM, Fishman EK.  
    Radiol Case Rep. 2023 Jan 11;18(3):1161-1163
  • Castleman disease is a rare nonmalignant lymphoproliferative disorder. Clinically, CD is characterized as either multicentric CD (MCD), meaning that it involves multiple lymphatic regions, or unicentric CD (UCD), involving a single lymph node or one region of lymph nodes . While UCD is clinically more predominant, MCD, which has a less favorable prognosis, is divided into 3 subgroups: human herpes virus-8-associated MCD disease, idiopathic MCD, and polyneuropathy, organomegaly, endocrinopathy, monoclonal gammopathy, and skin changes-associated MCD. Furthermore, CD is distinguished by 2 pathological subtypes, the plasma cell and hyaline-vascular variants
    CT of Castleman disease in the mediastinum.  
    Lugo-Fagundo E, Lugo-Fagundo C, Weisberg EM, Fishman EK.  
    Radiol Case Rep. 2023 Jan 11;18(3):1161-1163
  • With an estimated annual incidence of 4,900 to 6,000 patients in the United States, unicentric CD accounts for approximately 70% of patients with CD and is typically found in adults between the ages of 30-40, with a faint prevalence among women [6,9]. The typical locations of emergence include the chest (29%), neck (23%), abdomen (21%), and retroperitoneum (17%), as well as the axilla, pelvis, and groin, with rare involvement seen in the lungs, trachea, esophagus, and the spleen. Additionally, most patients present with localized, asymptomatic adenopathy. Surgical resection is the treatment of choice, with radiotherapy considered as an alternative in instances where the mass is unresectable. In the case of inflammation, rituximab, steroids, and embolization are also deemed viable treatment options
    CT of Castleman disease in the mediastinum.  
    Lugo-Fagundo E, Lugo-Fagundo C, Weisberg EM, Fishman EK.  
    Radiol Case Rep. 2023 Jan 11;18(3):1161-1163
Deep Learning

  • “In summary, AI poses challenges for applying tort principles. Because it is primarily plaintiffs who will struggle, liability worries may be outsized during this period of adolescence for software- related tort doctrine. However, we believe that this situation cannot hold. Tort doctrine will evolve to address needs arising from technological changes, as it has historically.”
    Understanding Liability Risk from Using Health Care Artificial Intelligence Tools
    Michelle M. Mello, J.D., Ph.D., and Neel Guha, M.S.
    n engl j med 390;3 nejm.org January 18, 2024
  • “Third, across all case clusters, the reluctance by courts to distinguish “AI” from “traditional” software suggests that rules or approaches that courts create in AI-related cases may have spillover effects on non-AI software (and vice versa), although technical differences may make them ill-suited to another type of model. For example, courts might relax requirements for proving design defects, although not all software models present opacity problems.”
    Understanding Liability Risk from Using Health Care Artificial Intelligence Tools
    Michelle M. Mello, J.D., Ph.D., and Neel Guha, M.S.
    n engl j med 390;3 nejm.org January 18, 2024
  • “A framework to support health care organizations and clinicians in assessing AI liability risk is provided in Figure 1. The framework incorporates our findings regarding how courts evaluate claims related to software errors and broadens the lens to include assessment of the likelihood that claims will be brought. Drawing on previous conceptual work in safety science and malpractice claiming dynamics, we conceptualized risk as a function of the following four factors: the likelihood and nature of model errors, the likelihood that humans or another system will detect the errors and prevent harm, the potential harm if errors are not caught, and the likelihood that injuries would garner compensation in the tort system.”
    Understanding Liability Risk from Using Health Care Artificial Intelligence Tools
    Michelle M. Mello, J.D., Ph.D., and Neel Guha, M.S.
    n engl j med 390;3 nejm.org January 18, 2024
  • “While awaiting clarification of how tort doctrine will evolve to address AI, health care organizations and clinicians can take several steps to manage liability uncertainty. One such step is to resist the temptation to lump all applications of AI together. Adoption decisions and postdeployment monitoring should reflect the fact that some tools are riskier than others. When tools have the hallmarks of high liability risk that we have identified (e.g., low opportunity to catch the error, high potential for patient harm, and unrealistic assumptions about clinician behavior), organizations should expect to allocate substantial time and resources to safety monitoring and gather considerable information from model developers and implementation teams. In contrast, for lower-risk tools, organizations may be able to apply more generalized, lower-touch monitoring.”
    Understanding Liability Risk from Using Health Care Artificial Intelligence Tools
    Michelle M. Mello, J.D., Ph.D., and Neel Guha, M.S.
    n engl j med 390;3 nejm.org January 18, 2024
  • “When models are developed in house, there is no external developer to assume legal obligations; having adequate insurance is therefore critical.29 Professional liability insurers may impose coverage exclusions for AI-related injuries, and cyber policies may cover only economic losses, not physical injuries. Organizations should ensure that their coverage is not limited in these ways and is deep enough to cover worst-case scenarios in which a systematic error affects many patients.”
    Understanding Liability Risk from Using Health Care Artificial Intelligence Tools
    Michelle M. Mello, J.D., Ph.D., and Neel Guha, M.S.
    n engl j med 390;3 nejm.org January 18, 2024
  • “Health care organizations should also anticipate the evidentiary problems that may arise in AI litigation. AI models may be frequently updated in order to account for distribution shift, yet litigation will require that parties be able to reproduce past predictions. Our reviewed cases included instances in which failure to appropriately track software versions or types prolonged litigation. Model inputs, outputs, and versions should be documented at the time of care, along with the reasons that clinicians followed or departed from model recommendations.”
    Understanding Liability Risk from Using Health Care Artificial Intelligence Tools
    Michelle M. Mello, J.D., Ph.D., and Neel Guha, M.S.
    n engl j med 390;3 nejm.org January 18, 2024
  • “It is also useful for health care organizations to recognize that the defense of AI cases may require different expertise than what malpractice defense counsel are accustomed to needing. Our case review suggests the question of who qualifies as a health care AI expert is far from settled. In addition to cultivating relationships with expert witnesses in computer science, counsel will need to develop sufficient familiarity with AI methods to be able to quarterback a legal defense.”
    Understanding Liability Risk from Using Health Care Artificial Intelligence Tools
    Michelle M. Mello, J.D., Ph.D., and Neel Guha, M.S.
    n engl j med 390;3 nejm.org January 18, 2024
  • “It also may be prudent to inform patients when AI models are used in diagnostic or treatment decisions. In evaluating claims alleging breach of informed consent, many jurisdictions apply a patient-centered standard to decide what constitutes material information that should have been disclosed, and unlike with other software, surveys indicate a majority of U.S. residents feel uncomfortable about AI being used in their care. If use of AI is documented in the medical record, it will come to light during litigation; disclosure to patients reduces the risk that plaintiffs will add informed-consent claims in response. A reasonable disclosure might include what function the model serves, what shortcomings are known, how the team uses output inlight of shortcomings, and why they believe that its use improves care.”
    Understanding Liability Risk from Using Health Care Artificial Intelligence Tools
    Michelle M. Mello, J.D., Ph.D., and Neel Guha, M.S.
    n engl j med 390;3 nejm.org January 18, 2024
  • “AI has entered the medical field so rapidly and unobtrusively that it seems as if its interactions with the profession have been accepted without due diligence or in-depth consideration. It is clear that AI applications are being developed with the speed of lightning, and from recent publications it becomes frightfully apparent what we are heading for and not all of this is good. AI may be capable of amazing performance in terms of speed, consistency, and accuracy, but all of its operations are builton knowledge derived from experts in the field.”
    AI's Threat to the Medical Profession.  
    Fogo AB, Kronbichler A, Bajema IM.  
    JAMA. 2024 Jan 19. doi: 10.1001/jama.2024.0018. Epub ahead of print. 
  • This era will show a decrease in intellectual debates among colleagues, a sign of the time that computer scientists have already warned us about. While authors of literature are fighting for regulations to control the usage of AI in art, physicians should contemplate how to take advantage of the potential benefits from AI in medicine without losing control over their profession. With the issue of a landmark Executive Order8 in the US to ensure that America leads the way in managing the risks of AI and the EU becoming the first continent to set clear rules for the use of AI, physicians should realize that keeping AI within boundaries is essential for the survival of their profession and for meaningful progress in diagnosis and understanding of disease mechanisms.
    AI's Threat to the Medical Profession.  
    Fogo AB, Kronbichler A, Bajema IM.  
    JAMA. 2024 Jan 19. doi: 10.1001/jama.2024.0018. Epub ahead of print. 
  • The integration of artificial intelligence (AI) into dental care holds the promise of revolutionizing the field by enhancing the accuracy of dental diagnosis and treatment. This paper explores the impact of AI in dental care, with a focus on its applications in diagnosis, treatment planning, and patient engagement. AI-driven dental imaging and radiography, computer-aided detection and diagnosis of dental conditions, and early disease detection and prevention are discussed in detail. Moreover, the paper delves into how AI assists in personalized treatment planning and provides predictive analytics for dental care. Ethical and privacy considerations, including data security, fairness, and regulatory aspects, are addressed, highlighting the need for a responsible and transparent approach to AI implementation. Finally, the paper underscores the potential for a collaborative partnership between AI and dental professionals to offer the best possible care to patients, making dental care more efficient, patient-centric, and effective. The advent of AI in dentistry presents a remarkable opportunity to improve oral health outcomes, benefiting both patients and the healthcare community.
    A New Era of Dental Care: Harnessing Artificial Intelligence for Better Diagnosis and Treatment  
    Aastha Mahesh Batra , Amit Reche
    Cureus 15(11): e49319. DOI 10.7759/cureus.49319
  • Enhanced accuracy: AI in dentistry can process vast amounts of dental data, including X-rays, images, and patient records, with exceptional precision. AI algorithms can detect subtle abnormalities and patterns that may go unnoticed by human clinicians. This enhanced accuracy can lead to more precise and early diagnoses of dental conditions, ultimately improving patient outcomes. For example, AI can help identify cavities, gum diseases, or oral cancer at earlier stages when treatment is more effective [6].  
    Efficiency: AI automates various routine tasks in dental practices, such as data entry, image analysis, and appointment scheduling. This automation significantly reduces the time required for administrative work, allowing dental professionals to focus more on patient care. It also minimizes the chances of human error in tasks such as record-keeping, which can substantially impact the efficiency and accuracy of the practice [6].
    A New Era of Dental Care: Harnessing Artificial Intelligence for Better Diagnosis and Treatment  
    Aastha Mahesh Batra , Amit Reche
    Cureus 15(11): e49319. DOI 10.7759/cureus.49319
  • Personalized care: AI systems can analyze a patient's dental history and health data to create highly personalized treatment plans. AI can recommend specific oral hygiene routines and preventive measures by considering individual patient needs. This tailored approach ensures that patients receive care well-suited to their unique circumstances, which can lead to improved oral health outcomes [3].  
    Early detection and prevention: AI-powered algorithms can detect oral health issues early. For instance, AI can identify signs of dental decay or periodontal disease before they become symptomatic. This early detection allows for timely intervention and the implementation of preventive measures. Preventing dental problems from progressing to more serious stages benefits the patient's health and can also reduce the longterm cost of treatment [7].
    A New Era of Dental Care: Harnessing Artificial Intelligence for Better Diagnosis and Treatment  
    Aastha Mahesh Batra , Amit Reche
    Cureus 15(11): e49319. DOI 10.7759/cureus.49319
  • Improved patient experience: AI-driven patient engagement tools are vital in enhancing the patient experience. These tools can facilitate communication between patients and dental professionals, providing educational resources to help patients understand their treatment options and oral health. AI-driven chatbots or virtual assistants can also assist patients in scheduling appointments, sending reminders, and answering common queries, making it easier for patients to engage with their dental care. Ultimately, this improves patient satisfaction and compliance with recommended treatments and follow-up appointments
    A New Era of Dental Care: Harnessing Artificial Intelligence for Better Diagnosis and Treatment  
    Aastha Mahesh Batra , Amit Reche
    Cureus 15(11): e49319. DOI 10.7759/cureus.49319
  • Image enhancement: AI algorithms can enhance dental images by improving the clarity and visibility of details. This can be particularly valuable in dental radiography, where subtle anomalies might not be easily discernible in standard images. Dental professionals can use AI for image enhancement to identify potential dental issues more effectively, even in challenging cases. Enhanced images can reveal finer details, aiding in the early detection and diagnosis of dental conditions [13]. Image analysis: AI's image analysis capabilities are crucial in automating the identification of common dental conditions. For example, AI can be trained to recognize and diagnose cavities, periodontal diseases, impacted teeth, and other dental anomalies in radiographs and intraoral images. This improves the speed and accuracy of diagnoses and ensures that dental professionals do not overlook any important findings, contributing to better patient care and outcomes [7].  
    Automation: AI can assist in automating various aspects of the radiographic process. This includes capturing images, positioning X-ray equipment, and ensuring image quality. Automation reduces the workload on dental staff and minimizes the potential for human error. By maintaining consistent imaging techniques and quality across different patients, AI can help produce more reliable diagnostic images and improve patient care [14].  
    A New Era of Dental Care: Harnessing Artificial Intelligence for Better Diagnosis and Treatment  
    Aastha Mahesh Batra , Amit Reche
    Cureus 15(11): e49319. DOI 10.7759/cureus.49319
  • In conclusion, integrating artificial intelligence (AI) into dental care marks the dawn of a transformative era. The profound impact of AI on dental diagnosis and treatment is indisputable, presenting myriad benefits. These range from elevating the precision of dental imaging and facilitating computer-aided detection and diagnosis to streamlining personalized treatment planning and predicting patient outcomes. These advancements can revolutionize dentistry, rendering it more efficient, patient-centric, and effective. However, it is imperative to emphasize the necessity for a collaborative synergy between AI and dental professionals. Specifically, it would be valuable to delve into concrete ways in which dental practitioners and AI can collaboratively ensure AI's responsible and ethical use in patient care. AI should be positioned as a complementary tool that enhances the expertise of dental practitioners rather than a replacement. By fostering a partnership between AI and dental experts, we can guarantee this technology's responsible and ethical application, upholding the highest standards of patient privacy and data security. This collaborative approach enhances patient care and contributes to a brighter and healthier future for dental practice, benefiting patients, practitioners, and the healthcare system at large.
    A New Era of Dental Care: Harnessing Artificial Intelligence for Better Diagnosis and Treatment  
    Aastha Mahesh Batra , Amit Reche
    Cureus 15(11): e49319. DOI 10.7759/cureus.49319
  • We found that provider number of years in practice (DATA), awareness of challenges related to MCED testing (DATA), and perceived competence in MCED test use (DATA) were positively and significantly associated with receptivity to MCED test use in practice. An exploratory factor analysis extracted two components: receptivity to MCEDs and awareness of challenges. Surprisingly, these factors had a positive correlation (r = 0.124, p = 0.024). Providers’ perceived competence in using MCED tests and providers’ experience level were significantly associated with receptivity to MCED testing. While there was strong agreement with potential challenges to implementing MCEDs, PCPs were generally receptive to using MCEDs in cancer screening. Keeping PCPs updated on the evolving knowledge of MCEDs is likely critical to building receptivity to MCED testing.
    Primary Care Provider Receptivity to Multi-Cancer Early Detection Test Use in Cancer Screening
    Christopher V. Chambers et al
    J. Pers. Med.2023, 13, 1673. https://doi.org/10.3390/jpm13121673
  • We found that PCPs are generally receptive to the idea of incorporating MCED testing into their routine practice for cancer screening. This is in contrast to previous research that found that PCPs had concerns about potential problems associated with genetic testing as a screening tool. In particular, they reported insufficient confidence in their ability to order genetic testing and uncertainty around the clinical benefits of this testing as a screening method in low risk patients . In contrast with other genetic testing, MCEDs appear to have a more clearly defined place in the practice of primary care . MCED testing may represent a role for genetic testing for which PCPs can better understand the management of the results and their ability to explain them to their patients.
    Primary Care Provider Receptivity to Multi-Cancer Early Detection Test Use in Cancer Screening
    Christopher V. Chambers et al
    J. Pers. Med.2023, 13, 1673. https://doi.org/10.3390/jpm13121673
  • Not surprisingly, PCPs endorsed many of the items in the survey that related to potential challenges to the introduction of MCED testing into their practice. Several of these related to the amount of time that a discussion of MCED testing and the handling of the results would likely impose on an already busy patient schedule. Others related to concerns about the patient. These included whether patients would complete the additional testing associated with a positive test result and whether insurance would cover these recommended tests and procedures. Previous research has shown that patients often fail to complete recommended follow-up after a positive finding on conventional screening  and that these delays may result in a new cancer diagnosis. The cost of the currently available MCED test alone will be outside the reach of many patients.
