google ads
November 2022 Imaging Pearls - Educational Tools | CT Scanning | CT Imaging | CT Scan Protocols - CTisus
Imaging Pearls ❯ November 2022

-- OR --

3D and Workflow

  • “Recent advances in 3-dimensional visualization of volumetric computed tomography data have led to the novel technique of cinematic rendering (CR), which provides photorealistic images with enhanced surface detail and realistic shadowing effects that are generally not possible with older methods such as volume rendering. The emergence of CR coincides with the increasingly widespread availability of virtual reality (VR)/ augmented reality (AR) interfaces including wearable headsets. The intersection of these technologies suggests many potential advances, including the ability of interpreting radiologists to look at photorealistic images of patient pathology in real time with surgeons and other referring providers, so long as VR/AR headsets are deployed and readily available. In this article, we will present our initial experience with viewing and manipulating CR images in the context of a VR/AR headset. We include a description of key aspects of the software and user interface, and provide relevant pictorial examples that may help potential adopters understand the initial steps of using this exciting convergence of technologies. Ultimately, trials evaluating the added value of the combination of CR with VR/AR will be necessary to understand the potential impact of these methods on medical practice.”
    Augmented Reality With Cinematic Rendered 3-Dimensional Images From Volumetric Computed Tomography Data
    Steven P. Rowe, MD, PhD,* Robert Schneider, PhD,† Sebastian Krueger, PhD,† Valerie Pryde, RT, CIIP,* Linda C. Chu, MD,* and Elliot K. Fishman, MD*
    J Comput Assist Tomogr • (in press) 2022
  • “In parallel to the development of CR, virtual reality (VR)/ augmented reality (AR) has also been increasingly incorporated intomedical imaging The combination of photorealistic CR images with a VR/AR interface can facilitate real-time discussions between imaging specialists and clinicians and allow multiple individuals from an interdisciplinary team to see and manipulate the CR images. Photorealistic images are necessary to create the proper depth and immersion to best leverage VR/AR emerging technology. In this article, we will describe our initial experience with the HoloLens headset as a display for CR images and offer observations on the interface and its potential future applications.”
    Augmented Reality With Cinematic Rendered 3-Dimensional Images From Volumetric Computed Tomography Data
    Steven P. Rowe, MD, PhD,* Robert Schneider, PhD,† Sebastian Krueger, PhD,† Valerie Pryde, RT, CIIP,* Linda C. Chu, MD,* and Elliot K. Fishman, MD*
    J Comput Assist Tomogr • (in press) 2022I
  • “With the CR image projected into AR, the user can make a brief squeezing motion with his/her hand and outline the image. A white cube surrounds the CR image, and the user can either manipulate the image from the corners of the cube (pinching a corner and moving in or out will zoom the image) or, with another hand motion, covert the cube to have linear projections from the middle of the sides, which permit the user to spin the image or apply cut-planes. Please note that in capturing images for the figures in this article, it was difficult to film the cube, hence this feature of the software is not shown. The user can also walk around the CR hologram to see obscured anatomy or pathology, although this should be done with caution in an area cleared of trip hazards, because the user's vision is restricted by the headset and the projected CR hologram.”
    Augmented Reality With Cinematic Rendered 3-Dimensional Images From Volumetric Computed Tomography Data
    Steven P. Rowe, MD, PhD,* Robert Schneider, PhD,† Sebastian Krueger, PhD,† Valerie Pryde, RT, CIIP,* Linda C. Chu, MD,* and Elliot K. Fishman, MD*
    J Comput Assist Tomogr • (in press) 2022I
  • “There are other potential advantages of the combination of CR and AR/VR. The rise of artificial intelligence (AI) as a driving force in the future of radiology suggests that new visualization methods for volumetric data may be important as data inputs for graphical processing unit–driven AI workstations. Adding AR/ VR to CR visualizations may allow nonradiologists to have input into the images that are sent to the picture archiving and communication system and facilitate the incorporation of clinical data into ensemble AI algorithms.”
    Augmented Reality With Cinematic Rendered 3-Dimensional Images From Volumetric Computed Tomography Data
    Steven P. Rowe, MD, PhD,* Robert Schneider, PhD,† Sebastian Krueger, PhD,† Valerie Pryde, RT, CIIP,* Linda C. Chu, MD,* and Elliot K. Fishman, MD*
    J Comput Assist Tomogr • (in press) 2022I
  • “CR of PET/CT data provides a photorealistic means of visualizing complex fusion imaging datasets. Such visualizations may aid anatomic understanding for surgical or procedural applications, may improve teaching of trainees, and may allow improved communication with patients.”
    Photorealistic three‑dimensional visualization of fusion datasets: cinematic rendering of PET/CT
    Steven P. Rowe · Martin G. Pomper · Jeffrey P. Leal · Robert Schneider · Sebastian Krüger · Linda C. Chu · Elliot K. Fishman 
  • The external light used for CR is emitted from a high dynamic range (HDR) lightmap that defines the environment of the rendering. Because CR is based on the enhanced rendering equation, it can support the option that external light can not only be scattered and reflected, but internal light can also be emitted by a volume or a segmentation. In the current algorithm, we added a parameter for the PET dataset that defines how much light is emitted by the PET, which can also be set to zero so that in such a case no internal light is emitted at all. To have more flexibility to influence internal versus external light, we also added a parameter that scales the intensity of the external light emitted from the lightmap.
    Photorealistic three‑dimensional visualization of fusion datasets: cinematic rendering of PET/CT
    Steven P. Rowe · Martin G. Pomper · Jeffrey P. Leal · Robert Schneider · Sebastian Krüger · Linda C. Chu ·Elliot K. Fishman
    Abdominal Radiology (2022) 47:3916–3920 
  • “There are potential limitations of the described technique. The creation of PET/CT CR images may add significant time to the interpretation of cases until the reader develops the necessary experience to quickly utilize presets and adjust those presets as needed. Although there is no specific expertise required for the successful deployment of PET/CT CR images, there is a learning curve and readers may need to make the time to familiarize themselves with the software and develop a facility with the presets and their manual manipulation. Further, key pathology can be obscured by overlapping structures in the CR images, necessitating diligent correlation to the 2D reconstructions and the use of cut planes and multiple presets to ensure important findings are well displayed. Of course, potential applications will need to be studied. Nonetheless, the presented technology is promising. The ultimate utility of this technology will depend upon its widespread availability and acceptance by imaging specialists.”
    Photorealistic three‑dimensional visualization of fusion datasets: cinematic rendering of PET/CT
    Steven P. Rowe · Martin G. Pomper · Jeffrey P. Leal · Robert Schneider · Sebastian Krüger · Linda C. Chu ·Elliot K. Fishman
    Abdominal Radiology (2022) 47:3916–3920 
  • “Augmented and virtual reality devices are being actively investigated and implemented for a wide range of medical uses. However, significant gaps in the evaluation of these medical devices and applications hinder their regulatory evaluation. Addressing these gaps is critical to demonstrating the devices’ safety and effectiveness. We outline the key technical and clinical evaluation challenges discussed during the US Food and Drug Administration’s public workshop, “Medical Extended Reality: Toward Best Evaluation Practices for Virtual and Augmented Reality in Medicine” and future directions for evaluation method development. Evaluation challenges were categorized into several key technical and clinical areas. Finally, we highlight current efforts in the standards communities and illustrate connections between the evaluation challenges and the intended uses of the medical extended reality (MXR) devices. Participants concluded that additional research is needed to assess the safety and effectiveness of MXR devices across the use cases.”
    Evaluation Challenges for the Application of Extended Reality Devices in Medicine
    Ryan Beams et al.  
    Journal of Digital Imaging (2022) 35:1409–1418
  • “In addition to image quality considerations from the hardware components, the software and rendering pipeline also introduce unique challenges for MXR devices. MXR devices often utilize commercial game engines for visualization and rendering. The formatting, bit-depth, voxelization, grayscale, and color properties of the input medical images can be impacted by the rendering process due to the use of shaders, material properties, and graphical performance optimization. This is particularly true for diagnostics and surgery planning using radiographic images that generally utilize the Digital Imaging and Communications in Medicine (DICOM) Grayscale Standard Display Function. The impact of these rendering engines on medical image quality is largely unexplored lacking both standards and evaluation methods. Besides the rendering pipeline, formatting of the saved data including biometrics also presents a challenge from both a data standardization perspective and a data security perspective.”
    Evaluation Challenges for the Application of Extended Reality Devices in Medicine
    Ryan Beams et al.  
    Journal of Digital Imaging (2022) 35:1409–1418
  • “The task and physical environments also impact the usability of MXR devices by adding additional evaluation considerations. For example, a VR device for immersive therapeutics raises different evaluation considerations for usability. Similarly, surgical tasks in interventional suites and operating rooms with bright ambient illumination present unique challenges for the visibility and spatial mapping of AR images, including the visibility of the patient’s anatomy and the virtual medical image overlaid on the patient. In addition to visibility, the perceived accuracy of an image overlaid on a patient also raises usability questions. Different surgical tasks have varying requirements for AR image accuracy, which can influence device design.”
    Evaluation Challenges for the Application of Extended Reality Devices in Medicine
    Ryan Beams et al.  
    Journal of Digital Imaging (2022) 35:1409–1418
  • “The consensus from the public workshop is that significant evaluation challenges for MXR devices persist across use cases. These can be categorized into a variety of technical and clinical challenges, which were summarized in this consensus article. To address these evaluation gaps, additional research is needed to characterize the performance of these devices from technical and medical performance perspectives. The relevant evaluation challenges and the specific assessment gaps primarily are determined by the intended use of a device. Therefore, development of suitable evaluation methods necessitates expertise across the MXR landscape in a precompetitive space to address the needs of the larger community. A number of potential avenues currently being explored would create the needed platforms for collaboration, including proposals to further the research establishing partnerships among industry, academia, and regulators.”
    Evaluation Challenges for the Application of Extended Reality Devices in Medicine
    Ryan Beams et al.
     Journal of Digital Imaging (2022) 35:1409–1418
  • “Recent advances in 3-dimensional visualization of volumetric computed tomography data have led to the novel technique of cinematic rendering (CR), which provides photorealistic images with enhanced surface detail and realistic shadowing effects that are generally not possible with older methods such as volume rendering. The emergence of CR coincides with the increasingly widespread availability of virtual reality (VR)/ augmented reality (AR) interfaces including wearable headsets. The intersection of these technologies suggests many potential advances, including the ability of interpreting radiologists to look at photorealistic images of patient pathology in real time with surgeons and other referring providers, so long as VR/AR headsets are deployed and readily available. In this article, we will present our initial experience with viewing and manipulating CR images in the context of a VR/AR headset. We include a description of key aspects of the software and user interface, and provide relevant pictorial examples that may help potential adopters understand the initial steps of using this exciting convergence of technologies. Ultimately, trials evaluating the added value of the combination of CR with VR/AR will be necessary to understand the potential impact of these methods on medical practice.”