    Primary Care Provider Receptivity to Multi-Cancer Early Detection Test Use in Cancer Screening
    Christopher V. Chambers et al
    J. Pers. Med.2023, 13, 1673. https://doi.org/10.3390/jpm13121673
  • In summary, we found that PCPs in the study were generally receptive to the idea of incorporating MCED testing into their practice of screening for cancer. While they acknowledged the potential challenges to using MCED testing and the additional time that they would need to spend on ordering MCED testing and managing the results, the respondents signaled that they were receptive to MCED testing for cancer screening. Introducing MCED testing into routine screening for cancer will likely mean that the visits with the PCP will take longer or that other trained staff will need to be involvedin the patient education process.
    Primary Care Provider Receptivity to Multi-Cancer Early Detection Test Use in Cancer Screening
    Christopher V. Chambers et al
    J. Pers. Med.2023, 13, 1673. https://doi.org/10.3390/jpm13121673 
  • Cinematic rendering is a 3D reconstruction technique inspired by the animated movie industry. It follows the same steps used for volume rendering in determining colour and opacity that models real-life physical propagation of light providing photorealistic 3D images with more surface details. The application of cinematic rendering in clinical practice has been described for pre-operative planning of tumours such as GIST. Originally clinical use of 3D imaging was confined to calculating organ volumes or orthopedic applications; however, the use of helical technology for the propagation of thin slice computed tomography (CT) in conjunction with advanced image reconstruction software has allowed this to be utilized for a variety of other applications. Applications for cinematic rendering have been reported to include lesion characterization, localization, and risk stratification in the pre-operative setting. 
    Utilization of Cinematic Rendering for Evaluation of Gastrointestinal Stromal Tumours (GIST)
    Ciara O’Brien
    Canadian Association of Radiologists Journal (in press)
  • “Cinematic rendering of GIST helps demonstrate the submucosal origin of the mass and visualize the dynamic enhancement pattern within the tumour allowing for better anatomical evaluation of the lesion providing more information on areas of necrosis and enhancement. Additionally, there is increased information regarding the growth pattern, vascular supply, adjacent anatomic structures, and blood vessels which improves pre-operative planning. Active bleeding from a small bowel tumour is difficult to characterize on conventional CT. Cinematic rendering can more easily detect if there is bleeding from a small bowel tumour. It also provides increased information to differentiate GIST form other gastrointestinal tumours, especially at the ampulla and in the pelvis where anatomical detail is limited on conventional CT.”
    Utilization of Cinematic Rendering for Evaluation of Gastrointestinal Stromal Tumours (GIST)
    Ciara O’Brien
    Canadian Association of Radiologists Journal (in press)
  • “Cinematic rendering is an exciting new technique currently in its infancy that has the potential to add great value to our practice. To fulfill the advice of Dr Brady: to move forward and keep up, the next step should be to investigate how to implement cinematic rendering into our day-to-day practice.”
    Utilization of Cinematic Rendering for Evaluation of Gastrointestinal Stromal Tumours (GIST)
    Ciara O’Brien
    Canadian Association of Radiologists Journal (in press)
  • The applications of AI for imaging of CAD using CT span multiple arenas including plaque detection, plaque characterization, improving risk stratification, and clinical decision-making. AI has been applied to both CAC scoring and CCTA. Studies have shown the ability of AI to detect hemodynamically significant stenosis across a broad range of imaging parameters and its potential ability to decrease the time needed for analysis of images for stenosis. AI can significantly reduce the time to perform quantitative plaque analysis, an important barrier to its application in clinical practice.
    Coronary Artery Disease: Role of Computed Tomography and Recent Advances
    Elizabeth Lee et al
    Radiol Clin N Am - (2024 (in press)
  • “One trial of AI-based CCTA interpretation in patients with stable chest pain referred for ICA found a lower cost compared with conventional interpretation due to lower rates of referral for ICA, without impacting the occurrence of cardiac events. A comprehensive review of all potential applications for AI in CT imaging of CAD is beyond the scope of this review; however, AI is certain to change how imaging is ordered, performed, and interpreted in the near future.”  
    Coronary Artery Disease: Role of Computed Tomography and Recent Advances
    Elizabeth Lee et al
    Radiol Clin N Am - (2024 (in press)
  • “Moreover, AI is playing a crucial role in personalized medicine. By analyzing large datasets that include patient health records, genetic information, and treatment outcomes, AI algorithms can identify patterns and correlations that help tailor treatment plans to individual patients. This enables healthcare providers to deliver targeted therapies, predict disease progression, and reduce adverse effects. Additionally, AI is streamlining administrative tasks and improving operational efficiency in healthcare facilities. Natural language processing (NLP) algorithms can automate tasks like medical coding and documentation, reducing the burden on healthcare professionals and minimizing errors. AI chatbots are being used to provide patients with round-the-clock assistance, answer their queries, schedule appointments, and even provide basic medical advice.”
    From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer
    Satvik Tripathi et al.
    Diagnostics 2024, 14, 174. https://doi.org/10.3390/diagnostics14020174

  • From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer
    Satvik Tripathi et al.
    Diagnostics 2024, 14, 174. https://doi.org/10.3390/diagnostics1402017
  • “Overall, ML techniques, including supervised learning algorithms like support vector machines and random forests, as well as unsupervised learning techniques like clustering and dimensionality reduction, are very valuable in pancreatic cancer research. They enable researchers to extract meaningful insights from complex datasets, improve diagnostic accuracy, predict patient outcomes, and facilitate personalized treatment strategies.”  
    From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer
    Satvik Tripathi et al.
    Diagnostics 2024, 14, 174. https://doi.org/10.3390/diagnostics14020174
  • “We can also utilize CNNs for lesion detection and localization for automated identification of anomalous or dubious regions in medical imagery. The application of computer vision techniques in pancreatic cancer research has the potential to facilitate the identification and localization of pancreatic tumors and other lesions. Through the automated identification of these regions, medical professionals can concentrate their efforts on the specific areas of concern, thereby enabling enhanced precision in diagnosis and treatment strategizing. These algorithms can also help classify tumors into distinct subtypes or determine their malignancy by extracting pertinent features from medical images, such as texture, shape, or intensity patterns. These extracted data hold significant value in terms of prognostication, informing treatment choices, and forecasting patient results.”
    From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer
    Satvik Tripathi et al.
    Diagnostics 2024, 14, 174. https://doi.org/10.3390/diagnostics14020174
  • “The early detection of pancreatic cancer is a critical factor in improving patient outcomes, as it is often diagnosed at an advanced stage when treatment options are limited. AI has the potential to aid in the early detection of pancreatic cancer by analyzing medical data and identifying patterns that may indicate the presence of the disease. Deep learning techniques can be trained on large datasets to accurately identify early stage pancreatic cancer based on characteristic imaging features or use morphology features to build segmentation frameworks for the pancreas. AI algorithms can integrate various patient data, such as age, family history, lifestyle factors, and medical history, to detect an individual’s developing pancreatic cancer early. AI can also analyze a patient’s electronic health records, including medical history, laboratory results, and diagnostic reports, to identify potential indicators of pancreatic cancer. By processing and interpreting vast amounts of data, AI algorithms can detect subtle patterns and abnormalities that may go unnoticed by clinicians.”
    From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer
    Satvik Tripathi et al.
    Diagnostics 2024, 14, 174. https://doi.org/10.3390/diagnostics14020174
  • However, finding reliable and specific biomarkers for pancreatic cancer is challenging due to the heterogeneity and complexity of the disease, the lack of adequate samples, and the interference of confounding factors . AI can help overcome these challenges by applying advanced computational methods to analyze large and diverse datasets of biomolecular information, such as genomics, proteomics, metabolomics, or microbiomics. AI can also integrate multiple types of data from the pancreas to identify novel biomarkers or biomarker signatures that have higher sensitivity and specificity than single biomarkers . A deep learning model based on multimodal neural networks (MNNs) was proposed to combine imaging data (WSI), gene expression data, clinical data (age, gender, tumor location), and biomarker data (mi-RNA) to forcast the survival of pancreatic cancerpatients.
    From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer
    Satvik Tripathi et al.
    Diagnostics 2024, 14, 174. https://doi.org/10.3390/diagnostics14020174 
  • “AI can serve as a powerful tool in the advancement of pancreatic cancer diagnosis, management, and prognosis, particularly in identifying tumors earlier in disease progression. Despite the many applications and advantages of AI in pancreatic cancer, multiple limitations pose challenges that must be addressed as the field grows. One is the lack of a standardized approach to treatment and diagnosis. Other challenges include a lack of robust and high-quality data, transparency and reproducibility of findings, and ethical considerations, including biases in algorithms.”
    From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer
    Satvik Tripathi et al.
    Diagnostics 2024, 14, 174. https://doi.org/10.3390/diagnostics14020174
  • “Furthermore, AI algorithms have been previously referred to as “Black boxes” due to their lack of transparency and interpretability. The opacity of the code used to build AI models and the hidden level of complexity make it difficult to reproduce results in an independent manner. General descriptions of the code used to build models do not provide enough information to reproduce most findings. The lack of easy interpretation of these AI models and prospective studies assessing AI-based tools has increased the hesitancy of adaptation into clinical practice. Without transparency andinterpretation, clinicians are not able to critically interrogate the output of these models, putting an incredible amount of faith in the accuracy of the model.”  
    From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer
    Satvik Tripathi et al.
    Diagnostics 2024, 14, 174. https://doi.org/10.3390/diagnostics14020174
  • “Additionally, the creation and use of large datasets needed to create AI models pose the challenging questions of data ownership and patient privacy, particularly inreference to medical imaging. At the same time, the integration of AI systems in medical practices raises questions about the security and confidentiality of sensitive patient data. Ensuring robust data protection mechanisms is imperative to prevent unauthorized access and potential misuse of personal health information. Additionally, ethical challenges encompass issues such as algorithmic bias, transparency, and accountability. Addressing these challenges requires the establishment of ethical guidelines and regulatory frameworks that prioritize fairness, transparency, and the responsible use of AI technologies. Striking a balance between innovation and ethical considerations is essential to foster public trust and promote the responsible adoptionof AI in healthcare, ultimately ensuring that advancements in technology benefit patientswithout compromising their privacy or perpetuating existing healthcare disparities.” 
  • “Additionally, ethical challenges encompass issues such as algorithmic bias, transparency, and accountability. Addressing these challenges requires the establishment of ethical guidelines and regulatory frameworks that prioritize fairness, transparency, and the responsible use of AI technologies. Striking a balance between innovation and ethical considerations is essential to foster public trust and promote the responsible adoptionof AI in healthcare, ultimately ensuring that advancements in technology benefit patientswithout compromising their privacy or perpetuating existing healthcare disparities.”
    From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer
    Satvik Tripathi et al.
    Diagnostics 2024, 14, 174. https://doi.org/10.3390/diagnostics14020174
  • In order to convert AI research into clinical practice, robust validation studies in pancreatic cancer are required to establish the clinical efficacy, safety, and cost-effectiveness of AI-based methods. Large-scale prospective studies should be conducted in the future to evaluate the performance of AI algorithms in realworld healthcare situations. Furthermore, regulatory and ethical factors such as privacy protection, informed consent, and algorithm transparency must be addressed to enable responsible and fair AI technology implementation in healthcare.  
    From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer
    Satvik Tripathi et al.
    Diagnostics 2024, 14, 174. https://doi.org/10.3390/diagnostics14020174
  • • [18F] Fluorodeoxyglucose18F-FDG) PET/CT can improve the staging accuracy and clinical management of patients with hepatobiliary and pancreatic cancers, by detection of unsuspected metastases.  
    • 18F-FDG PET/CT metabolic parameters are valuable in predicting treatment response and survival.  
    • Metabolic response on 18F-FDG PET/CT can predict preoperative pathologic response to neoadjuvant therapy in patients with pancreatic cancer and determine prognosis.  
    • Several novel non-FDG tracers, such as 68-Ga prostate-specific membrane antigen and 68Gafibroblast activation protein inhibitor PET/CT, show promise for imaging hepatobiliary and pancreatic cancers with potential for radioligand therapy.
    Quarter-Century PET/ Tomography Transformation of Oncology Hepatobiliary and Pancreatic Cancer
    Asha Kandathil et al.
    PET Clin (in press) 2024
  • “18F-FDG PET/CT has reported sensitivity of 85%to 100%, specificity of 61% to 94%, and accuracy of 84% to 95% in diagnosing pancreatic cancer.39–42 FDG uptake by pancreatic cancer correlates with increased Ki-67 and is highest in poorly differentiated tumors. Medium- or well-differentiated pancreatic cancers may not have increased FDG uptake. Inflammatory lesions such as chronic lymphoplasmacytic pancreatitis, autoimmune pancreatitis, and tuberculosis may have increased FDG uptake.”  
    Quarter-Century PET/ Tomography Transformation of Oncology Hepatobiliary and Pancreatic Cancer
    Asha Kandathil et al.
    PET Clin (in press) 2024
  • In a multicenter prospective study conducted in 18 UK pancreatic tertiary referral centers, Ghaneh and colleagues evaluated the performance of multidetector CT (MDCT) in 589 patients and FDG PET/CT in 550 patients with suspected pancreatic cancer. MDCT had a sensitivity of 88.5%and specificity of 70.6%; FDG PET/CT had a sensitivity of 92.7% and specificity of 75.8% for the diagnosis of pancreatic cancer. Pancreatic cancer had a higher median SUVmax of 7.5 compared with median SUVmax of 5.7 for other lesions. Adding PET/ CT to standard workup improved pancreatic cancer diagnosis, staging, and management.
    Quarter-Century PET/ Tomography Transformation of Oncology Hepatobiliary and Pancreatic Cancer
    Asha Kandathil et al.
    PET Clin (in press) 2024
  • “Surgical resection is the only curative option for pancreatic cancer; however, more than 80% of patients present unresectable disease due to locally advanced disease or distant metastases. Borderline resectable pancreatic cancer (BRPC) patients who could be eligible for radical surgery following neoadjuvant chemotherapy may have local arterial or venous (superior mesenteric vein/ portal vein) invasion.44 PET has less spatial resolution and accuracy than CT in assessing locoregional involvement, which is critical in therapeutic decision-making in pancreatic cancer. CT, MR imaging, and endoscopic ultrasound are better at defining tumor’s border and local spread.45 However, PET/CT performs better than CT in identifying unsuspected metastases, reducing the frequency of futile surgeries.”
    Quarter-Century PET/ Tomography Transformation of Oncology Hepatobiliary and Pancreatic Cancer
    Asha Kandathil et al.
    PET Clin (in press) 2024
  • “In a study of the utility of 18F-FDG PET/CT in assessing treatment response in 20 patients with LAPC treated with neoadjuvant chemo-RT, Choi and colleagues observed that mean survival was longer (23.2 months) in patients with   50% decrease in SUV between pre-study PET scan and PET scan after the first cycle of chemotherapy, as compared with 11.3 months in patients with less than 50% decrease in SUV.”  
    Quarter-Century PET/ Tomography Transformation of Oncology Hepatobiliary and Pancreatic Cancer
    Asha Kandathil et al.
    PET Clin (in press) 2024
  • Background: Chest radiography remains the most common radiologic examination, and interpretation of its results can be difficult.
    Purpose: To explore the potential benefit of artificial intelligence (AI) assistance in the detection of thoracic abnormalities on chest radiographs by evaluating the performance of radiologists with different levels of expertise, with and without AI assistance.
    Materials and Methods: Patients who underwent both chest radiography and thoracic CT within 72 hours between January 2010 and December 2020 in a French public hospital were screened retrospectively. Radiographs were randomly included until reaching 500 radiographs, with about 50% of radiographs having abnormal findings. A senior thoracic radiologist annotated the radiographs for five abnormalities (pneumothorax, pleural effusion, consolidation, mediastinal and hilar mass, lung nodule) based on the corresponding CT results (ground truth). A total of 12 readers (four thoracic radiologists, four general radiologists, four radiology residents) read half the radiographs without AI and half the radiographs with AI (ChestView; Gleamer). Changes in sensitivity and specificity were measured using paired t tests.
    Using AI to Improve Radiologist Performance in Detection of Abnormalities on Chest Radiographs
    Souhail Bennani et al.