    Augmented Reality With Cinematic Rendered 3-Dimensional Images From Volumetric Computed Tomography Data
    Steven P. Rowe, MD, PhD,* Robert Schneider, PhD,† Sebastian Krueger, PhD,† Valerie Pryde, RT, CIIP,* Linda C. Chu, MD,* and Elliot K. Fishman, MD*
    J Comput Assist Tomogr • (in press) 2022
  • “In parallel to the development of CR, virtual reality (VR)/ augmented reality (AR) has also been increasingly incorporated intomedical imaging The combination of photorealistic CR images with a VR/AR interface can facilitate real-time discussions between imaging specialists and clinicians and allow multiple individuals from an interdisciplinary team to see and manipulate the CR images. Photorealistic images are necessary to create the proper depth and immersion to best leverage VR/AR emerging technology. In this article, we will describe our initial experience with the HoloLens headset as a display for CR images and offer observations on the interface and its potential future applications.”
    Augmented Reality With Cinematic Rendered 3-Dimensional Images From Volumetric Computed Tomography Data
    Steven P. Rowe, MD, PhD,* Robert Schneider, PhD,† Sebastian Krueger, PhD,† Valerie Pryde, RT, CIIP,* Linda C. Chu, MD,* and Elliot K. Fishman, MD*
    J Comput Assist Tomogr • (in press) 2022I
  • “With the CR image projected into AR, the user can make a brief squeezing motion with his/her hand and outline the image. A white cube surrounds the CR image, and the user can either manipulate the image from the corners of the cube (pinching a corner and moving in or out will zoom the image) or, with another hand motion, covert the cube to have linear projections from the middle of the sides, which permit the user to spin the image or apply cut-planes. Please note that in capturing images for the figures in this article, it was difficult to film the cube, hence this feature of the software is not shown. The user can also walk around the CR hologram to see obscured anatomy or pathology, although this should be done with caution in an area cleared of trip hazards, because the user's vision is restricted by the headset and the projected CR hologram.”
    Augmented Reality With Cinematic Rendered 3-Dimensional Images From Volumetric Computed Tomography Data
    Steven P. Rowe, MD, PhD,* Robert Schneider, PhD,† Sebastian Krueger, PhD,† Valerie Pryde, RT, CIIP,* Linda C. Chu, MD,* and Elliot K. Fishman, MD*
    J Comput Assist Tomogr • (in press) 2022I
  • “There are other potential advantages of the combination of CR and AR/VR. The rise of artificial intelligence (AI) as a driving force in the future of radiology suggests that new visualization methods for volumetric data may be important as data inputs for graphical processing unit–driven AI workstations. Adding AR/ VR to CR visualizations may allow nonradiologists to have input into the images that are sent to the picture archiving and communication system and facilitate the incorporation of clinical data into ensemble AI algorithms.”
    Augmented Reality With Cinematic Rendered 3-Dimensional Images From Volumetric Computed Tomography Data
    Steven P. Rowe, MD, PhD,* Robert Schneider, PhD,† Sebastian Krueger, PhD,† Valerie Pryde, RT, CIIP,* Linda C. Chu, MD,* and Elliot K. Fishman, MD*
    J Comput Assist Tomogr • (in press) 2022I
  • “Augmented and virtual reality devices are being actively investigated and implemented for a wide range of medical uses. However, significant gaps in the evaluation of these medical devices and applications hinder their regulatory evaluation. Addressing these gaps is critical to demonstrating the devices’ safety and effectiveness. We outline the key technical and clinical evaluation challenges discussed during the US Food and Drug Administration’s public workshop, “Medical Extended Reality: Toward Best Evaluation Practices for Virtual and Augmented Reality in Medicine” and future directions for evaluation method development. Evaluation challenges were categorized into several key technical and clinical areas. Finally, we highlight current efforts in the standards communities and illustrate connections between the evaluation challenges and the intended uses of the medical extended reality (MXR) devices. Participants concluded that additional research is needed to assess the safety and effectiveness of MXR devices across the use cases.”
    Evaluation Challenges for the Application of Extended Reality Devices in Medicine
    Ryan Beams et al.  
    Journal of Digital Imaging (2022) 35:1409–1418
  • “In addition to image quality considerations from the hardware components, the software and rendering pipeline also introduce unique challenges for MXR devices. MXR devices often utilize commercial game engines for visualization and rendering. The formatting, bit-depth, voxelization, grayscale, and color properties of the input medical images can be impacted by the rendering process due to the use of shaders, material properties, and graphical performance optimization. This is particularly true for diagnostics and surgery planning using radiographic images that generally utilize the Digital Imaging and Communications in Medicine (DICOM) Grayscale Standard Display Function. The impact of these rendering engines on medical image quality is largely unexplored lacking both standards and evaluation methods. Besides the rendering pipeline, formatting of the saved data including biometrics also presents a challenge from both a data standardization perspective and a data security perspective.”
    Evaluation Challenges for the Application of Extended Reality Devices in Medicine
    Ryan Beams et al.  
    Journal of Digital Imaging (2022) 35:1409–1418
  • “The task and physical environments also impact the usability of MXR devices by adding additional evaluation considerations. For example, a VR device for immersive therapeutics raises different evaluation considerations for usability. Similarly, surgical tasks in interventional suites and operating rooms with bright ambient illumination present unique challenges for the visibility and spatial mapping of AR images, including the visibility of the patient’s anatomy and the virtual medical image overlaid on the patient. In addition to visibility, the perceived accuracy of an image overlaid on a patient also raises usability questions. Different surgical tasks have varying requirements for AR image accuracy, which can influence device design.”
    Evaluation Challenges for the Application of Extended Reality Devices in Medicine
    Ryan Beams et al.  
    Journal of Digital Imaging (2022) 35:1409–1418
  • “The consensus from the public workshop is that significant evaluation challenges for MXR devices persist across use cases. These can be categorized into a variety of technical and clinical challenges, which were summarized in this consensus article. To address these evaluation gaps, additional research is needed to characterize the performance of these devices from technical and medical performance perspectives. The relevant evaluation challenges and the specific assessment gaps primarily are determined by the intended use of a device. Therefore, development of suitable evaluation methods necessitates expertise across the MXR landscape in a precompetitive space to address the needs of the larger community. A number of potential avenues currently being explored would create the needed platforms for collaboration, including proposals to further the research establishing partnerships among industry, academia, and regulators.”
    Evaluation Challenges for the Application of Extended Reality Devices in Medicine
    Ryan Beams et al.  
    Journal of Digital Imaging (2022) 35:1409–1418
  • Through the haze of uncertainty in the interplay of these forces, 5 trends that may shape the future of diagnosis can be discerned:
    • Movement from symptom-prompted testing to continuous monitoring and assessment, and from within health settings to everyday living.
    • Shift in reliance on individual test results to interpretation of data streams and data patterns.
    • Change in the meaning of an “abnormal” test result from a deviation against a population norm to an aberrancy in an individual’s pattern of results over time.
    • Increasingly refined and specific diagnostic categories in step with the advent of increasingly differentiated treatment.
    • Augmentation of the goals of diagnostic excellence from the detection of disease to the preservation of wellness, and from indicative of the present disease to predictive of future state of health.
    The Future of Diagnostic Excellence
    Fineberg HV, Song S, Wang T
    JAMA September 20, 2022 Volume 328, Number 11 
  • Key Points for Diagnostic Excellence
    1. Many technologic initiatives to improve future diagnostic capabilities are already underway.
    2. The future of diagnosis will be marked by massive, continuously acquired data, automated interpretation of data streams and data patterns, and personal reference over time of what constitutes a normal result.
    3. Increasingly precise diagnoses will allow clinical comparisons across more nearly alike patients and ultimately provide a unique health profile for each individual.
    4. The future of diagnosis will emphasize prediction of future health state rather than identification of current disease.
    5. Diagnostic excellence begins and ends with the patient.
  • “Machine learning techniques to analyze large amounts of data in real time are becoming more sophisticated as guides both to an optimal diagnostic process and to more accurate, specific, and complete diagnostic assessments. For the foreseeable future, a combination of machine learning and human judgment may be optimal in reaching accurate, timely diagnoses. Over time, machine learning algorithms are more likely to improve in diagnostic acumen than are unaided human diagnosticians.”
    The Future of Diagnostic Excellence
    Fineberg HV, Song S, Wang T
    JAMA September 20, 2022 Volume 328, Number 11
  • “As more health-related data are collected in a more continuous manner, individual results at a moment in time will have a comparison baseline of that individual’s previous results. A more individualized definition of abnormal—that is, a pattern of results that warrants investigation—may follow a small deviation from an individual’s own previous levels, even if still “within normal limits” of a population comparison. Self-referenced norms may prove to be both more sensitive (eg, when a small increase should trigger investigation, even if the higher result is within the population norm) and more specific (when a consistent result over time just outside the population norm is not a cause for concern).”
    The Future of Diagnostic Excellence
    Fineberg HV, Song S, Wang T
    JAMA September 20, 2022 Volume 328, Number 11
  • “Today, clinicians think of diagnosis mainly in terms of the detection and classification of disease. Over time, increased understanding of the genomic, proteomic, metabolomic, and microbiomic underpinnings of human biology will produce greater understanding of the etiology and progression of biologic function from the state of health to the state of disease. As understanding of the precursors of disease grow more detailed and revealing, the art and science of diagnosis enlarge from the detection of present disease to the prediction of future disease. Put in equivalent, positive terms, medical diagnosis moves from characterizing the current state of health to predicting the future state of health. Then interventions may be designed to enhance, maintain, and as needed, restore health.”
    The Future of Diagnostic Excellence
    Fineberg HV, Song S, Wang T
    JAMA September 20, 2022 Volume 328, Number 11
  • “Whether diagnostic excellence comes to depict a state and future course of health or to describe a current category of disease, physicians and other clinicians will always do well to focus on the lived experience. The aims of diagnostic excellence begin and end with the patient.”
    The Future of Diagnostic Excellence
    Fineberg HV, Song S, Wang T
    JAMA September 20, 2022 Volume 328, Number 11
Adrenal

  • “Pheochromocytomas and Paragangliomas (PCC/PGL) are rare endocrine tumors that are mostly benign, but often hormone producing, causing significant morbidity and mortality due to excess catecholamine secretion and cardiovascular crises. It is estimated that 30% of PCC/PGL are due to germline mutations, including Neurofibromatosis type 1 (NF1).”  
    Pheochromocytoma and Paraganglioma in Neurofibromatosis type 1: frequent surgeries and cardiovascular crises indicate the need for screening.  
    Petr, E.J., Else, T.  
    Clin Diabetes Endocrinol 4, 15 (2018). 
  • "Catecholamine excess and resultant cardiovascular crises. A significant percentage (~ 30%) of those affected with PCC/PGL tumors harbor a germline mutation that predisposes them both to the development of PCC/PGL and also to other tumors unique to each particular inherited syndrome [1–5]. The most common known hereditary tumor syndromes that increase risk for PCC/PGL are Hereditary Paraganglioma Syndrome (SDHx), Neurofibromatosis Type 1 (NF1), von Hippel Lindau disease (VHL), Multiple Endocrine Neoplasia type 2 (MEN2, RET), TMEM127- and MAX-related hereditary pheochromocytoma, and Hereditary Leiomyomatosis and Renal Cell Cancer (HLRCC, FH) [6–8]. For MEN2 and VHL, there are recommendations to screen for PCC/PGL in mutation carriers (ie. annual metanephrine levels in MEN2 and annual metanephrine levels and review of adrenal glands on abdominal imaging in VHL)
    Pheochromocytoma and Paraganglioma in Neurofibromatosis type 1: frequent surgeries and cardiovascular crises indicate the need for screening.  