    Radiology 2023; 309(3):e230860
  • Results: The study included 500 patients (mean age, 54 years Å} 19 [SD]; 261 female, 239 male), with 522 abnormalities visible on 241 radiographs. On average, for all readers, AI use resulted in an absolute increase in sensitivity of 26% (95% CI: 20, 32), 14% (95% CI: 11, 17), 12% (95% CI: 10, 14), 8.5% (95% CI: 6, 11), and 5.9% (95% CI: 4, 8) for pneumothorax, consolidation, nodule,  pleural effusion, and mediastinal and hilar mass, respectively (P < .001). Specificity increased with AI assistance (3.9% [95% CI: 3.2, 4.6], 3.7% [95% CI: 3, 4.4], 2.9% [95% CI: 2.3, 3.5], and 2.1% [95% CI: 1.6, 2.6] for pleural effusion, mediastinal and hilar mass, consolidation, and nodule, respectively), except in the diagnosis of pneumothorax (−0.2%; 95% CI: −0.36, −0.04; P = .01). The mean reading time was 81 seconds without AI versus 56 seconds with AI (31% decrease, P < .001).
    Conclusion: AI-assisted chest radiography interpretation resulted in absolute increases in sensitivity for all radiologists of various levels ofexpertise and reduced the reading times; specificity increased with AI, except in the diagnosis of pneumothorax.  
    Using AI to Improve Radiologist Performance in Detection of Abnormalities on Chest Radiographs
    Souhail Bennani et al.
    Radiology 2023; 309(3):e230860
  • Summary
    Artificial intelligence assistance can improve the detection accuracy of thoracic abnormalities on chest radiographs across radiologists with varying levels of expertise, leading to marked improvements in sensitivity and a reduction in interpretation time.
    Key Results
    ■ In a retrospective study of 500 patients who underwent chest radiography and thoracic CT for all abnormality types, artificial intelligence (AI)-assisted chest radiography interpretation resulted in increased sensitivity of 6%–26% (P < .001) for all readers, including thoracic radiologists, general radiologists, and radiology residents.
    ■ Mean reading time was 81 seconds without AI versus 56 seconds with AI (a decrease of 31%, P < .001), with a 17% reduction for radiographs with abnormalities versus a 38% reduction for radiographs with no abnormalities.
    Using AI to Improve Radiologist Performance in Detection of Abnormalities on Chest Radiographs
    Souhail Bennani et al.
    Radiology 2023; 309(3):e230860
  • Our results showed that AI assistance resulted in absolute increases in sensitivity for all readers of various levels of experience, including general radiologists and radiology residents, in detecting all five types of abnormalities on chest radiographs: from 5.3% for mediastinal and hilar mass to 25.3% for pneumothorax (P < .001). Specificity increased with AI assistance (from 2.1% [95% CI: 1.6, 2.6] for nodule to 3.9% [95% CI: 3.2, 4.6]), except in the diagnosis of pneumothorax (−0.2%; 95% CI: −0.36, −0.04; P = .01). Although unassisted thoracic radiologists outperformed unassisted general radiologists for the five abnormality types, assisted thoracic radiologists solely outperformed assisted general radiologists in the detection of consolidations (73.9% [95% CI: 67, 80] vs 70.5% [95% CI: 64, 77]; P = .01). Finally, the mean reading time was 81 seconds without AI versus 56 seconds with AI, for a 31% reduction (P < .001), with 17% reduction for radiographs with abnormalities and 38% reduction for radiographs with no abnormalities.
    Using AI to Improve Radiologist Performance in Detection of Abnormalities on Chest Radiographs
    Souhail Bennani et al.
    Radiology 2023; 309(3):e230860
  • ‘In regard to the impact of AI on reading time, there are conflicting data, with some reports citing a 10% reduction in reading time and others citing an increase of more than 100%. In our study, the 31% decrease in reading time was more important than previously reported. As in the study by Shin et al, we observed that the time saved in reading is greater for radiographs without abnormalities, which represent the majority of chest radiographs in clinical practice.”  
    Using AI to Improve Radiologist Performance in Detection of Abnormalities on Chest Radiographs
    Souhail Bennani et al.
    Radiology 2023; 309(3):e230860
  • Application: Prior health AI applications often centered around diagnostics, but thereare many low-risk yet high-value scenarios across the entire health system that are ripe for impact
    Evaluation: Real-world use cases are often under-represented in existing health AI benchmarks; scaling realistic benchmark creation and evaluation is of increasing urgency
    Modeling: Unlike standard contrastive learning, multimodal generative AI can benefit from gravitating in text as the “interlingua” of all modalities, given the vast amount of human knowledge captured in state-of-the-art large language models.
    Multimodal Generative AI for Precision Health
    Hoifung Poon
    NEJM AI (in press)
Kidney

  • Methods The latest available ACR Appropriateness Recommendations, AUA guidelines, and CUA guidelines were reviewed. AUA and CUA guidelines imaging recommendations by variants and level of appropriateness were converted to match the style of ACR. Imaging recommendations including modality, anatomy, and requirement for contrast were recorded.
    Results Clinical variants included microhematuria without risk factors, microhematuria with risk factors, gross hematuria, and microhematuria during pregnancy. CUA recommends ultrasound kidneys as the first-line imaging study in the first 3 variants; pregnancy is not explicitly addressed. For hematuria without risk factors, ACR does not routinely recommend imaging, while AUA recommends shared decision-making to decide repeat urinalysis versus cystoscopy with ultrasound kidneys. For hematuria with risk factors and gross hematuria, ACR recommends CT urography; MR urography can also be considered in gross hematuria. AUA further stratifies intermediate- and high-risk patients, for which ultrasound kidneys and CT urography are recommended, respectively. For pregnancy, ACR and AUA both recommend ultrasound kidneys, though AUA additionally recommends consideration of CT or MR urography after delivery.
    Discrepant guidelines in the evaluation of hematuria
    Terrell A. Brown · Justin R. Tse
    Abdominal Radiology (2024) 49:202–208
  • Conclusion There is no universally agreed upon algorithm for diagnostic evaluation. Discrepancies centered on the role of upper tract imaging with ultrasound versus CT. Prospective studies and/or repeat simulation studies that apply newly updated guidelines are needed to further clarify the role of imaging, particularly for patients with microhematuria with noand intermediate risk factors.
    Discrepant guidelines in the evaluation of hematuria
    Terrell A. Brown · Justin R. Tse
    Abdominal Radiology (2024) 49:202–208
  • “In conclusion, ACR and urologic societies have discrepant guidelines on the evaluation of hematuria, which may lead to disparate care. Prospective studies and/or repeat simulation studies that apply newly updated guidelines are needed to further clarify the role of imaging, particularly for patients with microhematuria with no and intermediate risk factors.”  
    Discrepant guidelines in the evaluation of hematuria
    Terrell A. Brown · Justin R. Tse
    Abdominal Radiology (2024) 49:202–208
  • “Epithelioid angiomyolipoma (EAML) is a subtype of angiomyolipoma with malignant potential. A diagnosis of malignant EAML of the kidney is based on extrarenal metastasis, and predicting early transformation is difficult. ”
    Primary kidney malignant epithelioid angiomyolipoma: Two cases report and review of literature.  
    Zhan R, Li YQ, Chen CY, Hu HY, Zhang C.  
    Medicine (Baltimore). 2018 Aug;97(32):e11805.
  • “Kidney AML is a common benign PEComa that consists of blood vessels, smooth muscle, and matured adipose tissue. Epithelioid AML (EAML) of the kidney is an unusual subtype of AML that is potentially malignant. EAML is mainly composed of epithelioid cells with abundant eosinophilic or granular cytoplasm, round to oval nuclei, and prominent nucleoli.[4] Some studies have suggested that malignant progression of EAML may be predicted by the percentage of epithelioid cells, and <10, 80 to 95, and 95% epithelioid cells were associated with no, low (5%), and high progression rates (51.5%), respectively.[5–7] However, it is difficult to make a definitive diagnosis of primary kidney malignant EAML, because there are no standardized judgement criteria based on clinicopathology.”
    Primary kidney malignant epithelioid angiomyolipoma: Two cases report and review of literature.  
    Zhan R, Li YQ, Chen CY, Hu HY, Zhang C.  
    Medicine (Baltimore). 2018 Aug;97(32):e11805.
  • “Kidney EAML, mainly composed of epithelioid cells, has the potential to become malignant, with aggressive characteristics. Based on the risk of malignancy, EAML may be classified into 5 groups: none, low, intermediate, high, and malignancy. EAML at low risk of malignancy is ≥7 cm, with ≥50% epithelioid component. EAML at intermediate risk has been associated with TSC, moderate atypia epithelioid cells ≥10%, ≥2/10 HPF, atypical mitosis, and extrarenal extension. High-risk EAML is characterized by severe atypia epithelioid cells ≥10%, a carcinoma-like growth pattern, and tumor necrosis. Malignancy is shown by lymphovascular invasion, lymph node metastasis, or distant metastasis.”
    Primary kidney malignant epithelioid angiomyolipoma: Two cases report and review of literature.  
    Zhan R, Li YQ, Chen CY, Hu HY, Zhang C.  
    Medicine (Baltimore). 2018 Aug;97(32):e11805.
  • Objectives To assess the accuracy of low-dose dual-energy computed tomography (DECT) to differentiate uric acid from non-uric acid kidney stones in two generations of dual-source DECT with stone composition analysis as the reference standard.  
    Methods Patients who received a low-dose unenhanced DECT for the detection or follow-up of urolithiasis and stone extraction with stone composition analysis between January 2020 and January 2022 were retrospectively included. Collected stones were characterized using X-ray diffraction. Size, volume, CT attenuation, and stone characterization were assessed using DECT post-processing software. Characterization as uric acid or non-uric acid stones was compared to stone composition analysis as the reference standard. Sensitivity, specificity, and accuracy of stone classification were computed. Dose length product (DLP) and effective dose served as radiation dose estimates
    Dual-energy CT kidney stone characterization-can diagnostic accuracy be achieved at low radiation dose?
    Euler A, Wullschleger S, Sartoretti T, Müller D, Keller EX, Lavrek D, Donati O.
    Eur Radiol. 2023 Sep;33(9):6238-6244
  • Results: A total of 227 stones in 203 patients were analyzed. Stone composition analysis identified 15 uric acid and 212 non-uric acid stones. Mean size and volume were 4.7 mm × 2.8 mm and 114 mm3, respectively. CT attenuation of uric acid stones was significantly lower as compared to non-uric acid stones (p < 0.001). Two hundred twenty-five of 227 kidney stones were correctly classified by DECT. Pooled sensitivity, specificity, and accuracy were 1.0 (95%CI: 0.97, 1.00), 0.93 (95%CI: 0.68, 1.00), and 0.99 (95%CI: 0.97, 1.00), respectively. Eighty-two of 84 stones with a diameter of ≤ 3 mm were correctly classified. Mean DLP was 162 ± 57 mGy*cm and effective dose was 2.43 ± 0.86 mSv.
    Conclusions: Low-dose dual-source DECT demonstrated high accuracy to discriminate uric acid from non-uric acid stones even at small stone sizes.
    Dual-energy CT kidney stone characterization-can diagnostic accuracy be achieved at low radiation dose?
    Euler A, Wullschleger S, Sartoretti T, Müller D, Keller EX, Lavrek D, Donati O.
    Eur Radiol. 2023 Sep;33(9):6238-6244
  • Key points:  
    • Two hundred twenty-five of 227 stones were correctly classified as uric acid vs. non-uric acid stones by low-dose dual-energy CT with stone composition analysis as the reference standard.  
    • Pooled sensitivity, specificity, and accuracy for stone characterization were 1.0, 0.93, and 0.99, respectively.  
    • Low-dose dual-energy CT for stone characterization was feasible in the majority of small stones < 3 mm.
    Dual-energy CT kidney stone characterization-can diagnostic accuracy be achieved at low radiation dose?
    Euler A, Wullschleger S, Sartoretti T, Müller D, Keller EX, Lavrek D, Donati O.
    Eur Radiol. 2023 Sep;33(9):6238-6244
  • “In conclusion, low-dose DECT demonstrated high accuracy to discriminate uric acid from non-uric acid stones even at small stone sizes. Future studies could investigate if low dose DECT can replace low-dose SECT in a prospective randomized controlled non-inferiority trial.”
    Dual-energy CT kidney stone characterization-can diagnostic accuracy be achieved at low radiation dose?
    Euler A, Wullschleger S, Sartoretti T, Müller D, Keller EX, Lavrek D, Donati O.
    Eur Radiol. 2023 Sep;33(9):6238-6244
  • “The  most  common  cause  of  ascending  pyelonephritis  is  Escherichia  coli,  while  staphylococci  and  streptococci  typically  cause  pyelonephritis  via  the  hematogenous  route.  Well-established  acute  pyelonephritis  and  abscess  formation  can  be  readily  diagnosed  from  findings  on  CT  or  MR  images.  Imaging  findings  of  diffuse  pyelophritis  including  enlarged  kidneys  with  geographic  nephrographic  defects,  striated nephrogram, and perinephric fat stranding are well described  in  radiology  literature.  However,  solitary  or  multifocal  lesions  during  the  early  phase  of  pyelonephritis  or  focal  pyelonephritis  may  masquerade  as  tumors.  Clinical  symptoms  and  supportive  laboratory  findings  including abnormal urinalysis results allow a correct diagnosis to be made. While prompt treatment results in resolution of  renal  pseudomasses,  delays  in  diagnosis  and  institution  of treatment lead to progression to frank pyelonephritis and renal or perinephric abscess formation. Temporal changes in lesion size and morphology after antibiotic therapy provide confirmatory proof of diagnosis.”
    Tumefactive Nonneoplastic Proliferative Pseudotumors of the Kidneys and Urinary Tract: CT and MRI Findings with Histopathologic Correlation
    Krishna Prasad Shanbhogue et al.
    RadioGraphics 2023; 43(12):e230071
  • “Renal  tuberculosis  (TB)  almost  always  occurs  owing  to  in-fection from Mycobacterium tuberculosis, although Mycobac-terium  bovis  may  be  rarely  involved.  Secondary  TB  occurs  owing to reactivation of latent infection after initial dissem-ination to diverse organs. Genitourinary tract TB may affect the kidneys and upper and lower urinary tracts. It may manifest after a variable latency of 5–40 years after initial in-fection (4). The diffuse miliary form of renal TB may be seen in patients with disseminated systemic infection. The genitourinary  tract  is  one  of  the  common  extrapulmonary  sites  of TB, accounting for 15%–20% of cases. It commonly affects adults in the 2nd to 4th decades of life. Dysuria, flank pain, hematuria, and sterile pyuria are common clinical manifestations.”
    Tumefactive Nonneoplastic Proliferative Pseudotumors of the Kidneys and Urinary Tract: CT and MRI Findings with Histopathologic Correlation
    Krishna Prasad Shanbhogue et al.
    RadioGraphics 2023; 43(12):e230071
  • “Diffuse  wall  thickening  and  strictures  of  the  upper  urinary  tract,  including  the  characteristic  pelvic  and  infundibular  strictures,  may  be  seen;  a  sawtooth  pattern  of  ureteral  involvement  has  been  reported.  Focal  or  diffuse  urinary  bladder wall thickening may be seen during the early stage of disease.  Marked  fibrosis  of  the  urinary  bladder  wall  results  in  a  small-capacity  bladder  referred  to  as  “thimble  bladder”. TB epididymo-orchitis and prostatitis may be seen in 70%–80% of patients with urinary tract involvement. Anti-TB chemotherapy is the standard of treatment of genitourinary tract TB.”
    Tumefactive Nonneoplastic Proliferative Pseudotumors of the Kidneys and Urinary Tract: CT and MRI Findings with Histopathologic Correlation
    Krishna Prasad Shanbhogue et al.
    RadioGraphics 2023; 43(12):e230071
  • “Ascending infections lead to the development of mycetoma or “fungus balls” within the urinary tract that appear as non-enhancing filling defects on CT or MR urograms, with hyper-intensity on T2-weighted images (compared with the imaging appearance of renal parenchyma or bladder wall.  Multiple  microabscesses  and  tubulointerstitial  nephritis  result  from  hematogenous  spread  of  the  fungi.  While  Candida  microabscesses  appear  as  small  hypoattenuating  or  hypointense  lesions  within  bilateral  kidneys,  mucormycosis  manifests  as  solitary  or  multiple  unilateral  hypovascular  le-sions or abscesses. Mucormycosis shows marked proclivity for angioinvasion, leading to vessel thrombosis that results in infarction and hemorrhage with resultant high mortality rates in immunocompromised patients.”
    Tumefactive Nonneoplastic Proliferative Pseudotumors of the Kidneys and Urinary Tract: CT and MRI Findings with Histopathologic Correlation
    Krishna Prasad Shanbhogue et al.
    RadioGraphics 2023; 43(12):e230071
  • “While  diffuse  XGP  is  easily  diagnosed  on  the  basis  of  a  constellation  of  findings  such  as  an  enlarged  kidney  with  a  contracted pelvis, dilated calyces (“bear’s paw” morphology), and staghorn calculi, focal and segmental types of XGP can be indistinguishable  from  tumors  on  imaging  studies.  Focal  XGP  may  appear  as  hypoattenuating  or  variably  enhancing masses or abscesses with associated perinephric or renal sinus  extension.”
    Tumefactive Nonneoplastic Proliferative Pseudotumors of the Kidneys and Urinary Tract: CT and MRI Findings with Histopathologic Correlation
    Krishna Prasad Shanbhogue et al.
    RadioGraphics 2023; 43(12):e230071
  • “Immunoglobulin  G4  (IgG4)–related  disease  (IgG4-RD)  is  a  distinctive,  idiopathic,  multisystem  fibroinflammatory  dis-order with characteristic imaging, serologic (elevated serum IgG4 levels), and pathologic features. Renal involve-ment has been reported to occur in 7%–25% of patients with IgG4-RD,  with  the  majority  of  cases  being  incidentally  detected  at  imaging.  Common  clinical  manifestations  of  renal IgG4-RD include reduced kidney function, proteinuria, or hematuria. Plasma cell–rich tubulointerstitial nephritis with storiform fibrosis or “bird’s-eye fibrosis” and eosinophilia  comprise  the  most  common  histopathologic  findings  of  renal  IgG4-RD.”
    Tumefactive Nonneoplastic Proliferative Pseudotumors of the Kidneys and Urinary Tract: CT and MRI Findings with Histopathologic Correlation
    Krishna Prasad Shanbhogue et al.
    RadioGraphics 2023; 43(12):e230071
  • “Diffuse  or  multifocal  hypoattenuating  masslike  lesions  showing  coalescence  and  affecting  bilateral  kidneys  are  typ-ical  imaging  findings .Characteristically,  the  nodules  are  isointense  on  T1-weighted  images,  are  hy-pointense  on  T2-weighted  images,  and  display  restricted  dif-fusion  and  progressive  contrast  enhancement.  Other  imaging  manifestations  of  renal  IgG4-RD  include  smooth  thickening of the renal pelvis, a renal sinus mass, and a peri-nephric mass . Synchronous changes of autoimmune pancreatitis  and  retroperitoneal  fibrosis,  if  present,  can  help  in narrowing the differential diagnosis. Most  patients  with  IgG4-RD  respond  exquisitely  to  corticosteroids. ”
    Tumefactive Nonneoplastic Proliferative Pseudotumors of the Kidneys and Urinary Tract: CT and MRI Findings with Histopathologic Correlation
    Krishna Prasad Shanbhogue et al.
    RadioGraphics 2023; 43(12):e230071
Liver

  • SVCS is a combination of signs and symptoms that result from the compression or occlusion of the superior vena cava, associated with a significant morbidity and mortality. While thoracic malignancy is the most common cause of SVCS accounting for more than 60% of the cases, benign causes are on the rise with the increasing use of central venous catheters and indwelling cardiac devices .Benign SVCS usually has a more insidious course compared to malignant causes, as there is time for the development of adequate collaterals to bypass the central venous occlusion.
    Superior vena cava syndrome with the hepatic ‘hot spot’ sign.  
    Koratala, A., Bhatti, V.  
    Intern Emerg Med 13, 293–294 (2018).
  • A CT scan of the chest with contrast excluded acute pulmonary embolism, but showed extensive chest wall venous collaterals with near-complete occlusion of the superior vena cava. In addition, it demonstrated the “focal hepatic hot spot sign,” which is an enhanced area in the segment IV or quadrate lobe of the liver, which results from the communication between superficial epigastric veins and left portal vein in cases of superior vena cava obstruction
    Superior vena cava syndrome with the hepatic ‘hot spot’ sign.  
    Koratala, A., Bhatti, V.  
    Intern Emerg Med 13, 293–294 (2018).
  • OBJECTIVE. The purpose of this article is to review the CT findings associated with superior  vena  cava  obstruction  and  to  illustrate  collateral  venous  pathways  bypassing  the  ob-struction as shown on MDCT.
    CONCLUSION. Multiple collateral venous pathways can form to bypass an obstruction of the superior vena cava. With its ability to acquire near isotropic data, MDCT allows high-quality reformations and thus exquisitely displays these venous collaterals and has the potential to aid in planning therapy to bypass the obstruction.
    Superior Vena Cava Obstruction Evaluation With MDCT              
    Sheila Sheth, Mark D. Ebert, and Elliot K. Fishman              
    American Journal of Roentgenology 2010 194:4, W336-W346
  • “Obstruction  of  the  superior  vena  cava  re-sults  in  impaired  venous  drainage  of  the head  and  neck  and  upper  extremities.  Clinical  manifestations  include  facial  and  neck swelling, distended neck veins, headache due to  cerebral  edema,  dyspnea,  and,  in  severe cases, stridor and altered mental status. Correlation of imaging studies with clinical find-ings  suggests  that  the  severity  of  symptoms depends on the level of obstruction (above or below  the  level  of  the  azygos  arch)  and  the development of rich collateral network. In fact, CT can detect subclinical superior vena cava obstruction in patients who are relatively asymptomatic.”        
    Superior Vena Cava Obstruction Evaluation With MDCT              
    Sheila Sheth, Mark D. Ebert, and Elliot K. Fishman              
    American Journal of Roentgenology 2010 194:4, W336-W346
  • “The  radiologist  should  be  familiar  with findings  on  abdominal  CT  that  suggest  the presence  of  a  superior  vena  cava  obstruc-tion. In addition to enhancing round or tortu-ous vascular channels in the abdominal wall,  perfusion  abnormalities  in  the  liv-er  and  the  so-called  “hot  spot”  initially  de-scribed on nuclear medicine both result from communication  between  superficial  epigas-tric veins and left portal vein. On CT, there is intense opacification of the anterior quadrate  lobe.  The  area  of  enhancement  is  characteristic  in  its  position  as  well  as  its  shape and  should  not  be  mistaken  for  a  hypervascular mass.”
    Superior Vena Cava Obstruction Evaluation With MDCT
    Sheila Sheth, Mark D. Ebert, Elliot K. Fishman
    AJR 2010; 19 4:336–346 
  • “Fibrosing mediastinitis  is  a  rare  histologically  benign  disorder caused by proliferation of collagen tissue  and  fibrosis  in  the  mediastinum.  It  may be idiopathic, caused by an abnormal immunologic response to Histoplasma capsulatum infection or to tuberculosis, or it may be related  to  retroperitoneal  fibrosis,  particularly in its diffuse form. Radiation-induced fibro-sis is another potential cause of superior vena cava obstruction.”
    Superior Vena Cava Obstruction Evaluation With MDCT
    Sheila Sheth, Mark D. Ebert, Elliot K. Fishman
    AJR 2010; 19 4:336–346 
  • “The incidence of catheter-induced supe-rior vena cava obstruction is rapidly increasing. Large  central  venous  catheters,  such  as  dialysis catheters, Hickman catheters, and parenter-al nutrition catheters, have all been implicated in superior vena cava obstruction. Transvenous permanent  cardiac  pacemaker  implantation  is another  risk  factor,  particularly  after  an  atrio-ventricular node ablation procedure.”
    Superior Vena Cava Obstruction Evaluation With MDCT
    Sheila Sheth, Mark D. Ebert, Elliot K. Fishman
    AJR 2010; 19 4:336–346 
  • “The  azygos  and  hemiazygos veins  can  divert  blood  away  from  the  superior  vena  cava.  If  the  level  of  superior  vena cava  obstruction  is  above  the  azygos  arch, antegrade  flow  from  the  azygos  to  the  right atrium  is  seen,  with  abrupt  transition  between  a  densely  opacified  azygos  above  the arch and an unopacified inferior azygos vein. If  the  obstruction  is  below  the  arch,  the  entire azygos and hemiazygos veins are bright-ly  opacified  as  the  blood  flows  in  a  retro-grade  fashion  toward  the  inferior  vena  cava .”
    Superior Vena Cava Obstruction Evaluation With MDCT
    Sheila Sheth, Mark D. Ebert, Elliot K. Fishman
    AJR 2010; 19 4:336–346
Musculoskeletal

  • Primary retroperitoneal sarcomas (RPS) represent around 10–16% of all sarcomas, with liposarcomas and leiomyosarcomas being the most common subtypes. RPS have some peculiar characteristics, imaging appearances, worse prognosis, and complications compared to other locations of sarcoma. Commonly, RPS primarily present as large masses, progressively encasing adjacent structures, causing mass effect, and complications. RPS diagnosis is often challenging, and these tumors may be overlooked; however, failure to recognize RPS characteristics leads to a worse prognosis for the patients. Surgery is the only recognized curative treatment, but the anatomical constraints of the retroperitoneum limit the ability to achieve wide resection margins; therefore, these tumors have a high rate of recurrence, and require long-term follow-up. The radiologist has an important role in the diagnosis of RPS, the definition of their extent, and their follow-up.
    CT and MR Imaging of Retroperitoneal Sarcomas: A Practical Guide for the Radiologist.  
    Porrello G, Cannella R, Randazzo A, Badalamenti G, Brancatelli G, Vernuccio F.  
    Cancers (Basel). 2023 May 30;15(11):2985.
  • “The detection of retroperitoneal masses includes a wide spectrum of differential diagnoses that must be ruled out, such as metastatic adenocarcinoma, retroperitoneal fibrosis, lymphoma, germ cell tumor, paragangliomas, or Castleman’s disease. The diagnostic pathway firstly includes the identification of the most likely origin of the tumor (e.g., LPS can mimic renal or adrenal angiomyolipoma) by considering clinical and laboratory findings such as patient age (e.g., in young men pediatric tumors and, even if rare in retroperitoneal location, testicular masses) and history (e.g., history of melanoma) and presence of any positive serum markers. If nodal involvement is noted, other diagnosis should be considered upon RPS.”
    CT and MR Imaging of Retroperitoneal Sarcomas: A Practical Guide for the Radiologist.  
    Porrello G, Cannella R, Randazzo A, Badalamenti G, Brancatelli G, Vernuccio F.  
    Cancers (Basel). 2023 May 30;15(11):2985.
  • “Contrast-enhanced computed tomography (CT) is the most useful and widely available first-line imaging technique. CT allows confirmation of the site and origin of the mass and often offers information on tissue composition (e.g., lipomatous elements, calcifications or myxoid elements, internal necrosis) , which are fundamental to understand the possible RPS type and differential diagnosis to consider. While some guidelines on sarcomas affirm that magnetic resonance imaging (MRI) is the main imaging modality in sarcomas of the trunk and that CT has a specific role in calcified lesions, to identify fractures and rule out conditions such as myositis ossificans, in RPS CT seems to have a similar performance to MRI.”
    CT and MR Imaging of Retroperitoneal Sarcomas: A Practical Guide for the Radiologist.  
    Porrello G, Cannella R, Randazzo A, Badalamenti G, Brancatelli G, Vernuccio F.  
    Cancers (Basel). 2023 May 30;15(11):2985.
  • “LPS represent the most common primary RPS, and typically occur in adult patients (50–70 years). LPS commonly present as round, oval, or lobulated intra-abdominal fat-attenuating masses that exert mass effect on adjacent structures. They are histologically subdivided into five different subgroups based on the WHO 2020 classification. LPS with both well-differentiated and dedifferentiated components are often poorly evaluated and described as multifocal masses, because only the dedifferentiated or solid components are demarked, while the well-differentiated fatty mass is often not recognized. An incomplete report may lead to incomplete surgery, which worsens the prognosis. Lungs are the primary metastatic site.”
    CT and MR Imaging of Retroperitoneal Sarcomas: A Practical Guide for the Radiologist.  
    Porrello G, Cannella R, Randazzo A, Badalamenti G, Brancatelli G, Vernuccio F.  
    Cancers (Basel). 2023 May 30;15(11):2985.
  • Well-differentiated liposarcomas are low-grade tumors. Characteristic CT features include macroscopic fat in at least 75% of the whole tumor with smooth and lobular margins, thick septa (>3 mm), tendency to be nodular, and mild or inconstant low enhancement . Calcifi Myxoid/Round-cell liposarcomas (MLS) are intermediate-grade tumors and almost always occur in the retroperitoneum as secondary locations [41]. They are heterogeneous, lobular, with internal septations and features often described as “pseudocystic” due to myxoid components. Compared to true cystic lesions, they gradually enhance on delayed postcontrast phases, with progressive accumulation of contrast within the myxoid matrix. In more than 50% of cases, there is no fat component [ Calcifications are rare. cations are rare  and can indicate dedifferentiation or inflammation. These tumors can recur, but do not tend to metastasize.
    CT and MR Imaging of Retroperitoneal  Sarcomas: A Practical Guide for the Radiologist.  
    Porrello G, Cannella R, Randazzo A, Badalamenti G, Brancatelli G, Vernuccio F.  
    Cancers (Basel). 2023 May 30;15(11):2985.
  • Dedifferentiated liposarcomas are high-grade tumors with poor prognosis. Characteristic features include heterogeneous nonlipomatous mass within, adjacent to, or surrounding a fatty mass [37,38]. There may be no evidence of fat-density tissue in up to 20% of cases, making the imaging diagnosis difficult [40]. Enhancing septa within the fatty portions are frequently seen [37]. Calcifications are rare (around 25% of cases) and are poor prognostic factors [39].  Pleomorphic liposarcomas contain little or no fat and myxoid components. They are considered high-grade malignancies with high rates of local recurrence and distant metastases [38]. They are heterogeneous masses, isoattenuating to muscles on CT and commonly have internal areas of low attenuation representing necrosis. Calcifications are rare.  
    CT and MR Imaging of Retroperitoneal  Sarcomas: A Practical Guide for the Radiologist.  
    Porrello G, Cannella R, Randazzo A, Badalamenti G, Brancatelli G, Vernuccio F.  
    Cancers (Basel). 2023 May 30;15(11):2985.
  • Undifferentiated pleomorphic liposarcoma: imaging features are nonspecific. It manifests as a large, well-circumscribed soft-tissue mass with heterogeneous enhancement and myxoid components. Areas of necrosis and hemorrhage may be seen but are less extensive than leiomyosarcomas. Calcifications occur in up to 20% of cases with a ring-like pattern. Direct invasion of adjacent organs may be present.
    CT and MR Imaging of Retroperitoneal  Sarcomas: A Practical Guide for the Radiologist.  
    Porrello G, Cannella R, Randazzo A, Badalamenti G, Brancatelli G, Vernuccio F.  
    Cancers (Basel). 2023 May 30;15(11):2985.
  • The main differential diagnosis is with simple lipomas (Figure 3) that will present as purely adipocytic tumors. In this case, when the lesion is ≤10 cm, the patient can be managed without a biopsy. Beyond 10 cm, patients should still undergo MRI and biopsy. Another diagnosis to keep in mind is renal angiomyolipoma, which, contrary to LPS, is hypervascular and presents with a large vessel extending into the renal cortex. Moreover, the presence of a renal parenchymal defect at the site of tumor contact favors exophytic angiomyolipoma. Other rarer occurrences to consider are adrenal myelolipomas, which share similar imaging appearance with angiomyolipoma, and ovarian teratomas. Features that should favor the latter are the presence of fat–fluid levels or tooth-like calcifications [38]. propensity for pulmonary, and extrapulmonary metastases, that do not uptake contrast on FDG-PET. Of note, there is a preponderance of spinal metastases, not clearly visible on CT. Clinical practice guidelines have therefore included spine MRI as part of MLS staging. C. Dedifferentiated liposarcomas are high-grade tumors with poor prognosis. Characteristic features include heterogeneous nonlipomatous mass within, adjacent to, or surrounding a fatty mass. There may be no evidence of fat-density tissue in up to 20% of cases, making the imaging diagnosis difficult [40]. Enhancing septa within the fatty portions are frequently seen. Calcifications are rare (around 25% ).
    CT and MR Imaging of Retroperitoneal  Sarcomas: A Practical Guide for the Radiologist.  