    Petr, E.J., Else, T.  
    Clin Diabetes Endocrinol 4, 15 (2018). 
  • “The most common known hereditary tumor syndromes that increase risk for PCC/PGL are Hereditary Paraganglioma Syndrome (SDHx), Neurofibromatosis Type 1 (NF1), von Hippel Lindau disease (VHL), Multiple Endocrine Neoplasia type 2 (MEN2, RET), TMEM127- and MAX-related hereditary pheochromocytoma, and Hereditary Leiomyomatosis and Renal Cell Cancer (HLRCC, FH) [6–8]. For MEN2 and VHL, there are recommendations to screen for PCC/PGL in mutation carriers (ie. annual metanephrine levels in MEN2 and annual metanephrine levels and review of adrenal glands on abdominal imaging in VHL.”  
    Pheochromocytoma and Paraganglioma in Neurofibromatosis type 1: frequent surgeries and cardiovascular crises indicate the need for screening.  
    Petr, E.J., Else, T.  
    Clin Diabetes Endocrinol 4, 15 (2018). 
  • “Since almost all NF1-associated PCC/PGL appear to be biochemically active, screening with plasma or urine free fractionated metanephrine levels in the setting of a high pre-test probability should capture most cases. Most PCC/PGL were located in the adrenal gland, were amenable to complete surgical resection, and did not recur or progress to metastatic disease.”
    Pheochromocytoma and Paraganglioma in Neurofibromatosis type 1: frequent surgeries and cardiovascular crises indicate the need for screening.  
    Petr, E.J., Else, T.  
    Clin Diabetes Endocrinol 4, 15 (2018). 
  • “In the elective field of adrenal imaging, artificial intelligence (AI) can be used for adrenal lesion detection, characterization, hypersecreting syndrome management and patient follow-up. Although a perfect AI tool that includes all required steps from detection to analysis does not exist yet, multiple AI algorithms have been developed and tested with encouraging results. However, AI in this setting is still at an early stage. In this regard, most published studies about AI in adrenal gland imaging report preliminary results that do not have yet daily applications in clinical practice. In this review, recent developments and current results of AI in the field of adrenal imaging are presented. Limitations and future perspectives of AI are discussed.”
    Artificial intelligence in adrenal imaging: A critical review of current applications
    Maxime Baratab, Martin Gaillardb, Anne-Segolene Cottereaub, Elliot K. Fishman, Guillaume Assieb, Anne Jouinotb, Christine Hoeffel, Philippe Soyer, Anthony Dohana
    Diagnostic and Interventional Imaging 000 (2022) 1−6  
  • "Recently, deep neuronal networks (DNN) were developed to improve accuracy of adrenal gland segmentation. Luo et al. used a two-step method with a preprocessing step to reduce variabilities between examinations and the computational burden followed by a second step of small organs segmentation network using annotated input . The CT dataset was obtained from 348 patients, 60% for the training, 20% for the validation and 20% for the testing cohort . With this model, the authors obtained a DSC of 87.2%, which is the best reported one to date for adrenal gland segmentation Despite a better DSC than those obtained with previous segmentation algorithms, DNNs also require further external validation to demonstrate their robustness.”
    Artificial intelligence in adrenal imaging: A critical review of current applications
    Maxime Baratab, Martin Gaillardb, Anne-Segolene Cottereaub, Elliot K. Fishman, Guillaume Assieb, Anne Jouinotb, Christine Hoeffel, Philippe Soyer, Anthony Dohana
    Diagnostic and Interventional Imaging 000 (2022) 1−6  
  • "Radiomics is regarded as a promising research field for the characterization and follow-up of non-typical AL. Using first order texture analysis features, Jhaveri et al. found that a 5% cut-off of negative voxels on histogram derived from unenhanced CT data had 92.3% sensitivity and 100% specificity for the characterization of lipid-poor AA . Another found that entropy (i.e., a first order texture analysis feature) yielded an AUC of 0.65 (95% CI: 0.52−0.77) to differentiate between adrenal metastasis from lung cancer (showing greater entropy) and AA Ho et al. developed a model using 21 second order features extracted from contrast-enhanced CT data that allowed differentiating lipid-poor AA from malignant AL better than standard morphological features (AUC of 0.8 vs. 0.6, respectively). Similarly, a model using four second-order features extracted from unenhanced CT data yielded 96.6% sensitivity, 81% specificity and 85.2% accuracy for the diagnosis of pheochromocytoma vs. lipid poor AA.”
    Artificial intelligence in adrenal imaging: A critical review of current applications
    Maxime Baratab, Martin Gaillardb, Anne-Segolene Cottereaub, Elliot K. Fishman, Guillaume Assieb, Anne Jouinotb, Christine Hoeffel, Philippe Soyer, Anthony Dohana
    Diagnostic and Interventional Imaging 000 (2022) 1−6 
  • “AI has currently applications in almost all fields of adrenal diseases. Although most studies are preliminary studies, they suggestthat AI may improve AL classification, prognosis, and possibly management of patients affected with AL. However, there is a long way to go before AI is implemented into daily practice of radiologist, endocrinologist, and surgeons. In this regard, one current limitation for immediate applicability is the observed difference in recommended management among societies. Some studies suggest that AI algorithms should not be built using imaging data alone but should integrate biological data for better efficacy. Finally, large, prospective studies with external validations are needed to buildeffective, predictive models that will help improve patients’ care by selecting the most appropriate option among surveillance, open vs. laparoscopic surgery or “leave it alone” option.”
    Artificial intelligence in adrenal imaging: A critical review of current applications
    Maxime Baratab, Martin Gaillardb, Anne-Segolene Cottereaub, Elliot K. Fishman, Guillaume Assieb, Anne Jouinotb, Christine Hoeffel, Philippe Soyer, Anthony Dohana
    Diagnostic and Interventional Imaging 000 (2022) 1−6 
  • “A machine learning algorithm was developed that can accurately segment and classify adrenal glands as normal or mass-containing on contrastvenhanced CT images, with performance similar to that of radiologists.”
    Machine Learning for Adrenal Gland Segmentation and Classification of Normal and Adrenal Masses at CT
    Cory Robinson-Weiss et al.
    Radiology 2022; 000:1–8
  • • In this retrospective study using CT images from 251 (development data set) and 991 patients (secondary test set), a machine learning algorithm segmented adrenal glands, with a performance similar to that of radiologists; the median model Dice score 0.87 versus 0.89 for normal adrenal glands and 0.85 versus 0.89 for adrenal masses.
    • The algorithm differentiated adrenal masses from normal adrenal glands, with 83% sensitivity and 89% specificity for the development data set and 69% sensitivity and 91% specificity for the secondary test set.
    Machine Learning for Adrenal Gland Segmentation and Classification of Normal and Adrenal Masses at CT
    Cory Robinson-Weiss et al.
    Radiology 2022; 000:1–8
  • “ Our results are promising given that the adrenal gland is an inherently challenging organ to segment compared with larger organs (such as the liver and kidneys), as these glands are small and change in position due to respiration, and their shape, size, and location can vary by laterality and patient. In addition, adrenal glands have soft-tissue attenuation at CT that is similar to that of adjacent structures, including the liver, pancreas, kidneys, and vasculature. In patients with a paucity of intra-abdominal fat, the adrenal glands may be even more challenging to delineate from adjacent structures without the contrasting fat around the glands to separate them from other structures. Finally, there may be external mass effect on the glands, for example from an adjacent liver cyst or mass.”
    Machine Learning for Adrenal Gland Segmentation and Classification of Normal and Adrenal Masses at CT
    Cory Robinson-Weiss et al.
    Radiology 2022; 000:1–8
  • “In conclusion, we propose a two-stage machine learning pipeline to automatically segment the adrenal glands at contrast enhanced CT and then classify the glands as normal or mass containing. This tool may be used to assist radiologists in accurate and expedient image interpretation and potentially decrease interreader variability. Future work is needed to improve the classification stage of our model, as well as expand on the scope of the classification task by reviewing prior imaging and assessing for mass stability or growth.”
    Machine Learning for Adrenal Gland Segmentation and Classification of Normal and Adrenal Masses at CT
    Cory Robinson-Weiss et al.
    Radiology 2022; 000:1–8
  • “In conclusion, only one-fourth of patients received appropriate biochemical testing after incidental diagnosis of an adrenal nodule, and most nodules with indeterminate imaging characteristics did not have follow-up imaging. Advanced data analytic techniques on electronic imaging reports may aid in the clinical identification andimproved management of patients with adrenal incidentalomas.”
    Automated extraction of incidental adrenal nodules from electronic health records
    Max Schumm et al.
    Surgery xxx (2022) 1e7 (in press)
  • Background: Many adrenal incidentalomas do not undergo appropriate biochemical testing and complete imaging characterization to assess for hormone hypersecretion and malignancy. With the growing availability of clinical narratives in the electronic medical record, automated surveillance using advanced data analytic techniques may represent a promising method to improve management.
    Conclusion: Only one-fourth of patients received appropriate biochemical testing after incidental diagnosis of an adrenal nodule, and most nodules with indeterminate imaging characteristics did notundergo follow-up imaging. Advanced data analytic techniques on electronic imaging reports may aid in the clinical identification and improved management of patients with adrenal incidentalomas.
    Automated extraction of incidental adrenal nodules from electronic health records
    Max Schumm et al.
    Surgery xxx (2022) 1e7 (in press)
Cardiac

  • “CT is a useful technique as part of a multi-modality approach in the evaluation of LVADs and associated complications. Recent studies continue to build on the prognostic role of measuring skeletal muscle CT attenuation in predicting adverse LVAD outcomes, and on the value of 18F-fluorodeoxyglucose positron emission tomography-computed tomography (FDG PET-CT) in the evaluation of suspected LVAD infection. Though CT is very useful for the diagnosis of outflow graft obstruction, it often lacks the diagnostic capability to differentiate between intraluminal thrombus and extrinsic compression from biodebris accumulation. Newer CT techniques such as dual-energy CT and metal artifact reduction algorithms, though promising, lack high-quality published literature on their use in LVAD imaging.”
    Update on CT Imaging of Left Ventricular Assist Devices and Associated Complications
    Pratik S. Velangi et al.
    Current Cardiovascular Imaging Reports  2022 (in press) https://doi.org/10.1007/s12410-022-09570-0
  • “LVAD infections can occur on body surfaces in proximity to the device or on device hardware itself. Driveline infections can extend deeper to involve the pump or other components. They are often seen as rim-enhancing fluid collections, soft tissue stranding, or gas pockets adjacent to device components. Though the incremental value of cardiac CT in addition to echocardiography is being recognized for the diagnosis of prosthetic heart valve endocarditis in non-LVAD patients its diagnostic accuracy for infection in LVAD patients is limited due to device-related artifacts.”
    Update on CT Imaging of Left Ventricular Assist Devices and Associated Complications
    Pratik S. Velangi et al.