    Porrello G, Cannella R, Randazzo A, Badalamenti G, Brancatelli G, Vernuccio F.  
    Cancers (Basel). 2023 May 30;15(11):2985.
Pancreas

  • “Moreover, AI is playing a crucial role in personalized medicine. By analyzing large datasets that include patient health records, genetic information, and treatment outcomes, AI algorithms can identify patterns and correlations that help tailor treatment plans to individual patients. This enables healthcare providers to deliver targeted therapies, predict disease progression, and reduce adverse effects. Additionally, AI is streamlining administrative tasks and improving operational efficiency in healthcare facilities. Natural language processing (NLP) algorithms can automate tasks like medical coding and documentation, reducing the burden on healthcare professionals and minimizing errors. AI chatbots are being used to provide patients with round-the-clock assistance, answer their queries, schedule appointments, and even provide basic medical advice.”
    From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer
    Satvik Tripathi et al.
    Diagnostics 2024, 14, 174. https://doi.org/10.3390/diagnostics14020174

  • From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer
    Satvik Tripathi et al.
    Diagnostics 2024, 14, 174. https://doi.org/10.3390/diagnostics1402017
  • “Overall, ML techniques, including supervised learning algorithms like support vector machines and random forests, as well as unsupervised learning techniques like clustering and dimensionality reduction, are very valuable in pancreatic cancer research. They enable researchers to extract meaningful insights from complex datasets, improve diagnostic accuracy, predict patient outcomes, and facilitate personalized treatment strategies.”  
    From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer
    Satvik Tripathi et al.
    Diagnostics 2024, 14, 174. https://doi.org/10.3390/diagnostics14020174
  • “We can also utilize CNNs for lesion detection and localization for automated identification of anomalous or dubious regions in medical imagery. The application of computer vision techniques in pancreatic cancer research has the potential to facilitate the identification and localization of pancreatic tumors and other lesions. Through the automated identification of these regions, medical professionals can concentrate their efforts on the specific areas of concern, thereby enabling enhanced precision in diagnosis and treatment strategizing. These algorithms can also help classify tumors into distinct subtypes or determine their malignancy by extracting pertinent features from medical images, such as texture, shape, or intensity patterns. These extracted data hold significant value in terms of prognostication, informing treatment choices, and forecasting patient results.”
    From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer
    Satvik Tripathi et al.
    Diagnostics 2024, 14, 174. https://doi.org/10.3390/diagnostics14020174
  • “The early detection of pancreatic cancer is a critical factor in improving patient outcomes, as it is often diagnosed at an advanced stage when treatment options are limited. AI has the potential to aid in the early detection of pancreatic cancer by analyzing medical data and identifying patterns that may indicate the presence of the disease. Deep learning techniques can be trained on large datasets to accurately identify early stage pancreatic cancer based on characteristic imaging features or use morphology features to build segmentation frameworks for the pancreas. AI algorithms can integrate various patient data, such as age, family history, lifestyle factors, and medical history, to detect an individual’s developing pancreatic cancer early. AI can also analyze a patient’s electronic health records, including medical history, laboratory results, and diagnostic reports, to identify potential indicators of pancreatic cancer. By processing and interpreting vast amounts of data, AI algorithms can detect subtle patterns and abnormalities that may go unnoticed by clinicians.”
    From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer
    Satvik Tripathi et al.
    Diagnostics 2024, 14, 174. https://doi.org/10.3390/diagnostics14020174
  • However, finding reliable and specific biomarkers for pancreatic cancer is challenging due to the heterogeneity and complexity of the disease, the lack of adequate samples, and the interference of confounding factors . AI can help overcome these challenges by applying advanced computational methods to analyze large and diverse datasets of biomolecular information, such as genomics, proteomics, metabolomics, or microbiomics. AI can also integrate multiple types of data from the pancreas to identify novel biomarkers or biomarker signatures that have higher sensitivity and specificity than single biomarkers . A deep learning model based on multimodal neural networks (MNNs) was proposed to combine imaging data (WSI), gene expression data, clinical data (age, gender, tumor location), and biomarker data (mi-RNA) to forcast the survival of pancreatic cancerpatients.
    From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer
    Satvik Tripathi et al.
    Diagnostics 2024, 14, 174. https://doi.org/10.3390/diagnostics14020174 
  • “AI can serve as a powerful tool in the advancement of pancreatic cancer diagnosis, management, and prognosis, particularly in identifying tumors earlier in disease progression. Despite the many applications and advantages of AI in pancreatic cancer, multiple limitations pose challenges that must be addressed as the field grows. One is the lack of a standardized approach to treatment and diagnosis. Other challenges include a lack of robust and high-quality data, transparency and reproducibility of findings, and ethical considerations, including biases in algorithms.”
    From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer
    Satvik Tripathi et al.
    Diagnostics 2024, 14, 174. https://doi.org/10.3390/diagnostics14020174
  • “Furthermore, AI algorithms have been previously referred to as “Black boxes” due to their lack of transparency and interpretability. The opacity of the code used to build AI models and the hidden level of complexity make it difficult to reproduce results in an independent manner. General descriptions of the code used to build models do not provide enough information to reproduce most findings. The lack of easy interpretation of these AI models and prospective studies assessing AI-based tools has increased the hesitancy of adaptation into clinical practice. Without transparency andinterpretation, clinicians are not able to critically interrogate the output of these models, putting an incredible amount of faith in the accuracy of the model.”  
    From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer
    Satvik Tripathi et al.
    Diagnostics 2024, 14, 174. https://doi.org/10.3390/diagnostics14020174
  • “Additionally, the creation and use of large datasets needed to create AI models pose the challenging questions of data ownership and patient privacy, particularly inreference to medical imaging. At the same time, the integration of AI systems in medical practices raises questions about the security and confidentiality of sensitive patient data. Ensuring robust data protection mechanisms is imperative to prevent unauthorized access and potential misuse of personal health information. Additionally, ethical challenges encompass issues such as algorithmic bias, transparency, and accountability. Addressing these challenges requires the establishment of ethical guidelines and regulatory frameworks that prioritize fairness, transparency, and the responsible use of AI technologies. Striking a balance between innovation and ethical considerations is essential to foster public trust and promote the responsible adoptionof AI in healthcare, ultimately ensuring that advancements in technology benefit patientswithout compromising their privacy or perpetuating existing healthcare disparities.” 
  • “Additionally, ethical challenges encompass issues such as algorithmic bias, transparency, and accountability. Addressing these challenges requires the establishment of ethical guidelines and regulatory frameworks that prioritize fairness, transparency, and the responsible use of AI technologies. Striking a balance between innovation and ethical considerations is essential to foster public trust and promote the responsible adoptionof AI in healthcare, ultimately ensuring that advancements in technology benefit patientswithout compromising their privacy or perpetuating existing healthcare disparities.”
    From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer
    Satvik Tripathi et al.
    Diagnostics 2024, 14, 174. https://doi.org/10.3390/diagnostics14020174
  • In order to convert AI research into clinical practice, robust validation studies in pancreatic cancer are required to establish the clinical efficacy, safety, and cost-effectiveness of AI-based methods. Large-scale prospective studies should be conducted in the future to evaluate the performance of AI algorithms in realworld healthcare situations. Furthermore, regulatory and ethical factors such as privacy protection, informed consent, and algorithm transparency must be addressed to enable responsible and fair AI technology implementation in healthcare.  
    From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer
    Satvik Tripathi et al.
    Diagnostics 2024, 14, 174. https://doi.org/10.3390/diagnostics14020174
  • • [18F] Fluorodeoxyglucose18F-FDG) PET/CT can improve the staging accuracy and clinical management of patients with hepatobiliary and pancreatic cancers, by detection of unsuspected metastases.  
    • 18F-FDG PET/CT metabolic parameters are valuable in predicting treatment response and survival.  
    • Metabolic response on 18F-FDG PET/CT can predict preoperative pathologic response to neoadjuvant therapy in patients with pancreatic cancer and determine prognosis.  
    • Several novel non-FDG tracers, such as 68-Ga prostate-specific membrane antigen and 68Gafibroblast activation protein inhibitor PET/CT, show promise for imaging hepatobiliary and pancreatic cancers with potential for radioligand therapy.
    Quarter-Century PET/ Tomography Transformation of Oncology Hepatobiliary and Pancreatic Cancer
    Asha Kandathil et al.
    PET Clin (in press) 2024
  • “18F-FDG PET/CT has reported sensitivity of 85%to 100%, specificity of 61% to 94%, and accuracy of 84% to 95% in diagnosing pancreatic cancer.39–42 FDG uptake by pancreatic cancer correlates with increased Ki-67 and is highest in poorly differentiated tumors. Medium- or well-differentiated pancreatic cancers may not have increased FDG uptake. Inflammatory lesions such as chronic lymphoplasmacytic pancreatitis, autoimmune pancreatitis, and tuberculosis may have increased FDG uptake.”  
    Quarter-Century PET/ Tomography Transformation of Oncology Hepatobiliary and Pancreatic Cancer
    Asha Kandathil et al.
    PET Clin (in press) 2024
  • In a multicenter prospective study conducted in 18 UK pancreatic tertiary referral centers, Ghaneh and colleagues evaluated the performance of multidetector CT (MDCT) in 589 patients and FDG PET/CT in 550 patients with suspected pancreatic cancer. MDCT had a sensitivity of 88.5%and specificity of 70.6%; FDG PET/CT had a sensitivity of 92.7% and specificity of 75.8% for the diagnosis of pancreatic cancer. Pancreatic cancer had a higher median SUVmax of 7.5 compared with median SUVmax of 5.7 for other lesions. Adding PET/ CT to standard workup improved pancreatic cancer diagnosis, staging, and management.
    Quarter-Century PET/ Tomography Transformation of Oncology Hepatobiliary and Pancreatic Cancer
    Asha Kandathil et al.
    PET Clin (in press) 2024
  • “Surgical resection is the only curative option for pancreatic cancer; however, more than 80% of patients present unresectable disease due to locally advanced disease or distant metastases. Borderline resectable pancreatic cancer (BRPC) patients who could be eligible for radical surgery following neoadjuvant chemotherapy may have local arterial or venous (superior mesenteric vein/ portal vein) invasion.44 PET has less spatial resolution and accuracy than CT in assessing locoregional involvement, which is critical in therapeutic decision-making in pancreatic cancer. CT, MR imaging, and endoscopic ultrasound are better at defining tumor’s border and local spread.45 However, PET/CT performs better than CT in identifying unsuspected metastases, reducing the frequency of futile surgeries.”
    Quarter-Century PET/ Tomography Transformation of Oncology Hepatobiliary and Pancreatic Cancer
    Asha Kandathil et al.
    PET Clin (in press) 2024
  • “In a study of the utility of 18F-FDG PET/CT in assessing treatment response in 20 patients with LAPC treated with neoadjuvant chemo-RT, Choi and colleagues observed that mean survival was longer (23.2 months) in patients with   50% decrease in SUV between pre-study PET scan and PET scan after the first cycle of chemotherapy, as compared with 11.3 months in patients with less than 50% decrease in SUV.”  
    Quarter-Century PET/ Tomography Transformation of Oncology Hepatobiliary and Pancreatic Cancer
    Asha Kandathil et al.
    PET Clin (in press) 2024
  • Purpose To analyze the conspicuity of pancreatic ductal adenocarcinoma (PDAC) in virtual monoenergetic images (VMI) on a novel photon-counting detector CT (PCD-CT) in comparison to energy-integrating CT (EID-CT).
    Conclusion PCD-CT VMI reconstructions (≤ 70 keV) showed significantly improved conspicuity of PDAC in quantitative and qualitative analysis in both, arterial and portal venous contrast phase, compared to EID-CT, which may be important for early detection of tumor tissue in clinical routine. Tumor delineation was superior in portal venous contrast phase compared to arterial contrast phase.
    Optimal conspicuity of pancreatic ductal adenocarcinoma in virtual monochromatic imaging reconstructions on a photon‑counting detector CT: comparison to conventional MDCT
    Josua A. Decker et al.
    Abdominal Radiology (2024) 49:103–116
  • “Implementation of VMI with low keV levels (e.g. 40 keV) for both—arterial and portal venous phase—in clinical routine may improve delineation of pancreatic ductal adenocarcinoma in patients with suspected pancreatic cancer.”  
    Optimal conspicuity of pancreatic ductal adenocarcinoma in virtual monochromatic imaging reconstructions on a photon‑counting detector CT: comparison to conventional MDCT
    Josua A. Decker et al.
    Abdominal Radiology (2024) 49:103–116
  • Purpose We aim to compare FDG-PET/CT and cross-sectional imaging (contrast enhanced CT/MRI) diagnostic abilities in detecting recurrence/progression of pancreaticobiliary system tumors and to reveal the clinical impact of integrated FDG PET/ CT to CT/MRI on patient management.
    Conclusion FDG-PET/CT and cross-sectional imaging have different advantages and shortcomings. In recurrence/progression, recognition of early changes is more feasible by CT/MRI. However, inconsistency of morphologic and metabolic findings is important reason of cross-sectional imaging failure. FDG-PET/CT is superior in showing extraabdominal metastases, but missing small-volume lesions and misinterpreting inflammatory changes are still a problem lowering its sensitivity. Nevertheless FDGPET/CT is good option for guiding undetermined imaging findings or clinic-radiologic mismatch.
    Integrated FDG‑PET/CT contribution over cross‑sectional imaging in recurrence or progression of pancreaticobiliary neoplasms
    Banu Karaalioglu · Tansel Cakir · Yasin Kutlu · Mehmet Seker · Ahmet Bilici
    Abdominal Radiology (2024) 49:131–140
  • “In Kumar et al. study with 24 patients, FDG-PET/CT was found more sensitive, specific, and accurate in detecting recurrent GB carcinoma (93.7% vs 87.5%, 100% vs 50%, 95.8% vs 75%, respectively). However, they compared PET findings with quite diverse radiological modalities (contrast enhanced CT, MRI, ultrasonography, endoscopic retrograde cholangiopancreatography), which significantly reduces the reliability of the results, especially from a radiological point of view. In Lee et al. study with recurrent biliary tract carcinoma, they found FDG-PET/CT and CT equally sensitive in detecting locoregional disease (88%). In Corvera et al. study of 33 patients with suspected biliary tumors recurrence, they found FDG-PET only confirmatory in biliary cancer recurrence with 95% true concordant results with cross-sectional imaging.”
    Integrated FDG‑PET/CT contribution over cross‑sectional imaging in recurrence or progression of pancreaticobiliary neoplasms
    Banu Karaalioglu · Tansel Cakir · Yasin Kutlu · Mehmet Seker · Ahmet Bilici
    Abdominal Radiology (2024) 49:131–140
  • “We think that our study is the most comprehensive one comparing to previous studies on the topic so far. FDG-PET/ CT and cross-sectional imaging have different advantages and shortcomings in evaluating the recurrence and progression  of pancreaticobiliary system tumors. Cross-sectional imaging is superior to FDG-PET/CT in detecting recurrence/ progression of local disease and intra-abdominal metastases. High spatial resolution and the advantage of comparability with previous images makes recognition of early changes more feasible by cross-sectional imaging. Lesion size and metabolic activity inconsistency was important reason of its failure in this regard. FDG-PET/CT is superior in showingextra-abdominal distant metastases. However, its limitations in small volume lesions and misinterpretation of inflammatory changes are still a problem lowering its sensitivity. Nevertheless, FDG-PET/CT is a good option for guiding CT/MRI undetermined findings or clinic-radiologic mismatches and especially in such situations it has a crucial role in patient management.”
    Integrated FDG‑PET/CT contribution over cross‑sectional imaging in recurrence or progression of pancreaticobiliary neoplasms
    Banu Karaalioglu · Tansel Cakir · Yasin Kutlu · Mehmet Seker · Ahmet Bilici
    Abdominal Radiology (2024) 49:131–140
  • “While 10 %–20 % of SPTs demonstrate malignant behavior, the vast majority are indolent neoplasms that display excellent prognosis after surgical resection. Metastases, though rare, have also been reported in up to 2 % of cases, with the liver being the most common site of metastatic spread. Given their low malignant potential and excellent outcomes if appropriately treated, correct and timely radiological diagnosis is crucial in optimizing patient management and prognosis. Due to the rarity of SPTs however, in conjunction with the heterogeneity of their imaging features, establishing correct diagnosis has previously proven to be challenging. Prior studies have demonstrated that among cases of pathologically proven SPTs, preoperative suspicion of SPT based on imaging features was correctly raised in only 24 % of cases.”
    Cinematic rendering of solid pseudopapillary tumors: Augmenting diagnostics of an increasingly encountered tumor  
    Taha M. Ahmed, MD, Elliot K. Fishman, MD, Linda C. Chu, MD*
    Current Problems in Diagnostic Radiology (in press)
  • “Cinematic rendering is completed on an independent workstation equipped with Siemens Syngo Via (VB40) running cinematic rendering software. We have developed optimized rendering parameters for the pancreas which we have used for a range of pancreatic pathology. These pre-defined parameters are adjusted in real time to optimize output on a case-by-case basis. The final images are subsequently exported to PACS where they can be reviewed by the referring clinician.”
    Cinematic rendering of solid pseudopapillary tumors: Augmenting diagnostics of an increasingly encountered tumor  
    Taha M. Ahmed, MD, Elliot K. Fishman, MD, Linda C. Chu, MD*
    Current Problems in Diagnostic Radiology (in press)
  • “CT attenuation in cystic regions ranges from that of fluid attenuation equal to that of water to soft tissue attenuation of areas rich in blood. Internal hemorrhage, in the appropriate context of other imaging findings, is highly characteristic of these tumors and is present in between 29 and 88.9 % of cases. Calcifications are present in roughly one third of tumors and are more frequently encountered in larger tumors.19,20 Although peripheral curvilinear calcifications are most classic, calcification patterns may vary. The majority of SPTs (59.3 %) are located within the body and tail of the pancreas with a mean tumor size of 6.1 cm at the time of presentation.”
    Cinematic rendering of solid pseudopapillary tumors: Augmenting diagnostics of an increasingly encountered tumor  
    Taha M. Ahmed, MD, Elliot K. Fishman, MD, Linda C. Chu, MD*
    Current Problems in Diagnostic Radiology (in press)
  • “Differential diagnoses for predominantly solid SPTs consists of well differentiated pancreatic neuroendocrine tumor (PNET), pancreatic ductal adenocarcinoma (PDAC), serous adenoma (SCA) and metastases. For larger mixed solid and cystic SPTs, differential diagnoses consists of such as mucinous cystic neoplasm (MCN), SCA, intraductal papillary mucinous neoplasm (IPMN), cystic PNETs, calcified hemorrhagic pseudocyst, pancreatoblastoma in pediatric patients, and exophytic gastrointestinal stromal tumor (GIST) when arising in close relation to the pancreas.”
    Cinematic rendering of solid pseudopapillary tumors: Augmenting diagnostics of an increasingly encountered tumor  
    Taha M. Ahmed, MD, Elliot K. Fishman, MD, Linda C. Chu, MD*
    Current Problems in Diagnostic Radiology (in press)
  • “Computed tomography (CT) is the primary imaging modality used to assess SPT. At imaging, SPTs typically appear as well encapsulated mixed-density lesions composed of varying proportions of solid components and cystic components. Infrequently, they may be mostly solid or mostly cystic. SPTs are hypothesized to grow as solid tumors that outgrow their vascular supply and subsequently undergo cystic degeneration. As a result, cystic components tend to be centrally located while enhancing solid components are present peripherally. CT attenuation in cystic regions ranges from that of fluid attenuation equal to that of water to soft tissue attenuation of areas rich in blood. Internal hemorrhage, in the appropriate context of other imaging findings, is highly characteristic of these tumors and is present in between 29 and 88.9 % of cases.”
    Cinematic rendering of solid pseudopapillary tumors: Augmenting diagnostics of an increasingly encountered tumor  
    Taha M. Ahmed, MD, Elliot K. Fishman, MD, Linda C. Chu, MD*
    Current Problems in Diagnostic Radiology (in press)
  • “CR in these cases can better visualize internal septations, increase depth perception of cystic components and characterize the true cystic nature of the mass. Through this, the internal architecture of cystic components can be better appreciated which can help in differentiating between cystic neoplasms. In rare cases, SPT may also present as a purely cystic mass, making differentiation between SPT and MCNs challenging. In these equivocal cases, patient demographics, particularly age, may be used to help differentiate between the two entities.”
    Cinematic rendering of solid pseudopapillary tumors: Augmenting diagnostics of an increasingly encountered tumor  
    Taha M. Ahmed, MD, Elliot K. Fishman, MD, Linda C. Chu, MD*
    Current Problems in Diagnostic Radiology (in press)
  • “Vascular encasement, narrowing, occlusion and invasion in SPTs is rare and up to 95 % of SPT do not demonstrate any vascular involvement. CR in these cases can better characterize any vascular stretching, abutment, and compression from a large SPT and differentiate it from true vessel involvement from a PDAC or PNET. This can help rule in the correct diagnosis with more certainty. While most SPTs do not demonstrate vascular invasion, a small aggressive subset (4.6 %) of tumors can present with vascular involvement. Vascular invasion does not necessarily preclude surgical resection of SPT however, and previous reports have demonstrated long term improved outcomes when radical resection with vascular reconstruction is pursued. CR in such cases can better define the extent of vascular involvement through characterizing the length of involved vessel and degree of luminal narrowing."
    Cinematic rendering of solid pseudopapillary tumors: Augmenting diagnostics of an increasingly encountered tumor  
    Taha M. Ahmed, MD, Elliot K. Fishman, MD, Linda C. Chu, MD*
    Current Problems in Diagnostic Radiology (in press)
  • “Second, the display of CR images needs to be optimized to accurately depict the anatomy and pathology of interest. This requires the specialized expertise of radiologists who must tailor the display settings for each unique pathology. Utilization of incorrectly optimized parameters can hinder visualization and potentially lead to incorrect diagnoses. While this aspect of CR implementation may become more standardized and user-friendly in the future, and potentially automated with the help of artificial intelligence algorithms, currently radiologists must dedicate time to manually render each case. It takes an experienced radiologist approximately 5–7 min to render each case.”
    Cinematic rendering of solid pseudopapillary tumors: Augmenting diagnostics of an increasingly encountered tumor  
    Taha M. Ahmed, MD, Elliot K. Fishman, MD, Linda C. Chu, MD*
    Current Problems in Diagnostic Radiology (in press)
  • “Accurate diagnosis of postoperative complications requires a solid understanding of pancreatic anatomy, surgical indications, normal postoperative appearance, and expected postsurgical changes. The practicing radiologist should be familiar with the most common perioperative complications, such as anastomotic leak, abscess, and hemorrhage, and be able to differentiate these entities from normal anticipated postoperative changes such as seroma, edema and fat stranding at the surgical site, and perivascular soft-tissue thickening. In addition to evaluation of the primary operative fossa, imaging plays a fundamental role in assessment of the adjacent organ systems secondarily affected after pancreatic surgery, such as vascular, biliary, and enteric complications.”
    Imaging after Pancreatic Surgery: Expected Findings and Postoperative Complications
    Ayman H. Gaballah et al.
    RadioGraphics 2024; 44(1):e230061
  • • Complications often occur at the sites of surgical anastomoses, and knowledge of the surgical approach is critical for identifying the location and type of complication with imaging.
    • Leakage of pancreatic juice can trigger the autodigestion of nearby structures, resulting in complications such as vascular erosion, hemorrhage, pseudoaneurysms, and fistulous communications with adjacent structures. Additionally, it is known to be associated with delayed gastric emptying, ileus, and infections, including abdominal abscesses and wound infections.
    • Unexplained abdominal pain, features of pancreatic exocrine insufficiency, and attacks of acute pancreatitis in the late postoperative period associated with imaging findings of progressive pancreatic ductal dilatation and abrupt narrowing at the anastomotic site should raise concern for stricture formation
    Imaging after Pancreatic Surgery: Expected Findings and Postoperative Complications
    Ayman H. Gaballah et al.
    RadioGraphics 2024; 44(1):e230061
  • • Risk factors for anastomotic leak include preoperative radiation therapy, small size of the bile duct, and anastomosis of the CBD rather than the common hepatic duct to the jejunal loop. Pancreatic leak can also lead to bile leaks.
    • Early-onset hemorrhage is due to surgical factors including inadequate hemostasis, slipped ligature, or fresh bleeding at a surgical site. It can occur due to arterial or venous injury or bleeding along the anastomotic siteor resected parenchymal surface. Late-onset hemorrhage can occur up to several days or weeks after surgery and generally has a pathologic cause.
    Imaging after Pancreatic Surgery: Expected Findings and Postoperative Complications
    Ayman H. Gaballah et al.
    RadioGraphics 2024; 44(1):e230061
  • “The pancreas mainly receives its blood supply from the celiac trunk and in part from the superior mesenteric artery (SMA). Typically the pancreatic head gets its arterial supply through the superior pancreaticoduodenal branches of the gastrodu-odenal artery and the inferior pancreaticoduodenal branches of the SMA. The body and tail receive their arterial supply predominantly from the dorsal pancreatic artery, which commonly arises from the splenic artery but may occasionally arise from the proximal proper hepatic artery or the celiac trunk. Additional small pancreatic branches from adjacent arteries, most of which arise from the splenic artery, also supply the body and tail.”
    Imaging after Pancreatic Surgery: Expected Findings and Postoperative Complications
    Ayman H. Gaballah et al.
    RadioGraphics 2024; 44(1):e230061
  • “The venous drainage of the pancreatic head passes through four pancreaticoduodenal veins. The posterior superior pancreaticoduodenal vein drains via the main portal vein. The anterior superior, anterior inferior, and posterior inferior pancreaticoduodenal veins drain via the SMV. The body and tail drain via tributaries predominantly into the splenic vein. Pancreatic lymphatic drainage mainly follows the arterial supply of the pancreas. The head drains into the pyloric nodes, and the body and tail drain into the pancreaticosplenic nodes. These lymph nodes drain into the celiac and superior mesenteric nodes.”
    Imaging after Pancreatic Surgery: Expected Findings and Postoperative Complications
    Ayman H. Gaballah et al.
    RadioGraphics 2024; 44(1):e230061
  • “CT is the primary imaging modality used for postoperative pancreatic imaging due to its excellent spatial resolution, short imaging time, and accurate depiction of air and calcifications. Additionally, CT angiography aids in detecting vascular complications. The CT protocol for postoperative surveillance should be multiphase. It should include contrast-enhanced imaging during the arterial phase (pancreatic parenchymal phase) at 40–50 seconds and portal venous phase at 65–70 seconds, which is also in line with the recommended protocol for preoperative evaluation.”
    Imaging after Pancreatic Surgery: Expected Findings and Postoperative Complications
    Ayman H. Gaballah et al.
    RadioGraphics 2024; 44(1):e230061
  • “Enlarged lymph nodes can manifest in the surgical bed in the postoperative period and can measure greater than 1 cm in diameter. These lymph nodes are rarely metastatic. They can be followed up at subsequent imaging to ensure stability or resolution.”
    Imaging after Pancreatic Surgery: Expected Findings and Postoperative Complications
    Ayman H. Gaballah et al.
    RadioGraphics 2024; 44(1):e230061
  • “It is widely regarded as the Achilles’ heel of pancreatic surgery owing to its potential to cause significant morbidity and mortality. Leakage of pancreatic juice can trigger the autodigestion of nearby structures, resulting in complications such as vascular erosion, hemorrhage, pseudoaneurysms, and fistulous communications with adjacent structures. Additionally, it is known to be associated with delayed gastric emptying, ileus, and infections, including abdominal abscesses and wound infections. In some cases, sepsis and multiorgan failure can also result from pancreatic leak.”  
    Imaging after Pancreatic Surgery: Expected Findings and Postoperative Complications
    Ayman H. Gaballah et al.
    RadioGraphics 2024; 44(1):e230061

  • Imaging after Pancreatic Surgery: Expected Findings and Postoperative Complications
    Ayman H. Gaballah et al.
    RadioGraphics 2024; 44(1):e230061
  • “Pancreatic leak is the most common cause of pathologic fluid collection after surgery . The rate of clinically significant leak after distal pancreatectomy ranges from 5% to 40% in various studies. It is generally higher than the incidence observed after pancreaticoduodenectomy, which is reported to be between 6% and 14%. However, the leak following distal pancreatectomy tends to be less severe in terms of clinical impact than those following pancreaticoduodenectomy. The diagnosis of leak is essentially based on clinical and laboratory parameters and covers a spectrum ranging from a mild self-limiting leak to a severe or fatal leak.”
    Imaging after Pancreatic Surgery: Expected Findings and Postoperative Complications
    Ayman H. Gaballah et al.
    RadioGraphics 2024; 44(1):e230061
  • “Multiple vascular complications can occur after pancreatic surgery. These complications include hemorrhage, stenosis, thrombosis, graft occlusion, pseudoaneurysm formation, and organ ischemia and infarction. They are more common in patients undergoing vascular reconstructions, and risk increases with the complexity of the reconstruction Additionally, other postoperative complications and endovascular procedures can lead to the development of vascular complications.”  
    Imaging after Pancreatic Surgery: Expected Findings and Postoperative Complications
    Ayman H. Gaballah et al.
    RadioGraphics 2024; 44(1):e230061
  • “The International Study Group of Pancreatic Surgery (ISGPS) developed a classification system for postpancreatic surgery hemorrhage. This system is based on three key parameters: the timing of onset (early vs late), the location of bleeding (intraluminal vs extraluminal), and the severity of the hemorrhage (mild vs severe). The ISGPS classification system further subdivides hemorrhage into three distinct grades. Specifically, grade A refers to mild early-onset hemorrhage within the first 24 hours after surgery, whereas grade B represents severe early-onset or any mild late-onset hemorrhage. Finally, grade C hemorrhage denotes severe late-onset hemorrhage.”
    Imaging after Pancreatic Surgery: Expected Findings and Postoperative Complications
    Ayman H. Gaballah et al.
    RadioGraphics 2024; 44(1):e230061
  • “Early-onset hemorrhage is due to surgical factors including inadequate hemostasis, slipped ligature, or fresh bleeding at a surgical site. It can occur due to arterial or venous injury or bleeding along the anastomotic site or resected parenchymal surface. Late-onset hemorrhage can occur up to several days or weeks after the surgery and generally has a pathologic cause. Anastomotic leaks (most commonly pancreatic leak) and postsurgical infection or abscess can lead to vascular erosions causing delayed hemorrhage. Arterial pseudoaneurysms and bleeding anastomotic ulcers can also cause delayed hemorrhage.”  
    Imaging after Pancreatic Surgery: Expected Findings and Postoperative Complications
    Ayman H. Gaballah et al.
    RadioGraphics 2024; 44(1):e230061
  • “Active bleeding and pseudoaneurysms can be identified after intravenous contrast material injection and are ideally evaluated at CT angiography. With a sensitivity and specificity of 91% and 99%, respectively, arterial phase contrast-enhanced CT is highly effective in identifying the precise bleeding site. During the arterial phase, active extravasation may exhibit a jetlike or swirling appearance . Confirmation of the diagnosis can be achieved by observing contrast material pooling at the same site during the venous phase on dual-phase CT images .Patients whose condition is unstable may directly undergo conventional angiography for both diagnosis and therapy.”
    Imaging after Pancreatic Surgery: Expected Findings and Postoperative Complications
    Ayman H. Gaballah et al.
    RadioGraphics 2024; 44(1):e230061
  • “Bowel ischemia can also occur secondary to arterial or portal venous occlusion. In addition to the direct sign of vascular occlusion, other possible findings include bowel wall thickening, hemorrhage as evidenced by hyperattenuating bowel wall on unenhanced CT images, nonenhancement of the bowel wall, pneumatosis intestinalis, and portal venous gas. Ischemic gastropathy is a complication of an Appleby procedure and can manifest with refractory gastric ulcers, which may be complicated by bleeding or perforation. Beger and Frey procedures involve resection of the pancreatic head and may lead to ischemia of the CBD or duodenum owing to the possible disruption of their blood supply.”
    Imaging after Pancreatic Surgery: Expected Findings and Postoperative Complications
    Ayman H. Gaballah et al.
    RadioGraphics 2024; 44(1):e230061
  • “Seeding metastases, from pancreatic cancer following pancreatectomy or interventional procedures, is a rare complication with a few cases reported in the literature. In most cases, tumor recurrence occurred within the body wall at the laparotomy site, along the course of the postsurgical drain, or along the tract of a needle biopsy or percutaneous transhepatic biliary drainage catheter. Seeding metastasis within the posterior wall of the stomach has also been documented following an endoscopic US-guided fine needle aspiration of pancreatic cancer. The imaging features of the metastatic deposits can be similar to those of the primary tumor.”