    Current Cardiovascular Imaging Reports  2022 (in press) https://doi.org/10.1007/s12410-022-09570-0
  • “Recent studies continue to build on the prognostic role of measuring skeletal muscle CT attenuation in predicting adverse LVAD outcomes, and on the value of 18F-fluorodeoxyglucose positron emission tomographycomputed tomography (FDG PET-CT) in the evaluation of suspected LVAD infection. Though CT is very useful for the diagnosis of outflow graft obstruction, it often lacks the diagnostic capability to differentiate between intraluminal thrombus and extrinsic compression from biodebris accumulation. Newer CT techniques such as dual-energy CT and metal artifact reduction algorithms, though promising, lack high-quality published literature on their use in LVAD imaging.”
    Update on CT Imaging of Left Ventricular Assist Devices and Associated Complications
    Pratik S. Velangi et al.
    Current Cardiovascular Imaging Reports  2022 (in press) https://doi.org/10.1007/s12410-022-09570-0 
Chest

  • Ectopic Cushings Syndrome
    - Ectopic Cushing syndrome is a form of Cushing syndrome in which a tumor outside the pituitary gland produces a hormone called adrenocorticotropic hormone (ACTH).
    - ACTH is usually made by the pituitary in small amounts and then signals the adrenal glands to produce cortisol. Sometimes other cells outside the pituitary can make large amounts of ACTH. This is called ectopic Cushing syndrome.
  • Ectopic Cushing syndrome: Causes
    - Benign carcinoid tumors of the lung
    - Islet cell tumors of the pancreas
    - Medullary carcinoma of the thyroid
    - Small cell tumors of the lung
    - Tumors of the thymus gland
  • “CT is a useful technique as part of a multi-modality approach in the evaluation of LVADs and associated complications. Recent studies continue to build on the prognostic role of measuring skeletal muscle CT attenuation in predicting adverse LVAD outcomes, and on the value of 18F-fluorodeoxyglucose positron emission tomography-computed tomography (FDG PET-CT) in the evaluation of suspected LVAD infection. Though CT is very useful for the diagnosis of outflow graft obstruction, it often lacks the diagnostic capability to differentiate between intraluminal thrombus and extrinsic compression from biodebris accumulation. Newer CT techniques such as dual-energy CT and metal artifact reduction algorithms, though promising, lack high-quality published literature on their use in LVAD imaging.”
    Update on CT Imaging of Left Ventricular Assist Devices and Associated Complications
    Pratik S. Velangi et al.
    Current Cardiovascular Imaging Reports  2022 (in press) https://doi.org/10.1007/s12410-022-09570-0
  • “LVAD infections can occur on body surfaces in proximity to the device or on device hardware itself. Driveline infections can extend deeper to involve the pump or other components. They are often seen as rim-enhancing fluid collections, soft tissue stranding, or gas pockets adjacent to device components. Though the incremental value of cardiac CT in addition to echocardiography is being recognized for the diagnosis of prosthetic heart valve endocarditis in non-LVAD patients its diagnostic accuracy for infection in LVAD patients is limited due to device-related artifacts.”
    Update on CT Imaging of Left Ventricular Assist Devices and Associated Complications
    Pratik S. Velangi et al.
    Current Cardiovascular Imaging Reports  2022 (in press) https://doi.org/10.1007/s12410-022-09570-0
  • “Recent studies continue to build on the prognostic role of measuring skeletal muscle CT attenuation in predicting adverse LVAD outcomes, and on the value of 18F-fluorodeoxyglucose positron emission tomographycomputed tomography (FDG PET-CT) in the evaluation of suspected LVAD infection. Though CT is very useful for the diagnosis of outflow graft obstruction, it often lacks the diagnostic capability to differentiate between intraluminal thrombus and extrinsic compression from biodebris accumulation. Newer CT techniques such as dual-energy CT and metal artifact reduction algorithms, though promising, lack high-quality published literature on their use in LVAD imaging.”
    Update on CT Imaging of Left Ventricular Assist Devices and Associated Complications
    Pratik S. Velangi et al.
    Current Cardiovascular Imaging Reports  2022 (in press) https://doi.org/10.1007/s12410-022-09570-0 
Colon

  • CT Evaluation of the Colon: Pearls and Pitfalls
    - Bowel wall thickening
    - Increased submucosal fat
    - Pneumatosis coli
    - Bowel obstruction (i.e. tumor, volvulus)
    - Hernia (external)
    - Pericolonic inflammation (i.e. diverticulitis, perforation, appendix epipolicae)
  • CT of the Colon: Colonic Distension
    - Rectal contrast
    - Oral contrast (delayed scans at 3-4 hours)
    - Virtual colonoscopy
Deep Learning

  • “The current results found in the literature support the concept of “AI-augmented” radiologists instead of supporting the theory of the replacement of radiologists by AI in many indications. Current evidence bolsters the assumption that AI-assisted radiologists work better and faster. AI is a great aid to radiologists in the emergency setting, and improves their workflow by decreasing reading time in some areas. As the applications of AI increase, it becomes clear that the role of the radiologist may change dramatically in coming years, raising additional issues in terms of responsibility and liability.”
    Does artificial intelligence surpass the radiologist?
    Soyer P, Fishman EK, Rowe SP, Patlas MN, Chassagnon G.
    Diagn Interv Imaging. 2022 Oct;103(10):445-447. 
  • “However, all these advances must be interpreted with caution. Virtually all studies about AI were made retrospectively and more research is needed to make sure than the use of AI provides equivalent results in real word prospective studies. Moreover, the added value of AI in radiology should be evaluated using other metrics than sensitivity only, but also in terms of level of confidence of a given diagnosis, faster workflow, improved patient management, and better work life balance for the radiologists. Weak AI will continue to dominate the current landscape until strong AI becomes a more relevant reality − at which point, it will be impossible to predict the implications for radiology and society at large. To date, we can say that the final diagnosis is still the specific task and the responsibility of the radiologist.”
    Does artificial intelligence surpass the radiologist?
    Soyer P, Fishman EK, Rowe SP, Patlas MN, Chassagnon G.
    Diagn Interv Imaging. 2022 Oct;103(10):445-447. 
  • “There are other fields in which AI seriously challenges the radiologist. In this regard, Romero-Martin et al. evaluated the standalone performance of an AI system (Transpara, version 1.7.0; ScreenPoint Medical) as an independent reader of digital mammography or digital breast tomosynthesis screening examinations. These researchers found that AI could replace radiologists' readings in breast screening, achieving a noninferior sensitivity compared to single or double human reading for digital mammography (62.8% vs. 58.4% and 67.3%, respectively; P = 0.458 and 0.523), with a lower recall rate. For digital breast tomosynthesis, AI yielded noninferior sensitivity compared to single or double human reading (80.5% vs. 77.0% and 81.4%, respectively; P = 0.648) but with a greater recall rate .Although this study performed in a real word scenario has limitations, it raises some serious questions about the systematic implementation of AI in the field of breast screening in the near future.”
    Does artificial intelligence surpass the radiologist?
    Soyer P, Fishman EK, Rowe SP, Patlas MN, Chassagnon G.
    Diagn Interv Imaging. 2022 Oct;103(10):445-447. 
  • Through the haze of uncertainty in the interplay of these forces, 5 trends that may shape the future of diagnosis can be discerned:
    • Movement from symptom-prompted testing to continuous monitoring and assessment, and from within health settings to everyday living.
    • Shift in reliance on individual test results to interpretation of data streams and data patterns.
    • Change in the meaning of an “abnormal” test result from a deviation against a population norm to an aberrancy in an individual’s pattern of results over time.
    • Increasingly refined and specific diagnostic categories in step with the advent of increasingly differentiated treatment.
    • Augmentation of the goals of diagnostic excellence from the detection of disease to the preservation of wellness, and from indicative of the present disease to predictive of future state of health.
    The Future of Diagnostic Excellence
    Fineberg HV, Song S, Wang T
    JAMA September 20, 2022 Volume 328, Number 11 
  • Key Points for Diagnostic Excellence
    1. Many technologic initiatives to improve future diagnostic capabilities are already underway.
    2. The future of diagnosis will be marked by massive, continuously acquired data, automated interpretation of data streams and data patterns, and personal reference over time of what constitutes a normal result.
    3. Increasingly precise diagnoses will allow clinical comparisons across more nearly alike patients and ultimately provide a unique health profile for each individual.
    4. The future of diagnosis will emphasize prediction of future health state rather than identification of current disease.
    5. Diagnostic excellence begins and ends with the patient.
    The Future of Diagnostic Excellence
    Fineberg HV, Song S, Wang T
    JAMA September 20, 2022 Volume 328, Number 11
  • “Machine learning techniques to analyze large amounts of data in real time are becoming more sophisticated as guides both to an optimal diagnostic process and to more accurate, specific, and complete diagnostic assessments. For the foreseeable future, a combination of machine learning and human judgment may be optimal in reaching accurate, timely diagnoses. Over time, machine learning algorithms are more likely to improve in diagnostic acumen than are unaided human diagnosticians.”
    The Future of Diagnostic Excellence
    Fineberg HV, Song S, Wang T
    JAMA September 20, 2022 Volume 328, Number 11
  • “As more health-related data are collected in a more continuous manner, individual results at a moment in time will have a comparison baseline of that individual’s previous results. A more individualized definition of abnormal—that is, a pattern of results that warrants investigation—may follow a small deviation from an individual’s own previous levels, even if still “within normal limits” of a population comparison. Self-referenced norms may prove to be both more sensitive (eg, when a small increase should trigger investigation, even if the higher result is within the population norm) and more specific (when a consistent result over time just outside the population norm is not a cause for concern).”
    The Future of Diagnostic Excellence
    Fineberg HV, Song S, Wang T
    JAMA September 20, 2022 Volume 328, Number 11
  • “Today, clinicians think of diagnosis mainly in terms of the detection and classification of disease. Over time, increased understanding of the genomic, proteomic, metabolomic, and microbiomic underpinnings of human biology will produce greater understanding of the etiology and progression of biologic function from the state of health to the state of disease. As understanding of the precursors of disease grow more detailed and revealing, the art and science of diagnosis enlarge from the detection of present disease to the prediction of future disease. Put in equivalent, positive terms, medical diagnosis moves from characterizing the current state of health to predicting the future state of health. Then interventions may be designed to enhance, maintain, and as needed, restore health.”
    The Future of Diagnostic Excellence
    Fineberg HV, Song S, Wang T
    JAMA September 20, 2022 Volume 328, Number 11
  • “Whether diagnostic excellence comes to depict a state and future course of health or to describe a current category of disease, physicians and other clinicians will always do well to focus on the lived experience. The aims of diagnostic excellence begin and end with the patient.”
    The Future of Diagnostic Excellence
    Fineberg HV, Song S, Wang T
    JAMA September 20, 2022 Volume 328, Number 11
  • Background: As the number of conventional radiographic examinations in pediatric emergency departments increases, so, too, does the number of reading errors by radiologists.
    Objective: The aim of this study is to investigate the ability of artificial intelligence (AI) to improve the detection of fractures by radiologists in children and young adults.
    Materials and methods: A cohort of 300 anonymized radiographs performed for the detection of appendicular fractures in patients ages 2 to 21 years was collected retrospectively. The ground truth for each examination was established after an independent review by two radiologists with expertise in musculoskeletal imaging. Discrepancies were resolved by consensus with a third radiologist. Half of the 300 examinations showed at least 1 fracture. Radiographs were read by three senior pediatric radiologists and five radiology residents in the usual manner and then read again immediately after with the help of AI.
    Assessment of an artificial intelligence aid for the detection of appendicular skeletal fractures in children and young adults by senior and junior radiologists
    Toan Nguyen et al.
    Pediatric Radiology (2022) 52:2215–2226
  • Results: The mean sensitivity for all groups was 73.3% (110/150) without AI; it increased significantly by almost 10% (P<0.001) to 82.8% (125/150) with AI. For junior radiologists, it increased by 10.3% (P<0.001) and for senior radiologists by 8.2% (P=0.08). On average, there was no significant change in specificity (from 89.6% to 90.3% [+0.7%, P=0.28]); for junior radiologists, specificity increased from 86.2% to 87.6% (+1.4%, P=0.42) and for senior radiologists, it decreased from 95.1% to 94.9% (-0.2%, P=0.23). The stand-alone sensitivity and specificity of the AI were, respectively, 91% and 90%.
    Conclusion: With the help of AI, sensitivity increased by an average of 10% without significantly decreasing specificity in fracture detection in a predominantly pediatric population.
     Assessment of an artificial intelligence aid for the detection of appendicular skeletal fractures in children and young adults by senior and junior radiologists
    Toan Nguyen et al.
    Pediatric Radiology (2022) 52:2215–2226
  • “We have shown that the diagnostic performance of junior and senior radiologists for fracture detection from conventional radiographs can be improved with the assistance of AI. The study confirms that AI is suitable for bone fracture detection in clinical practice even for young children. A prospective evaluation in a setting closer to the real-life scenario should be considered.”
    Assessment of an artificial intelligence aid for the detection of appendicular skeletal fractures in children and young adults by senior and junior radiologists
    Toan Nguyen et al.
    Pediatric Radiology (2022) 52:2215–2226
  • “Second, our study was retrospective in nature, with readers in artificial reading conditions, which could affect their reading. Moreover, the performance of readers was assessed solely on their ability to make decisions from the radiograph alone, without any of the clinical information or medical history that can be crucial in decision-making, creating a context bias. This same limitation applies to the radiologists who determined the ground truth, as they also worked without clinical information. Clinical information could have increased the sensitivity and specificity of readers and would have been more akin to daily practice. Furthermore, in everyday practice, indications are diverse and do not concern only trauma. Finally, reading with AI immediately after reading without AI could have introduced some bias. A study with clinical information, two separate phases and a washout period in between should be considered to remove these biases.”
    Assessment of an artificial intelligence aid for the detection of appendicular skeletal fractures in children and young adults by senior and junior radiologists
    Toan Nguyen et al.
    Pediatric Radiology (2022) 52:2215–2226
  • Background: As the number of conventional radiographic examinations in pediatric emergency departments increases, so, too, does the number of reading errors by radiologists.
    Objective: The aim of this study is to investigate the ability of artificial intelligence (AI) to improve the detection of fractures by radiologists in children and young adults.
    Materials and methods: A cohort of 300 anonymized radiographs performed for the detection of appendicular fractures in patients ages 2 to 21 years was collected retrospectively. The ground truth for each examination was established after an independent review by two radiologists with expertise in musculoskeletal imaging. Discrepancies were resolved by consensus with a third radiologist. Half of the 300 examinations showed at least 1 fracture. Radiographs were read by three senior pediatric radiologists and five radiology residents in the usual manner and then read again immediately after with the help of AI.
    Assessment of an artificial intelligence aid for the detection of appendicular skeletal fractures in children and young adults by senior and junior radiologists
    Toan Nguyen et al.
    Pediatric Radiology (2022) 52:2215–2226
  • Results: The mean sensitivity for all groups was 73.3% (110/150) without AI; it increased significantly by almost 10% (P<0.001) to 82.8% (125/150) with AI. For junior radiologists, it increased by 10.3% (P<0.001) and for senior radiologists by 8.2% (P=0.08). On average, there was no significant change in specificity (from 89.6% to 90.3% [+0.7%, P=0.28]); for junior radiologists, specificity increased from 86.2% to 87.6% (+1.4%, P=0.42) and for senior radiologists, it decreased from 95.1% to 94.9% (-0.2%, P=0.23). The stand-alone sensitivity and specificity of the AI were, respectively, 91% and 90%.
    Conclusion: With the help of AI, sensitivity increased by an average of 10% without significantly decreasing specificity in fracture detection in a predominantly pediatric population.
     Assessment of an artificial intelligence aid for the detection of appendicular skeletal fractures in children and young adults by senior and junior radiologists
    Toan Nguyen et al.
    Pediatric Radiology (2022) 52:2215–2226
  • “We have shown that the diagnostic performance of junior and senior radiologists for fracture detection from conventional radiographs can be improved with the assistance of AI. The study confirms that AI is suitable for bone fracture detection in clinical practice even for young children. A prospective evaluation in a setting closer to the real-life scenario should be considered.”
    Assessment of an artificial intelligence aid for the detection of appendicular skeletal fractures in children and young adults by senior and junior radiologists
    Toan Nguyen et al.
    Pediatric Radiology (2022) 52:2215–2226
  • “Second, our study was retrospective in nature, with readers in artificial reading conditions, which could affect their reading. Moreover, the performance of readers was assessed solely on their ability to make decisions from the radiograph alone, without any of the clinical information or medical history that can be crucial in decision-making, creating a context bias. This same limitation applies to the radiologists who determined the ground truth, as they also worked without clinical information. Clinical information could have increased the sensitivity and specificity of readers and would have been more akin to daily practice. Furthermore, in everyday practice, indications are diverse and do not concern only trauma. Finally, reading with AI immediately after reading without AI could have introduced some bias. A study with clinical information, two separate phases and a washout period in between should be considered to remove these biases.”
    Assessment of an artificial intelligence aid for the detection of appendicular skeletal fractures in children and young adults by senior and junior radiologists
    Toan Nguyen et al.
    Pediatric Radiology (2022) 52:2215–2226
  • Background: Approximately 40% of pancreatic tumors smaller than 2 cm are missed at abdominal CT.
    Purpose: To develop and to validate a deep learning (DL)–based tool able to detect pancreatic cancer at CT.
    Conclusion: The deep learning–based tool enabled accurate detection of pancreatic cancer on CT scans, with reasonable sensitivity for tumors smaller than 2 cm.
    Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study
    Po-Ting Chen et al.
    Radiology 2022; 000:1–11 (in press)
  • “Approximately 40% of pancreatic tumors smaller than 2 cm are missed at abdominal CT.”
    Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study
    Po-Ting Chen et al.
    Radiology 2022; 000:1–11 (in press)
  • Materials and Methods: Retrospectively collected contrast-enhanced CT studies in patients diagnosed with pancreatic cancer between January 2006 and July 2018 were compared with CT studies of individuals with a normal pancreas (control group) obtained between January 2004 and December 2019. An end-to-end tool comprising a segmentation convolutional neural network (CNN) and a classifier ensembling five CNNs was developed and validated in the internal test set and a nationwide real-world validation set. The sensitivities of the computer-aided detection (CAD) tool and radiologist interpretation were compared using the McNemar test.
    Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study
    Po-Ting Chen et al.
    Radiology 2022; 000:1–11 (in press)
  • Results: A total of 546 patients with pancreatic cancer (mean age, 65 years 6 12 [SD], 297 men) and 733 control subjects were randomly divided into training, validation, and test sets. In the internal test set, the DL tool achieved 89.9% (98 of 109; 95% CI: 82.7, 94.9) sensitivity and 95.9% (141 of 147; 95% CI: 91.3, 98.5) specificity (area under the receiver operating characteristic curve [AUC], 0.96; 95% CI: 0.94, 0.99), without a significant difference (P = .11) in sensitivity compared with the original radiologist report (96.1% [98 of 102]; 95% CI: 90.3, 98.9). In a test set of 1473 real-world CT studies (669 malignant, 804 control) from institutions throughout Taiwan, the DL tool distinguished between CT malignant and control studies with 89.7% (600 of 669; 95% CI: 87.1, 91.9) sensitivity and 92.8% specificity (746 of 804; 95% CI: 90.8, 94.5) (AUC, 0.95; 95% CI: 0.94, 0.96), with 74.7% (68 of 91; 95% CI: 64.5, 83.3) sensitivity for malignancies smaller than 2 cm.
    Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study
    Po-Ting Chen et al.
    Radiology 2022; 000:1–11 (in press)
  • “CT is the major imaging modality used to help detect PC, but its sensitivity for small tumors is modest, with approximately 40% of tumors smaller than 2 cm being missed. Furthermore, the diagnostic performance of CT is interpreter dependent and may be influenced by disparities in radiologist availability and expertise. Therefore, an effective tool to supplement radiologists in improving the sensitivity for PC detection is needed and constitutes a major unmet medical need.”  
    Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study
    Po-Ting Chen et al.
    Radiology 2022; 000:1–11 (in press)
  • Key Results
    • A deep learning tool for pancreatic cancer detection that was developed using contrast-enhanced CT scans obtained in 546 patients with pancreatic cancer and in 733 healthy control subjects achieved 89.9% sensitivity and 95.9% specificity in the internal test set (109 patients, 147 control subjects), which was similar to the sensitivity of radiologists (96.1%; P = .11).
    • In a validation set comprising 1473 individual CT studies (669 patients, 804 control subjects) from institutions throughout Taiwan, the deep learning tool achieved 89.7% sensitivity and 92.8% specificity in distinguishing pancreatic cancer, with 74.7% sensitivity for pancreatic cancers smaller than 2 cm.  
    Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study
    Po-Ting Chen et al.
    Radiology 2022; 000:1–11 (in press)
  • “Last, the control group did not include patients with pancreatic abnormalities other than PC, many of which require tissue sampling for confirmatory diagnosis. We seek to include other pancreatic abnormalities and prospectively assess the potential usefulness of the CAD tool in clinical settings in a future study.”    
    Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study
    Po-Ting Chen et al.
    Radiology 2022; 000:1–11 (in press)
  • “In conclusion, this study developed an end-to-end deep learning–based computer-aided detection (CAD) tool that could accurately and robustly detect pancreatic cancers (PCs) on contrast-enhanced CT scans. The CAD tool may be a useful supplement for radiologists to enhance detection of PC. Our results also suggest that the classification convolutional neural networks might have learned the secondary signs of PC, which warrants further investigation. While the results of this study provide strong support for the generalizability of the CAD tool in the Taiwanese and perhaps Asian populations, the performance of the CAD tool in other populations needs to be evaluated further.”
    Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study
    Po-Ting Chen et al.
    Radiology 2022; 000:1–11 (in press)
  • “Mukherjee et al. explored the ability of quantitative CT radiomic features of the pancreas to identity patients who would develop pancreatic cancer in the subsequent 3 to 36 months. They found that their radiomics-based model showed good predictive capacity, achieving sensitivity of 95% and specificity of 90% in a validation sample. Importantly, they showed performance robustness across CT scanners and slice thicknesses, and the model outperformed radiologists in identifying cases of pancreatic cancer. These findings add to the growing body of evidence that the indirect effects of pancreatic cancer, including endocrine and exocrine dysfunction and now whole-organ radiomic changes, may precede the diagnosis of cancer and could serve as early detection biomarkers.”