    Imaging after Pancreatic Surgery: Expected Findings and Postoperative Complications
    Ayman H. Gaballah et al.
    RadioGraphics 2024; 44(1):e230061
  • Serous cystadenoma (SCA) is a benign cystic pancreatic neoplasm of the pancreas, accounting for approximately 15% of resected pancreatic cysts. Current recommendations are to proceed with surgical resection in symptomatic patients or when there is uncertainty regarding diagnosis. The latter continues to be a challenge since intentional resection of a serous cystadenoma account for only a minority of resected of cases.
    Pancreatic Serous Cystadenoma: A Continuing Diagnostic Challenge.  
    Assawasirisin, Charnwit et al.  
    Annals of Surgery ():10.1097/SLA.0000000000006203, January 17, 2024
  • “A total of 250 patients were analyzed. Median age was 62 (range 22 – 89), 65% were female, and 34% had symptoms. Tumor size ranged from 0.6 to 20, with a median of 3.4 cm. The morphological appearance was microcystic in 58%, macrocystic in 16%, mixed-type in 23%, and solid in 3%. Pancreatic duct dilation and pancreatic atrophy were found in 22% and 14%, respectively. The average growth rate was 1.8 mm/year regardless of tumor size. Of the 172 patients who underwent surgery, serous cystadenoma was the preoperative diagnosis in only 33%. A correct diagnosis was independently associated with large tumors and cyst fluid CEA analysis. Pancreatic duct dilation was independently associated with an in-growing cyst and presence of calcification.”
    Pancreatic Serous Cystadenoma: A Continuing Diagnostic Challenge.  
    Assawasirisin, Charnwit et al.  
    Annals of Surgery ():10.1097/SLA.0000000000006203, January 17, 2024
  • “SCA is a slow-growing pancreatic cystic neoplasm that is mostly asymptomatic but can lead to pancreatic duct dilation and atrophy in some patients. A surprisingly small number of correct preoperative diagnoses confirms that this entity continues to be a diagnostic challenge. A more thorough preoperative workup that includes EUS should improve the rate of mis-diagnosis..”
    Pancreatic Serous Cystadenoma: A Continuing Diagnostic Challenge.  
    Assawasirisin, Charnwit et al.  
    Annals of Surgery ():10.1097/SLA.0000000000006203, January 17, 2024
PET-CT

  • • [18F] Fluorodeoxyglucose18F-FDG) PET/CT can improve the staging accuracy and clinical management of patients with hepatobiliary and pancreatic cancers, by detection of unsuspected metastases.  
    • 18F-FDG PET/CT metabolic parameters are valuable in predicting treatment response and survival.  
    • Metabolic response on 18F-FDG PET/CT can predict preoperative pathologic response to neoadjuvant therapy in patients with pancreatic cancer and determine prognosis.  
    • Several novel non-FDG tracers, such as 68-Ga prostate-specific membrane antigen and 68Gafibroblast activation protein inhibitor PET/CT, show promise for imaging hepatobiliary and pancreatic cancers with potential for radioligand therapy.
    Quarter-Century PET/ Tomography Transformation of Oncology Hepatobiliary and Pancreatic Cancer
    Asha Kandathil et al.
    PET Clin (in press) 2024
  • “18F-FDG PET/CT has reported sensitivity of 85%to 100%, specificity of 61% to 94%, and accuracy of 84% to 95% in diagnosing pancreatic cancer.39–42 FDG uptake by pancreatic cancer correlates with increased Ki-67 and is highest in poorly differentiated tumors. Medium- or well-differentiated pancreatic cancers may not have increased FDG uptake. Inflammatory lesions such as chronic lymphoplasmacytic pancreatitis, autoimmune pancreatitis, and tuberculosis may have increased FDG uptake.”  
    Quarter-Century PET/ Tomography Transformation of Oncology Hepatobiliary and Pancreatic Cancer
    Asha Kandathil et al.
    PET Clin (in press) 2024
  • In a multicenter prospective study conducted in 18 UK pancreatic tertiary referral centers, Ghaneh and colleagues evaluated the performance of multidetector CT (MDCT) in 589 patients and FDG PET/CT in 550 patients with suspected pancreatic cancer. MDCT had a sensitivity of 88.5%and specificity of 70.6%; FDG PET/CT had a sensitivity of 92.7% and specificity of 75.8% for the diagnosis of pancreatic cancer. Pancreatic cancer had a higher median SUVmax of 7.5 compared with median SUVmax of 5.7 for other lesions. Adding PET/ CT to standard workup improved pancreatic cancer diagnosis, staging, and management.
    Quarter-Century PET/ Tomography Transformation of Oncology Hepatobiliary and Pancreatic Cancer
    Asha Kandathil et al.
    PET Clin (in press) 2024
  • “Surgical resection is the only curative option for pancreatic cancer; however, more than 80% of patients present unresectable disease due to locally advanced disease or distant metastases. Borderline resectable pancreatic cancer (BRPC) patients who could be eligible for radical surgery following neoadjuvant chemotherapy may have local arterial or venous (superior mesenteric vein/ portal vein) invasion.44 PET has less spatial resolution and accuracy than CT in assessing locoregional involvement, which is critical in therapeutic decision-making in pancreatic cancer. CT, MR imaging, and endoscopic ultrasound are better at defining tumor’s border and local spread.45 However, PET/CT performs better than CT in identifying unsuspected metastases, reducing the frequency of futile surgeries.”
    Quarter-Century PET/ Tomography Transformation of Oncology Hepatobiliary and Pancreatic Cancer
    Asha Kandathil et al.
    PET Clin (in press) 2024
  • “In a study of the utility of 18F-FDG PET/CT in assessing treatment response in 20 patients with LAPC treated with neoadjuvant chemo-RT, Choi and colleagues observed that mean survival was longer (23.2 months) in patients with   50% decrease in SUV between pre-study PET scan and PET scan after the first cycle of chemotherapy, as compared with 11.3 months in patients with less than 50% decrease in SUV.”  
    Quarter-Century PET/ Tomography Transformation of Oncology Hepatobiliary and Pancreatic Cancer
    Asha Kandathil et al.
    PET Clin (in press) 2024
Small Bowel

  • “Cinematic rendering has multiple applications in the abdomen and may serve as an important adjunct to standard CT images in the evaluation of a variety of abdominal conditions. Cinematic rendering offers the potential for comprehensive assessment of ileal NETs as it improves the appreciation of relationships between the tumor and surrounding organs, and delineation of the major vascular supply, which may influence surgical planning and help anticipate the radicality of associated ileal loop resection. Our findings provide additional evidence on the role of cinematic rendering for preoperative planning of ileal NETs compared to more traditional CT imaging.”
    Comprehensive preoperative assessment of ileal neuroendocrine tumor with cinematic rendering.  
    Pellat A, Terris B, Soyer P.  
    Diagn Interv Imaging. 2024 Jan;105(1):40-41. 
  • “Cinematic rendering is a 3D reconstruction technique inspired by the animated movie industry. It follows the same steps used for volume rendering in determining colour and opacity that models real-life physical propagation of light providing photorealistic 3D images with more surface details.2 The application of cinematic rendering in clinical practice has been described for pre-operative planning of tumours such as GIST. Originally clinical use of 3D imaging was confined to calculating organ volumes or orthopedic applications; however, the use of helical technology for the propagation of thin slice computed tomography (CT) in conjunction with advanced image reconstruction software has allowed this to be utilized for a variety of other applications.3 Applications for cinematic rendering have been reported to include lesion characterization, localization, and risk stratification in the pre-operative setting. This has been adopted in the literature to date for the assessment of liver masses, pancreatic cancer, gastric tumours, leiomyosarcomas, gastrointestinal bleeding and GIST, to name a few.”
    Utilization of Cinematic Rendering for Evaluation of Gastrointestinal Stromal Tumours (GIST).  
    O’Brien C.
    Canadian Association of Radiologists Journal. 2023;0(0). doi:10.1177/08465371231221936
  • “Cinematic rendering of GIST helps demonstrate the submucosal origin of the mass and visualize the dynamic enhancement pattern within the tumour allowing for better anatomical evaluation of the lesion providing more information on areas of necrosis and enhancement. Additionally, there is increased information regarding the growth pattern, vascular supply, adjacent anatomic structures, and blood vessels which improves pre-operative planning. Active bleeding from a small bowel tumour is difficult to characterize on conventional CT. Cinematic rendering can more easily detect if there is bleeding from a small bowel tumour. It also provides increased information to differentiate GIST form other gastrointestinal tumours, especially at the ampulla and in the pelvis where anatomical detail is limited on conventional CT. The use of cinematic rendering in GIST is particularly useful as this technique provides exquisite mucosal detail which increases sensitivity for assessment of gastrointestinal mucosal fold changes. Lastly, the ability to produce vascular mapping of a GIST with cinematic rendering allows localization of the feeding vessel in a preoperative setting. Many of the features described are also used to risk stratify GISTs from very low to high risk for recurrence; the added value of cinematic rendering for assessment of GIST may provide a future role for imaging estimation of risk.”
    Utilization of Cinematic Rendering for Evaluation of Gastrointestinal Stromal Tumours (GIST).  
    O’Brien C.
    Canadian Association of Radiologists Journal. 2023;0(0). doi:10.1177/08465371231221936
  •        “As Barat et al discuss, there are limitations to adopting cinematic rendering into clinical practice. However, the scope for future developments is an exciting avenue for improving management of GIST including investigating gene mutations, and incorporating it into a hybrid imaging tool such as positron emission tomography/CT. This technique also has other potential applications including teaching anatomy with more photorealistic images simulating cadaveric specimens. Patient education could be improved with illustration of pathologic diseases in the pre-treatment setting and in the future to be used as an alternative to three-dimensional printing. Cinematic rendering is an exciting new technique currently in its infancy that has the potential to add great value to our practice. To fulfill the advice of Dr Brady: to move forward and keep up, the next step should be to investigate how to implement cinematic rendering into our day-to-day practice.  
    Utilization of Cinematic Rendering for Evaluation of Gastrointestinal Stromal Tumours (GIST).  
    O’Brien C.
    Canadian Association of Radiologists Journal. 2023;0(0). doi:10.1177/08465371231221936
  • “Cinematic rendering is an exciting new technique currently in its infancy that has the potential to add great value to our practice. To fulfill the advice of Dr Brady: to move forward and keep up, the next step should be to investigate how to implement cinematic rendering into our day-to-day practice.”
    Utilization of Cinematic Rendering for Evaluation of Gastrointestinal Stromal Tumours (GIST).  
    O’Brien C.
    Canadian Association of Radiologists Journal. 2023;0(0). doi:10.1177/08465371231221936
  • “Mesothelioma has been linked to toxic exposure to industrial pollutants, especially asbestos. The most common site is the visceral pleura, followed by the peritoneum. Because pleural mesothelioma is more common than malignant peritoneal mesothelioma (MPM), most research has been on the pleural variant. The assumption has been that mesothelioma in the peritoneum would be biologically similar to the pleura, but some differences have been found. MPM commonly presents with diffuse, extensive spread throughout the abdomen with rare metastatic spread beyond the abdominal cavity.”
    Malignant peritoneal mesothelioma: a review.
    Kim J, Bhagwandin S, Labow DM.  
    Ann Transl Med. 2017 Jun;5(11):236
  • “Mesothelioma has been linked to industrial pollutants and mineral exposure. The most common carcinogen identified for pleural mesothelioma has been asbestos, with approximately 80% of cases linked to asbestos exposure. While asbestos is also the best defined risk factor for MPM, the link is weaker. Only 33–50% of patients diagnosed with MPM report any known prior exposure to asbestos. Time and duration of exposure do not directly correlate with disease development, with some long-term exposures yielding no disease while some short-term exposures leading to significant tumor burden.”
    Malignant peritoneal mesothelioma: a review.
    Kim J, Bhagwandin S, Labow DM.  
    Ann Transl Med. 2017 Jun;5(11):236
  • “On CT, MPM appears as a solid, heterogeneous, soft tissue mass with irregular margins that enhances with the use of intravenous (IV) contrast. MPM tends to be more expansive than infiltrative so diffuse distribution throughout the abdominal cavity should raise suspicion. The lack of a primary site with neither lymph node involvement nor distant metastases helps differentiate MPM from other intra-abdominal malignancies . Ascites is found in 60–100% of patients that are newly diagnosed. Other findings include caking, thickening or masses in the omentum, mesenteric nodules, peritoneal thickening, diaphragmatic involvement, scalloping of the intraabdominal organs such as the liver and spleen, and loculated ascites.”
    Malignant peritoneal mesothelioma: a review.
    Kim J, Bhagwandin S, Labow DM.  
    Ann Transl Med. 2017 Jun;5(11):236
  • “MPM can be difficult to diagnose based solely on histologic patterns, making immunohistochemical markers important in diagnosis. No single immunohistochemical marker is specific for MPM. Instead, panels of markers are used to differentiate MPM from other more common tumors that can have similar histologic features. MPM stains positive for EMA, calretinin, CK 5/6, WT-1, mesothelin, and antimesothelial cell antibody-1, and negative for carcinoma markers CEA, Ber-EP4, LeuM1, and Bg8 thyroid transcription factor-1, and B72.3. These markers help differentiate MPM from primary papillary serous carcinoma of the peritoneum, serous ovarian carcinomas, colorectal adenocarcinoma involving the peritoneum, and borderline serous tumors. The current recommendation is to use two mesothelioma markers and two carcinoma markers.”
    Malignant peritoneal mesothelioma: a review.
    Kim J, Bhagwandin S, Labow DM.  
    Ann Transl Med. 2017 Jun;5(11):236
  • “MPM is a very rare disease of peritoneal surfaces which is diagnosed less frequently than the pleural variant. Advances have been made in treatment, with CRS-HIPEC as first-line therapy in those with favorable factors. While systemic chemotherapy has been shown to be effective, further advancements in systemic therapy are likely to be found in targeting molecular pathways. Investigations into this treatment modality are underway and are promising for providing better survival for this disease which is currently ultimately fatal due to its aggressive extensive peritoneal spread.”
    Malignant peritoneal mesothelioma: a review.
    Kim J, Bhagwandin S, Labow DM.  
    Ann Transl Med. 2017 Jun;5(11):236
  • “Cinematic rendering has multiple applications in the abdomen and may serve as an important adjunct to standard CT images in the evaluation of a variety of abdominal conditions. Cinematic rendering offers the potential for comprehensive assessment of ileal NETs as it improves the appreciation of relationships between the tumor and surrounding organs, and delineation of the major vascular supply, which may influence surgical planning and help anticipate the radicality of associated ileal loop resection. Our findings provide additional evidence on the role of cinematic rendering for preoperative planning of ileal NETs compared to more traditional CT imaging.”
    Comprehensive preoperative assessment of ileal neuroendocrine tumor with cinematic rendering.  
    Pellat A, Terris B, Soyer P.  
    Diagn Interv Imaging. 2024 Jan;105(1):40-41. 
  • Cinematic rendering is a 3D reconstruction technique inspired by the animated movie industry. It follows the same steps used for volume rendering in determining colour and opacity that models real-life physical propagation of light providing photorealistic 3D images with more surface details. The application of cinematic rendering in clinical practice has been described for pre-operative planning of tumours such as GIST. Originally clinical use of 3D imaging was confined to calculating organ volumes or orthopedic applications; however, the use of helical technology for the propagation of thin slice computed tomography (CT) in conjunction with advanced image reconstruction software has allowed this to be utilized for a variety of other applications. Applications for cinematic rendering have been reported to include lesion characterization, localization, and risk stratification in the pre-operative setting.  
    Utilization of Cinematic Rendering for Evaluation of Gastrointestinal Stromal Tumours (GIST)
    Ciara O’Brien
    Canadian Association of Radiologists Journal (in press)
  • “Cinematic rendering of GIST helps demonstrate the submucosal origin of the mass and visualize the dynamic enhancement pattern within the tumour allowing for better anatomical evaluation of the lesion providing more information on areas of necrosis and enhancement. Additionally, there is increased information regarding the growth pattern, vascular supply, adjacent anatomic structures, and blood vessels which improves pre-operative planning. Active bleeding from a small bowel tumour is difficult to characterize on conventional CT. Cinematic rendering can more easily detect if there is bleeding from a small bowel tumour. It also provides increased information to differentiate GIST form other gastrointestinal tumours, especially at the ampulla and in the pelvis where anatomical detail is limited on conventional CT.”