    Beyond the AJR: CT Radiomic Features of the Pancreas Predict Development of Pancreatic Cancer.
    Rosenthal MH, Schawkat K.
    AJR 2022 Oct 5 [published online]. Accepted manuscript. doi:10.2214/AJR.22.28582
  • “This work adds another potential tool to the radiologist’s arsenal for opportunistic screening from routine clinical imaging. Opportunistic screening takes advantage of features within imaging examinations that are not the subject of the examination but nonetheless convey important information about entities such as cardiovascular risk . Potential CT-based biomarkers for cancer include body composition analysis, CT based radiomic and texture analysis, and organ-based volumetry. These automated CT biomarkers could be deployed as part of the radiologist’s clinical workflow, allowing for prospective risk profiling in practice. In pancreatic cancer, opportunistic screening could identify individuals at sufficiently high risk to warrant active screening, as is currently performed for high-risk families. Such an approach, however, would generate a high rate of false positives for every true positive. To be clinically useful, it will likely need to be integrated with other risk markers.”
    Beyond the AJR: CT Radiomic Features of the Pancreas Predict Development of Pancreatic Cancer.
    Rosenthal MH, Schawkat K.
    AJR 2022 Oct 5 [published online]. Accepted manuscript. doi:10.2214/AJR.22.28582
  • “The use of ML-based radiomic analyses may offer a novel screening strategy for pancreatic cancer by detecting changes in the pancreas that precede the development of pancreatic cancer and the emergence of a radiologically detectable mass.”
    Beyond the AJR: CT Radiomic Features of the Pancreas Predict Development of Pancreatic Cancer.
    Rosenthal MH, Schawkat K.
    AJR 2022 Oct 5 [published online]. Accepted manuscript. doi:10.2214/AJR.22.28582
  • “Radiomics is a rapidly growing field that quantitatively extracts image features in a high-throughput manner from medical imaging. In this study, we analyzed the radiomics features of the whole pancreas between healthy individuals and pancreatic cancer patients, and we established a predictive model that can distinguish cancer patients from healthy individuals based on these radiomics features.”
    Compute Tomography Radiomics Analysis on Whole Pancreas Between Healthy Individual and Pancreatic Ductal Adenocarcinoma Patients: Uncertainty Analysis and Predictive Modeling
    Shuo Wang et al.
    Technology in Cancer Research & Treatment 2022; Volume 21: 1-14
  • Results: We identified that 91 radiomics features are stable against various uncertainty sources, including bin width, resampling, image transformation, image noise, and segmentation uncertainty. Eight of the 91 features are nonredundant. Our final predictive model, using these 8 features, has achieved a mean area under the receiver operating characteristic curve (AUC) of 0.99±0.01 on the training dataset (189 subjects) by cross-validation. The model achieved an AUC of 0.910 on the independent test set (77 subjects)and an accuracy of 0.935.  
    Conclusion: CT-based radiomics analysis based on the whole pancreas can distinguish cancer patients from healthy individuals, and it could potentially become an early detection tool for pancreatic cancer.
    Compute Tomography Radiomics Analysis on Whole Pancreas Between Healthy Individual and Pancreatic Ductal Adenocarcinoma Patients: Uncertainty Analysis and Predictive Modeling
    Shuo Wang et al.
    Technology in Cancer Research & Treatment 2022; Volume 21: 1-14
  • “Our study proved that CT-based radiomics analysis and modeling can distinguish healthy individuals from pancreatic cancer patients, and potentially can become an effective tool to detect cancerous pancreatic tissue at an early stage.”  
    Compute Tomography Radiomics Analysis on Whole Pancreas Between Healthy Individual and Pancreatic Ductal Adenocarcinoma Patients: Uncertainty Analysis and Predictive Modeling
    Shuo Wang et al.
    Technology in Cancer Research & Treatment 2022; Volume 21: 1-14
  • “In the elective field of adrenal imaging, artificial intelligence (AI) can be used for adrenal lesion detection, characterization, hypersecreting syndrome management and patient follow-up. Although a perfect AI tool that includes all required steps from detection to analysis does not exist yet, multiple AI algorithms have been developed and tested with encouraging results. However, AI in this setting is still at an early stage. In this regard, most published studies about AI in adrenal gland imaging report preliminary results that do not have yet daily applications in clinical practice. In this review, recent developments and current results of AI in the field of adrenal imaging are presented. Limitations and future perspectives of AI are discussed.”
    Artificial intelligence in adrenal imaging: A critical review of current applications
    Maxime Baratab, Martin Gaillardb, Anne-Segolene Cottereaub, Elliot K. Fishman, Guillaume Assieb, Anne Jouinotb, Christine Hoeffel, Philippe Soyer, Anthony Dohana
    Diagnostic and Interventional Imaging 000 (2022) 1−6  
  • "Recently, deep neuronal networks (DNN) were developed to improve accuracy of adrenal gland segmentation. Luo et al. used a two-step method with a preprocessing step to reduce variabilities between examinations and the computational burden followed by a second step of small organs segmentation network using annotated input . The CT dataset was obtained from 348 patients, 60% for the training, 20% for the validation and 20% for the testing cohort . With this model, the authors obtained a DSC of 87.2%, which is the best reported one to date for adrenal gland segmentation Despite a better DSC than those obtained with previous segmentation algorithms, DNNs also require further external validation to demonstrate their robustness.”
    Artificial intelligence in adrenal imaging: A critical review of current applications
    Maxime Baratab, Martin Gaillardb, Anne-Segolene Cottereaub, Elliot K. Fishman, Guillaume Assieb, Anne Jouinotb, Christine Hoeffel, Philippe Soyer, Anthony Dohana
    Diagnostic and Interventional Imaging 000 (2022) 1−6  
  • "Radiomics is regarded as a promising research field for the characterization and follow-up of non-typical AL. Using first order texture analysis features, Jhaveri et al. found that a 5% cut-off of negative voxels on histogram derived from unenhanced CT data had 92.3% sensitivity and 100% specificity for the characterization of lipid-poor AA . Another found that entropy (i.e., a first order texture analysis feature) yielded an AUC of 0.65 (95% CI: 0.52−0.77) to differentiate between adrenal metastasis from lung cancer (showing greater entropy) and AA Ho et al. developed a model using 21 second order features extracted from contrast-enhanced CT data that allowed differentiating lipid-poor AA from malignant AL better than standard morphological features (AUC of 0.8 vs. 0.6, respectively). Similarly, a model using four second-order features extracted from unenhanced CT data yielded 96.6% sensitivity, 81% specificity and 85.2% accuracy for the diagnosis of pheochromocytoma vs. lipid poor AA.”
    Artificial intelligence in adrenal imaging: A critical review of current applications
    Maxime Baratab, Martin Gaillardb, Anne-Segolene Cottereaub, Elliot K. Fishman, Guillaume Assieb, Anne Jouinotb, Christine Hoeffel, Philippe Soyer, Anthony Dohana
    Diagnostic and Interventional Imaging 000 (2022) 1−6 
  • “AI has currently applications in almost all fields of adrenal diseases. Although most studies are preliminary studies, they suggestthat AI may improve AL classification, prognosis, and possibly management of patients affected with AL. However, there is a long way to go before AI is implemented into daily practice of radiologist, endocrinologist, and surgeons. In this regard, one current limitation for immediate applicability is the observed difference in recommended management among societies. Some studies suggest that AI algorithms should not be built using imaging data alone but should integrate biological data for better efficacy. Finally, large, prospective studies with external validations are needed to buildeffective, predictive models that will help improve patients’ care by selecting the most appropriate option among surveillance, open vs. laparoscopic surgery or “leave it alone” option.”
    Artificial intelligence in adrenal imaging: A critical review of current applications
    Maxime Baratab, Martin Gaillardb, Anne-Segolene Cottereaub, Elliot K. Fishman, Guillaume Assieb, Anne Jouinotb, Christine Hoeffel, Philippe Soyer, Anthony Dohana
    Diagnostic and Interventional Imaging 000 (2022) 1−6 
  • “A machine learning algorithm was developed that can accurately segment and classify adrenal glands as normal or mass-containing on contrastvenhanced CT images, with performance similar to that of radiologists.”
    Machine Learning for Adrenal Gland Segmentation and Classification of Normal and Adrenal Masses at CT
    Cory Robinson-Weiss et al.
    Radiology 2022; 000:1–8
  • • In this retrospective study using CT images from 251 (development data set) and 991 patients (secondary test set), a machine learning algorithm segmented adrenal glands, with a performance similar to that of radiologists; the median model Dice score 0.87 versus 0.89 for normal adrenal glands and 0.85 versus 0.89 for adrenal masses.
    • The algorithm differentiated adrenal masses from normal adrenal glands, with 83% sensitivity and 89% specificity for the development data set and 69% sensitivity and 91% specificity for the secondary test set.
    Machine Learning for Adrenal Gland Segmentation and Classification of Normal and Adrenal Masses at CT
    Cory Robinson-Weiss et al.
    Radiology 2022; 000:1–8
  • “ Our results are promising given that the adrenal gland is an inherently challenging organ to segment compared with larger organs (such as the liver and kidneys), as these glands are small and change in position due to respiration, and their shape, size, and location can vary by laterality and patient. In addition, adrenal glands have soft-tissue attenuation at CT that is similar to that of adjacent structures, including the liver, pancreas, kidneys, and vasculature. In patients with a paucity of intra-abdominal fat, the adrenal glands may be even more challenging to delineate from adjacent structures without the contrasting fat around the glands to separate them from other structures. Finally, there may be external mass effect on the glands, for example from an adjacent liver cyst or mass.”
    Machine Learning for Adrenal Gland Segmentation and Classification of Normal and Adrenal Masses at CT
    Cory Robinson-Weiss et al.
    Radiology 2022; 000:1–8
  • “In conclusion, we propose a two-stage machine learning pipeline to automatically segment the adrenal glands at contrast enhanced CT and then classify the glands as normal or mass containing. This tool may be used to assist radiologists in accurate and expedient image interpretation and potentially decrease interreader variability. Future work is needed to improve the classification stage of our model, as well as expand on the scope of the classification task by reviewing prior imaging and assessing for mass stability or growth.”
    Machine Learning for Adrenal Gland Segmentation and Classification of Normal and Adrenal Masses at CT
    Cory Robinson-Weiss et al.
    Radiology 2022; 000:1–8
  • “In conclusion, only one-fourth of patients received appropriate biochemical testing after incidental diagnosis of an adrenal nodule, and most nodules with indeterminate imaging characteristics did not have follow-up imaging. Advanced data analytic techniques on electronic imaging reports may aid in the clinical identification andimproved management of patients with adrenal incidentalomas.”
    Automated extraction of incidental adrenal nodules from electronic health records
    Max Schumm et al.
    Surgery xxx (2022) 1e7 (in press)
  • Background: Many adrenal incidentalomas do not undergo appropriate biochemical testing and complete imaging characterization to assess for hormone hypersecretion and malignancy. With the growing availability of clinical narratives in the electronic medical record, automated surveillance using advanced data analytic techniques may represent a promising method to improve management.