    Utilization of Cinematic Rendering for Evaluation of Gastrointestinal Stromal Tumours (GIST)
    Ciara O’Brien
    Canadian Association of Radiologists Journal (in press)
  • “Cinematic rendering is an exciting new technique currently in its infancy that has the potential to add great value to our practice. To fulfill the advice of Dr Brady: to move forward and keep up, the next step should be to investigate how to implement cinematic rendering into our day-to-day practice.”
    Utilization of Cinematic Rendering for Evaluation of Gastrointestinal Stromal Tumours (GIST)
    Ciara O’Brien
    Canadian Association of Radiologists Journal (in press)
Vascular

  • “Non-traumatic thoracic aorta emergencies are acute conditions associated with substantial morbidity and mortality. In the emergency setting, timely detection of aortic injury through radiological imaging is crucial for prompt treatment planning and favorable patient outcomes. 3D cinematic rendering (CR), a novel rendering algorithm for computed tomography (CT) image processing, allows for life-like visualization of spatial details and contours of highly complex anatomic structures such as the thoracic aorta and its vessels, generating a photorealistic view that not just adds to diagnostic confidence, but is especially useful for non-radiologists, including surgeons and emergency medicine physicians. In this pictorial review, we demonstrate the utility of CR in the setting of non-traumatic thoracic aorta emergencies through 10 cases that were processed at a standalone 3D CR station at the time of presentation, including its role in diagnosis and management.”
    Cinematic rendering of non-traumatic thoracic aorta emergencies: a new look at an old problem.  
    Yasrab M, Rizk RC, Chu LC, Fishman EK.  
    Emerg Radiol. 2024 Jan 18. doi: 10.1007/s10140-024-02204-6. Epub ahead of print.
  • “Routinely employed 3D post-processing tools include maximum intensity projection (MIP) and volume rendering (VR) that allow for the generation of angiographic images and a more intuitive and interactive representations of the spatial information in the dataset, respectively. Improving upon traditional VR, 3D cinematic rendering (CR) is a Food andDrug Administration (FDA)-approved technique that employs a novel lighting model to generate photorealistic images. CR involves global illumination and path tracing models whereby numerous light rays from all directions propagate through and interact with the volumetric data to generate a voxel. Complex anatomical relations are better evaluated and enhanced depth and shape perception is achieved as the technique considers a natural lighting environment and its effects (e.g., reflection, diffusion, refraction). Postprocessing windowing and the use of clip planes/masks allow cutting into the volume and isolation of the area/organ of interest.”
    Cinematic rendering of non-traumatic thoracic aorta emergencies: a new look at an old problem.  
    Yasrab M, Rizk RC, Chu LC, Fishman EK.  
    Emerg Radiol. 2024 Jan 18. doi: 10.1007/s10140-024-02204-6. Epub ahead of print.
  • “There are some limitations that come with 3D CR. Notably, shadows generated in the images might conceal certain pathologies when viewed from specific angles, necessitating meticulous optimization and assessment from diverse angles in conjunction with the multiplanar reformations. Thus, while an initial learning period to become adept in handling and familiarizing themselves with the CR process is required for radiologists, as demonstrated in our case studies, an experienced radiologist can efficiently execute the rendering process in under 5 min.”
    Cinematic rendering of non-traumatic thoracic aorta emergencies: a new look at an old problem.  
    Yasrab M, Rizk RC, Chu LC, Fishman EK.  
    Emerg Radiol. 2024 Jan 18. doi: 10.1007/s10140-024-02204-6. Epub ahead of print.
  • “Color mapping of different phases enhances visualization of the key pathology, such as the flow through the false and true lumens in a dissection that can be delineated by high contrast shading. CR rendering emphasizes textural changes attributable to inflammatory processes with realistic shadowing that is otherwise difficult to appreciate. The improved surface detail helps characterize an impending PAU or the nature of outpouchings suspicious for mycotic aneurysms and gives a clearer view of multiple plaques and sites of ulceration that could be otherwise missed.”
    Cinematic rendering of non-traumatic thoracic aorta emergencies: a new look at an old problem.  
    Yasrab M, Rizk RC, Chu LC, Fishman EK.  
    Emerg Radiol. 2024 Jan 18. doi: 10.1007/s10140-024-02204-6. Epub ahead of print.
  • “Another application of 3D CR is via the black blood cinematic rendering (BBCR) preset.. BBCR is a preset we specifically developed to visualize intraluminal contours and structures of the heart and great vessels, all through adjustments that can be madein under a minute. This is especially useful in the setting of visualizing various zones of thrombi and occlusion, the degree of obstruction, and the subtle irregularities and internal arrangement of the thrombus that can only be appreciateddue to enhanced depth perception and shadowing.”
    Cinematic rendering of non-traumatic thoracic aorta emergencies: a new look at an old problem.  
    Yasrab M, Rizk RC, Chu LC, Fishman EK.  
    Emerg Radiol. 2024 Jan 18. doi: 10.1007/s10140-024-02204-6. Epub ahead of print.
  • “The intrinsic features of 3D CR with its ability to provide a holistic field of view of the vascular map increases confidence in management and surgical planning. A global viewing angle of the thoracic aorta helps in tracking the dissection and its involvement of the aorta and the extent of mediastinal and pericardial bleeding where present .In cases where patients underwent thoracic endovascular aortic repair (TEVAR), coiling, or graft repairing, CR adds to surgical planning by improved depth perception, shadow effects, and realistic textures, demonstrating the anatomical relationships of the thoracic aorta, surrounding structures, and the pathology to be addressed, with photorealism providing the surgeon a familiar perspective to work with.”
    Cinematic rendering of non-traumatic thoracic aorta emergencies: a new look at an old problem.  
    Yasrab M, Rizk RC, Chu LC, Fishman EK.  
    Emerg Radiol. 2024 Jan 18. doi: 10.1007/s10140-024-02204-6. Epub ahead of print.
  • “3D cinematic rendering (CR) represents an important advancement in radiological imaging, particularly in enhancing the visualization of complex anatomical structures and systems such as the thoracic aorta and its vessels. CR provides detailed, photorealistic illustrations crucial for diagnosis and surgical planning as we have seen in several cases. Future research is needed to evaluate CR’s diagnostic accuracy, both prospectively and in head-to-head comparisons with other rendering methods, as well as its role in other domains such as patient education and medical training. CR, therefore, is emerging as a promising, evolving tool for radiologists, surgeons, and the patients they treat.”  
    Cinematic rendering of non-traumatic thoracic aorta emergencies: a new look at an old problem.  
    Yasrab M, Rizk RC, Chu LC, Fishman EK.  
    Emerg Radiol. 2024 Jan 18. doi: 10.1007/s10140-024-02204-6. Epub ahead of print.
  • SVCS is a combination of signs and symptoms that result from the compression or occlusion of the superior vena cava, associated with a significant morbidity and mortality. While thoracic malignancy is the most common cause of SVCS accounting for more than 60% of the cases, benign causes are on the rise with the increasing use of central venous catheters and indwelling cardiac devices .Benign SVCS usually has a more insidious course compared to malignant causes, as there is time for the development of adequate collaterals to bypass the central venous occlusion.
    Superior vena cava syndrome with the hepatic ‘hot spot’ sign.
     Koratala, A., Bhatti, V.  
    Intern Emerg Med 13, 293–294 (2018).
  • A CT scan of the chest with contrast excluded acute pulmonary embolism, but showed extensive chest wall venous collaterals with near-complete occlusion of the superior vena cava. In addition, it demonstrated the “focal hepatic hot spot sign,” which is an enhanced area in the segment IV or quadrate lobe of the liver, which results from the communication between superficial epigastric veins and left portal vein in cases of superior vena cava obstruction
    Superior vena cava syndrome with the hepatic ‘hot spot’ sign.  
    Koratala, A., Bhatti, V.  
    Intern Emerg Med 13, 293–294 (2018).
  • OBJECTIVE. The purpose of this article is to review the CT findings associated with superior  vena  cava  obstruction  and  to  illustrate  collateral  venous  pathways  bypassing  the  ob-struction as shown on MDCT.
    CONCLUSION. Multiple collateral venous pathways can form to bypass an obstruction of the superior vena cava. With its ability to acquire near isotropic data, MDCT allows high-quality reformations and thus exquisitely displays these venous collaterals and has the potential to aid in planning therapy to bypass the obstruction.      
    Superior Vena Cava Obstruction Evaluation With MDCT              
    Sheila Sheth, Mark D. Ebert, and Elliot K. Fishman              
    American Journal of Roentgenology 2010 194:4, W336-W346
  • “Obstruction  of  the  superior  vena  cava  re-sults  in  impaired  venous  drainage  of  the head  and  neck  and  upper  extremities.  Clinical  manifestations  include  facial  and  neck swelling, distended neck veins, headache due to  cerebral  edema,  dyspnea,  and,  in  severe cases, stridor and altered mental status. Cor-relation of imaging studies with clinical find-ings  suggests  that  the  severity  of  symptoms depends on the level of obstruction (above or below  the  level  of  the  azygos  arch)  and  the development of rich collateral network. In fact, CT can detect subclinical superior vena cava obstruction in patients who are relatively asymptomatic.”        
    Superior Vena Cava Obstruction Evaluation With MDCT              
    Sheila Sheth, Mark D. Ebert, and Elliot K. Fishman              
    American Journal of Roentgenology 2010 194:4, W336-W346
  • “The  radiologist  should  be  familiar  with findings  on  abdominal  CT  that  suggest  the presence  of  a  superior  vena  cava  obstruc-tion. In addition to enhancing round or tortu-ous vascular channels in the abdominal wall,  perfusion  abnormalities  in  the  liv-er  and  the  so-called  “hot  spot”  initially  de-scribed on nuclear medicine both result from communication  between  superficial  epigas-tric veins and left portal vein. On CT, there is intense opacification of the anterior quadrate  lobe.  The  area  of  enhancement  is  characteristic  in  its  position  as  well  as  its  shape and  should  not  be  mistaken  for  a  hypervascular mass.”
    Superior Vena Cava Obstruction Evaluation With MDCT
    Sheila Sheth, Mark D. Ebert, Elliot K. Fishman
    AJR 2010; 19 4:336–346 
  • “Fibrosing mediastinitis  is  a  rare  histologically  benign  disorder caused by proliferation of collagen tissue  and  fibrosis  in  the  mediastinum.  It  may be idiopathic, caused by an abnormal immunologic response to Histoplasma capsulatum infection or to tuberculosis, or it may be related  to  retroperitoneal  fibrosis,  particularly in its diffuse form. Radiation-induced fibro-sis is another potential cause of superior vena cava obstruction.”
    Superior Vena Cava Obstruction Evaluation With MDCT
    Sheila Sheth, Mark D. Ebert, Elliot K. Fishman
    AJR 2010; 19 4:336–346 
  • “The incidence of catheter-induced supe-rior vena cava obstruction is rapidly increasing. Large  central  venous  catheters,  such  as  dialysis catheters, Hickman catheters, and parenter-al nutrition catheters, have all been implicated in superior vena cava obstruction. Transvenous permanent  cardiac  pacemaker  implantation  is another  risk  factor,  particularly  after  an  atrio-ventricular node ablation procedure.”
    Superior Vena Cava Obstruction Evaluation With MDCT
    Sheila Sheth, Mark D. Ebert, Elliot K. Fishman
    AJR 2010; 19 4:336–346
  • “The  azygos  and  hemiazygos veins  can  divert  blood  away  from  the  superior  vena  cava.  If  the  level  of  superior  vena cava  obstruction  is  above  the  azygos  arch, antegrade  flow  from  the  azygos  to  the  right atrium  is  seen,  with  abrupt  transition  between  a  densely  opacified  azygos  above  the arch and an unopacified inferior azygos vein. If  the  obstruction  is  below  the  arch,  the  entire azygos and hemiazygos veins are bright-ly  opacified  as  the  blood  flows  in  a  retro-grade  fashion  toward  the  inferior  vena  cava .”
    Superior Vena Cava Obstruction Evaluation With MDCT
    Sheila Sheth, Mark D. Ebert, Elliot K. Fishman
    AJR 2010; 19 4:336–346 
  • “Repair of sporadic aortic root and ascending aortic aneurysms when they reach a maximum diameter of 5.5 cm is strongly recommended (SR; nonrandomized studies [NR]); it is reasonable to repair at a diameter of 5.0 cm when care can occur at a high-volume center with management by a multidisciplinary aortic team (MR; NR). It is reasonable to repair the aorta in patients at increased risk of adverse aortic events, and some genetic aortopathies at even lower thresholds (MR; LD).”
    Diagnosis and Management of Aortic Diseases.  
    Altenburg MM, Davis AM, DeCara JM.  
    JAMA. 2023 Dec 21. doi: 10.1001/jama.2023.23668. Epub ahead of print. PMID: 38127327. 
  • • First-degree relatives of patients with aortic root aneurysms,ascending aortic aneurysms, or history of aortic dissection should have screening for aortic disease (SR; LD).
    • Preconception counseling on risks of pregnancy-associated aortic dissection is recommended for patients with bicuspid aortic valve and aortic dilatation,syndromic and nonsyndromic thoracic aortic disease, and Turner syndrome (SR; LD).
    Diagnosis and Management of Aortic Diseases.  
    Altenburg MM, Davis AM, DeCara JM.  
    JAMA. 2023 Dec 21. doi: 10.1001/jama.2023.23668. Epub ahead of print. PMID: 38127327. 
  • • A multidisciplinary team should determine the most appropriate type of intervention for patients with acute aortic disease requiring urgent repair(strong recommendation [SR; benefit much greater than risk]; expert opinion [EO]). Patients with asymptomatic extensive disease, multiple comorbidities, or who may require complex repairs may be referred to centers with higher case volumes( 30-40cases/y) and a multidisciplinary aortic team(moderate recommendation [MR; benefit greater than risk]; limited data [LD]).
    Diagnosis and Management of Aortic Diseases.  
    Altenburg MM, Davis AM, DeCara JM.  
    JAMA. 2023 Dec 21. doi: 10.1001/jama.2023.23668. Epub ahead of print. PMID: 38127327.
  • Type A aortic dissection has a mortality rate of 57% without emergency surgery and up to 25%with emergency surgery. This guideline addresses thoracic and abdominal aortic disease, genetic and hereditable aortopathies, peripheral artery disease, bicuspid aortic valves, and Turner syndrome. Herein, we focus mainly on recommendations for aneurysms that involve the aortic root and/or the ascending aorta.
    Diagnosis and Management of Aortic Diseases.  
    Altenburg MM, Davis AM, DeCara JM.  
    JAMA. 2023 Dec 21. doi: 10.1001/jama.2023.23668. Epub ahead of print. PMID: 38127327.
  • “In a major change, the guideline suggests that it is reasonable to repair sporadic aneurysms of the aortic root or ascending aorta in select patients with low surgical risk when the aneurysm reaches 5.0cm, provided management is at a high-volume center by experienced surgeons as part of a multidisciplinary aortic team. This suggestion is based on observational data from the Multi-Ethnic Study of Atherosclerosis database, which modeled risk of dissection at various aortic diameters relative to 3.4 cm or smaller: aorta diameters were less than 3.5 cmin 79.2%, 3.5 to 3.9 cmin 18.0%, 4.0 to 4.4 cm in 2.6%, and 4.5 cm or greater in 0.22%.”  
    Diagnosis and Management of Aortic Diseases.  
    Altenburg MM, Davis AM, DeCara JM.  
    JAMA. 2023 Dec 21. doi: 10.1001/jama.2023.23668. Epub ahead of print. PMID: 38127327.
  • The recommendation for exercise limits deserves additional supportive evidence, as it is not clear to what degree aortic dissections are precipitated by increased wall stress or decreased wall strength.  The recommendation of referrals to high-volume centers for certain complex asymptomatic patients may face insurance and travel barriers. Studies are needed to better stratify which patients merit travel to high-volume centers. Similarly, prospective studies show that despite a lower overall incidence, women appear to have a 2- to 3-fold increased risk of fatal aortic rupture relative to men (hazard ratio, 2.60; 95%CI, 1.58-4.29; P < .001). Determining sex specific surgical thresholds for aneurysms of the aortic root and TAA are a high priority for future investigation.
    Diagnosis and Management of Aortic Diseases.  
    Altenburg MM, Davis AM, DeCara JM.  
    JAMA. 2023 Dec 21. doi: 10.1001/jama.2023.23668. Epub ahead of print. PMID: 38127327.

Privacy Policy

Copyright © 2024 The Johns Hopkins University, The Johns Hopkins Hospital, and The Johns Hopkins Health System Corporation. All rights reserved.