    Conclusion: Only one-fourth of patients received appropriate biochemical testing after incidental diagnosis of an adrenal nodule, and most nodules with indeterminate imaging characteristics did notundergo follow-up imaging. Advanced data analytic techniques on electronic imaging reports may aid in the clinical identification and improved management of patients with adrenal incidentalomas.
    Automated extraction of incidental adrenal nodules from electronic health records
    Max Schumm et al.
    Surgery xxx (2022) 1e7 (in press)
Musculoskeletal

  • Background: As the number of conventional radiographic examinations in pediatric emergency departments increases, so, too, does the number of reading errors by radiologists.
    Objective: The aim of this study is to investigate the ability of artificial intelligence (AI) to improve the detection of fractures by radiologists in children and young adults.
    Materials and methods: A cohort of 300 anonymized radiographs performed for the detection of appendicular fractures in patients ages 2 to 21 years was collected retrospectively. The ground truth for each examination was established after an independent review by two radiologists with expertise in musculoskeletal imaging. Discrepancies were resolved by consensus with a third radiologist. Half of the 300 examinations showed at least 1 fracture. Radiographs were read by three senior pediatric radiologists and five radiology residents in the usual manner and then read again immediately after with the help of AI.
    Assessment of an artificial intelligence aid for the detection of appendicular skeletal fractures in children and young adults by senior and junior radiologists
    Toan Nguyen et al.
    Pediatric Radiology (2022) 52:2215–2226
  • Results: The mean sensitivity for all groups was 73.3% (110/150) without AI; it increased significantly by almost 10% (P<0.001) to 82.8% (125/150) with AI. For junior radiologists, it increased by 10.3% (P<0.001) and for senior radiologists by 8.2% (P=0.08). On average, there was no significant change in specificity (from 89.6% to 90.3% [+0.7%, P=0.28]); for junior radiologists, specificity increased from 86.2% to 87.6% (+1.4%, P=0.42) and for senior radiologists, it decreased from 95.1% to 94.9% (-0.2%, P=0.23). The stand-alone sensitivity and specificity of the AI were, respectively, 91% and 90%.
    Conclusion: With the help of AI, sensitivity increased by an average of 10% without significantly decreasing specificity in fracture detection in a predominantly pediatric population.
     Assessment of an artificial intelligence aid for the detection of appendicular skeletal fractures in children and young adults by senior and junior radiologists
    Toan Nguyen et al.
    Pediatric Radiology (2022) 52:2215–2226
  • “We have shown that the diagnostic performance of junior and senior radiologists for fracture detection from conventional radiographs can be improved with the assistance of AI. The study confirms that AI is suitable for bone fracture detection in clinical practice even for young children. A prospective evaluation in a setting closer to the real-life scenario should be considered.”
    Assessment of an artificial intelligence aid for the detection of appendicular skeletal fractures in children and young adults by senior and junior radiologists
    Toan Nguyen et al.
    Pediatric Radiology (2022) 52:2215–2226
  • “Second, our study was retrospective in nature, with readers in artificial reading conditions, which could affect their reading. Moreover, the performance of readers was assessed solely on their ability to make decisions from the radiograph alone, without any of the clinical information or medical history that can be crucial in decision-making, creating a context bias. This same limitation applies to the radiologists who determined the ground truth, as they also worked without clinical information. Clinical information could have increased the sensitivity and specificity of readers and would have been more akin to daily practice. Furthermore, in everyday practice, indications are diverse and do not concern only trauma. Finally, reading with AI immediately after reading without AI could have introduced some bias. A study with clinical information, two separate phases and a washout period in between should be considered to remove these biases.”
    Assessment of an artificial intelligence aid for the detection of appendicular skeletal fractures in children and young adults by senior and junior radiologists
    Toan Nguyen et al.
    Pediatric Radiology (2022) 52:2215–2226
Pancreas

  • “Cinematic rendering allows for nuanced visualization of areas of interest. Our preliminary experience, as one of the first centers to incorporate the routine use of CR, has proven very useful in surgical planning. For local determination of resectability, vascular mapping allows for accurate assessment of major arteries and the portovenous system. For the portovenous anatomy it assists in determining the optimal surgical approach (extent of resection, appropriate technique for reconstruction, and need for mesocaval shunting). For arterial anatomy, vessel encasement either represents dissectible involvement via periadventitial dissection or true vessel invasion that is unresectable. CR could potentially provide superior ability than traditional PPCT to discern between the two. Additionally, CR allows for better 3D visualization of arterial anatomic variants which, if not appreciated preoperatively, increases risk of intraoperative ischemia and postoperative complications. Lastly, CR could help avoid unnecessary surgery by enhanced identification of occult metastatic disease that is metastatic disease that is otherwise not appreciated on a standard PPCT.”
    Cinematic Rendering: Novel Tool for Improving Pancreatic Cancer Surgical Planning
    Ammar A. Javed, Robert W.C. Young, Joseph R. Habib,  Benedict Kinny-K€oster, Steven M. Cohen, Elliot K. Fishman,Christopher L. Wolfgang
    Curr Probl Diagn Radiol. 2022 Apr (in press)
  • “A pancreas protocol computed tomography (PPCT) scan is the single most important imaging modality in the determination of local resectability. The PPCT allows precise visualization of vascular structures in relation to the tumor. While advancements have been made in the radiological assessment of pancreatic lesions, the reported ability of PPCT to accurately classify tumor resectability as compared to MRI and histopathological findings ranges from 73% to 83%. In many cases, this may be dependent on inter-operator variability when determining the degree of tumor-vessel involvement and as many as 8% of all pancreatectomies are aborted due to the presence of metastatic disease that was not previously seen on imaging.”
    Cinematic Rendering: Novel Tool for Improving Pancreatic Cancer Surgical Planning
    Ammar A. Javed, Robert W.C. Young, Joseph R. Habib,  Benedict Kinny-K€oster, Steven M. Cohen, Elliot K. Fishman,Christopher L. Wolfgang
    Curr Probl Diagn Radiol. 2022 Apr (in press)
  • “We believe that CR has potential to more confidently determine patient candidacy for successful oncological resection and to aid in pre-surgical planning, particularly in complex cases of tumor-vascular involvement. Herein we describe the first routine implementationof CR in our pancreas multidisciplinary clinic, and the ways in which we utilize CR for our surgical planning.”
    Cinematic Rendering: Novel Tool for Improving Pancreatic Cancer Surgical Planning
    Ammar A. Javed, Robert W.C. Young, Joseph R. Habib,  Benedict Kinny-K€oster, Steven M. Cohen, Elliot K. Fishman,Christopher L. Wolfgang
    Curr Probl Diagn Radiol. 2022 Apr (in press)
  • “As described previously by our group, a halo sign is present when there is >180 degrees encasement of the SMA with tumor infiltration of surrounding lymphatic and neural tissue, however the vessel itself remains fully patent and without apparent tumor invasion. Here, the affected tissue surrounding the artery forms a halo, which appears hypodense, similar to the cancer itself, with circumferential abutment of the artery. In the case of perineural invasion an R0 resection can often be achieved through periadventitial dissection, whereas true arterial wall invasion would require a formal resection. We have found that CR is capable of detecting a thin plane of tissue separating vessel from overlying tumor  and is helpful in making determining true invasion. Briefly, a string sign represents >180 degrees encasement of the SMA by tumor infiltration of lymphatic and neural tissue results in the narrowing of a segment or segmental stenosis of the SMA owing to true arterial invasion and/or mechanical compression. In general, we do not offer surgery to patients with true superior mesenteric artery invasion.”
    Cinematic Rendering: Novel Tool for Improving Pancreatic Cancer Surgical Planning
    Ammar A. Javed, Robert W.C. Young, Joseph R. Habib,  Benedict Kinny-K€oster, Steven M. Cohen, Elliot K. Fishman,Christopher L. Wolfgang
    Curr Probl Diagn Radiol. 2022 Apr (in press)
  • “Cinematic rendering has the potential to detect and differentiate subtle liver and peritoneal metastases from surrounding tissue in the preoperative setting. Anecdotally, we have encountered instances in which CR visualized OMD in patients, despite no evidence of OMD on their initial PPCT scan read. These findingswere later confirmed on diagnostic laparoscopy. Further studiesare underway in order to validate the use of CR as a means to avoid diagnostic laparoscopy or aborted pancreatectomies. If validated, in the near future CR could help to avoid unnecessary laparotomy or laparoscopy, allow for the patient to receive appropriate counselling at the time of presentation, and avoid unnecessary delays in starting chemotherapy.”
    Cinematic Rendering: Novel Tool for Improving Pancreatic Cancer Surgical Planning
    Ammar A. Javed, Robert W.C. Young, Joseph R. Habib,  Benedict Kinny-K€oster, Steven M. Cohen, Elliot K. Fishman, Christopher L. Wolfgang
    Curr Probl Diagn Radiol. 2022 Apr (in press)
  • "Based on our experience, CR can provide additional information about tumor-vessel relationship, venous collateralization patterns and the presence of OMD. We have found CR to be particularly useful in differentiating true tumor infiltration from simple proximity to vessels. We have found this to be most helpful in evaluating encasement of the SMA based on the halo and string sign previously described. In our experience, patients with a halo sign usually proceed to surgery with periadventitial dissection of the SMA and most often undergo a negative margin (R0) resection. As systemic therapies continue to improve, we anticipate performing increasingly complex pancreatic operations, further enhancing the benefits of the routine implementation of CR.”
    Cinematic Rendering: Novel Tool for Improving Pancreatic Cancer Surgical Planning
    Ammar A. Javed, Robert W.C. Young, Joseph R. Habib,  Benedict Kinny-K€oster, Steven M. Cohen, Elliot K. Fishman, Christopher L. Wolfgang
    Curr Probl Diagn Radiol. 2022 Apr (in press)
  • "While cinematic rendering has potential to improve the determination of resectability, there remain several limitations to its widespreadi mplementation. CR requires specialized hardware andsoftware that may not be readily accessible at most institutions. Additionally,a radiologist requires specialized training in order to appropriately generate and adjust the parameters in real time for each unique pathology. To date there have been few studies investigating CR’s ability to impact surgical planning or ultimately improve patient outcomes. Future studies by our group will be directed toward elucidating its true impact. Additionally, while this review comments only on CR’s ability to assist in surgical planning, future studies are planned to investigate the utility of CR in the initial diagnosis and staging of pancreatic lesions, as well as the radiologic assessment of treatment response to preoperative chemotherapy.”
    Cinematic Rendering: Novel Tool for Improving Pancreatic Cancer Surgical Planning
    Ammar A. Javed, Robert W.C. Young, Joseph R. Habib,  Benedict Kinny-K€oster, Steven M. Cohen, Elliot K. Fishman, Christopher L. Wolfgang
    Curr Probl Diagn Radiol. 2022 Apr (in press)
  • Background: Approximately 40% of pancreatic tumors smaller than 2 cm are missed at abdominal CT.
    Purpose: To develop and to validate a deep learning (DL)–based tool able to detect pancreatic cancer at CT.
    Conclusion: The deep learning–based tool enabled accurate detection of pancreatic cancer on CT scans, with reasonable sensitivity for tumors smaller than 2 cm.
    Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study
    Po-Ting Chen et al.
    Radiology 2022; 000:1–11 (in press)
  • “Approximately 40% of pancreatic tumors smaller than 2 cm are missed at abdominal CT.”
    Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study
    Po-Ting Chen et al.
    Radiology 2022; 000:1–11 (in press)
  • Materials and Methods: Retrospectively collected contrast-enhanced CT studies in patients diagnosed with pancreatic cancer between January 2006 and July 2018 were compared with CT studies of individuals with a normal pancreas (control group) obtained between January 2004 and December 2019. An end-to-end tool comprising a segmentation convolutional neural network (CNN) and a classifier ensembling five CNNs was developed and validated in the internal test set and a nationwide real-world validation set. The sensitivities of the computer-aided detection (CAD) tool and radiologist interpretation were compared using the McNemar test.
    Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study
    Po-Ting Chen et al.
    Radiology 2022; 000:1–11 (in press)
  • Results: A total of 546 patients with pancreatic cancer (mean age, 65 years 6 12 [SD], 297 men) and 733 control subjects were randomly divided into training, validation, and test sets. In the internal test set, the DL tool achieved 89.9% (98 of 109; 95% CI: 82.7, 94.9) sensitivity and 95.9% (141 of 147; 95% CI: 91.3, 98.5) specificity (area under the receiver operating characteristic curve [AUC], 0.96; 95% CI: 0.94, 0.99), without a significant difference (P = .11) in sensitivity compared with the original radiologist report (96.1% [98 of 102]; 95% CI: 90.3, 98.9). In a test set of 1473 real-world CT studies (669 malignant, 804 control) from institutions throughout Taiwan, the DL tool distinguished between CT malignant and control studies with 89.7% (600 of 669; 95% CI: 87.1, 91.9) sensitivity and 92.8% specificity (746 of 804; 95% CI: 90.8, 94.5) (AUC, 0.95; 95% CI: 0.94, 0.96), with 74.7% (68 of 91; 95% CI: 64.5, 83.3) sensitivity for malignancies smaller than 2 cm.
    Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study
    Po-Ting Chen et al.
    Radiology 2022; 000:1–11 (in press)
  • “CT is the major imaging modality used to help detect PC, but its sensitivity for small tumors is modest, with approximately 40% of tumors smaller than 2 cm being missed. Furthermore, the diagnostic performance of CT is interpreter dependent and may be influenced by disparities in radiologist availability and expertise. Therefore, an effective tool to supplement radiologists in improving the sensitivity for PC detection is needed and constitutes a major unmet medical need.”  
    Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study
    Po-Ting Chen et al.
    Radiology 2022; 000:1–11 (in press)
  • Key Results
    • A deep learning tool for pancreatic cancer detection that was developed using contrast-enhanced CT scans obtained in 546 patients with pancreatic cancer and in 733 healthy control subjects achieved 89.9% sensitivity and 95.9% specificity in the internal test set (109 patients, 147 control subjects), which was similar to the sensitivity of radiologists (96.1%; P = .11).
    • In a validation set comprising 1473 individual CT studies (669 patients, 804 control subjects) from institutions throughout Taiwan, the deep learning tool achieved 89.7% sensitivity and 92.8% specificity in distinguishing pancreatic cancer, with 74.7% sensitivity for pancreatic cancers smaller than 2 cm.  
    Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study
    Po-Ting Chen et al.
    Radiology 2022; 000:1–11 (in press)
  • “Last, the control group did not include patients with pancreatic abnormalities other than PC, many of which require tissue sampling for confirmatory diagnosis. We seek to include other pancreatic abnormalities and prospectively assess the potential usefulness of the CAD tool in clinical settings in a future study.”    
    Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study
    Po-Ting Chen et al.
    Radiology 2022; 000:1–11 (in press)
  • “In conclusion, this study developed an end-to-end deep learning–based computer-aided detection (CAD) tool that could accurately and robustly detect pancreatic cancers (PCs) on contrast-enhanced CT scans. The CAD tool may be a useful supplement for radiologists to enhance detection of PC. Our results also suggest that the classification convolutional neural networks might have learned the secondary signs of PC, which warrants further investigation. While the results of this study provide strong support for the generalizability of the CAD tool in the Taiwanese and perhaps Asian populations, the performance of the CAD tool in other populations needs to be evaluated further.”
    Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study
    Po-Ting Chen et al.
    Radiology 2022; 000:1–11 (in press)
  • “Mukherjee et al. explored the ability of quantitative CT radiomic features of the pancreas to identity patients who would develop pancreatic cancer in the subsequent 3 to 36 months. They found that their radiomics-based model showed good predictive capacity, achieving sensitivity of 95% and specificity of 90% in a validation sample. Importantly, they showed performance robustness across CT scanners and slice thicknesses, and the model outperformed radiologists in identifying cases of pancreatic cancer. These findings add to the growing body of evidence that the indirect effects of pancreatic cancer, including endocrine and exocrine dysfunction and now whole-organ radiomic changes, may precede the diagnosis of cancer and could serve as early detection biomarkers.”
    Beyond the AJR: CT Radiomic Features of the Pancreas Predict Development of Pancreatic Cancer.
    Rosenthal MH, Schawkat K.
    AJR 2022 Oct 5 [published online]. Accepted manuscript. doi:10.2214/AJR.22.28582
  • “This work adds another potential tool to the radiologist’s arsenal for opportunistic screening from routine clinical imaging. Opportunistic screening takes advantage of features within imaging examinations that are not the subject of the examination but nonetheless convey important information about entities such as cardiovascular risk . Potential CT-based biomarkers for cancer include body composition analysis, CT based radiomic and texture analysis, and organ-based volumetry. These automated CT biomarkers could be deployed as part of the radiologist’s clinical workflow, allowing for prospective risk profiling in practice. In pancreatic cancer, opportunistic screening could identify individuals at sufficiently high risk to warrant active screening, as is currently performed for high-risk families. Such an approach, however, would generate a high rate of false positives for every true positive. To be clinically useful, it will likely need to be integrated with other risk markers.”
    Beyond the AJR: CT Radiomic Features of the Pancreas Predict Development of Pancreatic Cancer.
    Rosenthal MH, Schawkat K.
    AJR 2022 Oct 5 [published online]. Accepted manuscript. doi:10.2214/AJR.22.28582
  • “The use of ML-based radiomic analyses may offer a novel screening strategy for pancreatic cancer by detecting changes in the pancreas that precede the development of pancreatic cancer and the emergence of a radiologically detectable mass.”
    Beyond the AJR: CT Radiomic Features of the Pancreas Predict Development of Pancreatic Cancer.
    Rosenthal MH, Schawkat K.
    AJR 2022 Oct 5 [published online]. Accepted manuscript. doi:10.2214/AJR.22.28582
  • “Radiomics is a rapidly growing field that quantitatively extracts image features in a high-throughput manner from medical imaging. In this study, we analyzed the radiomics features of the whole pancreas between healthy individuals and pancreatic cancer patients, and we established a predictive model that can distinguish cancer patients from healthy individuals based on these radiomics features.”
    Compute Tomography Radiomics Analysis on Whole Pancreas Between Healthy Individual and Pancreatic Ductal Adenocarcinoma Patients: Uncertainty Analysis and Predictive Modeling
    Shuo Wang et al.
    Technology in Cancer Research & Treatment 2022; Volume 21: 1-14
  • Results: We identified that 91 radiomics features are stable against various uncertainty sources, including bin width, resampling, image transformation, image noise, and segmentation uncertainty. Eight of the 91 features are nonredundant. Our final predictive model, using these 8 features, has achieved a mean area under the receiver operating characteristic curve (AUC) of 0.99±0.01 on the training dataset (189 subjects) by cross-validation. The model achieved an AUC of 0.910 on the independent test set (77 subjects)and an accuracy of 0.935.  
    Conclusion: CT-based radiomics analysis based on the whole pancreas can distinguish cancer patients from healthy individuals, and it could potentially become an early detection tool for pancreatic cancer.
    Compute Tomography Radiomics Analysis on Whole Pancreas Between Healthy Individual and Pancreatic Ductal Adenocarcinoma Patients: Uncertainty Analysis and Predictive Modeling
    Shuo Wang et al.
    Technology in Cancer Research & Treatment 2022; Volume 21: 1-14
  • “Our study proved that CT-based radiomics analysis and modeling can distinguish healthy individuals from pancreatic cancer patients, and potentially can become an effective tool to detect cancerous pancreatic tissue at an early stage.”  
    Compute Tomography Radiomics Analysis on Whole Pancreas Between Healthy Individual and Pancreatic Ductal Adenocarcinoma Patients: Uncertainty Analysis and Predictive Modeling
    Shuo Wang et al.
    Technology in Cancer Research & Treatment 2022; Volume 21: 1-14
  • “Radiological features as pancreatic duct dilation and interruption, and focal atrophy are common first signs of PDAC and are often missed or unrecognized. Further investigation with dedicated pancreas imaging is warranted in patients with PDAC-related radiological findings.”
    Prevalence, features, and explanations of missed and misinterpreted pancreatic cancer on imaging: a matched case–control study
    Sanne A. Hoogenboom et al.
    Abdominal Radiology 2022 (in press) https://doi.org/10.1007/s00261-022-03671-6
  • “As stated earlier, PanIN with high-grade dysplasia and early invasive PDAC lesions do not generally form clear hypodense masses. Still, they may cause visible changes of the pancreatic parenchyma and the pancreatic duct, and these changes are rarely observed in patients who do not subsequently develop PDAC, as demonstrated in this study. Focal parenchymal atrophy may be a less known PDAC related imaging feature, but was observed on CT and MRI in 46%–49% of cases and only in one control patient. These results confirm the conclusion of recently published papers, who recognized focal atrophy as one of the first radiological features of early-stage PDAC.”
    Prevalence, features, and explanations of missed and misinterpreted pancreatic cancer on imaging: a matched case–control study
    Sanne A. Hoogenboom et al.
    Abdominal Radiology 2022 (in press) https://doi.org/10.1007/s00261-022-03671-6
  • “Current practice may underestimate the importance of these secondary findings, especially in the absence of a distinct mass. For patients with PD dilation, interruption, and focal atrophy, thorough examination (e.g., dedicated pancreas imaging with MRI/ MRCP, CT or endoscopic ultrasound) and close follow-up is recommended.”
    Prevalence, features, and explanations of missed and misinterpreted pancreatic cancer on imaging: a matched case–control study
    Sanne A. Hoogenboom et al.
    Abdominal Radiology 2022 (in press) https://doi.org/10.1007/s00261-022-03671-6
  • “Approximately 35% of the reassessed CTs in this study were obtained without contrast, which may have restricted the radiologists’ ability to assess the presence of lesions and secondary signs. This represents a real world scenario, in which unfortunately not all opportunities to detect pre-diagnostic pancreatic cancer will be according to ideal imaging protocols. When pancreas pathology is suspected, the next immediate step after substandard imaging would be to follow-up with the optimal CT and MRI protocols for assessing the pancreas according to society recommendations.”
    Prevalence, features, and explanations of missed and misinterpreted pancreatic cancer on imaging: a matched case–control study
    Sanne A. Hoogenboom et al.
    Abdominal Radiology 2022 (in press) https://doi.org/10.1007/s00261-022-03671-6
  • “FPPA occurred in 28% of the PDAC group at 35 months prediagnosis. The FPPA area resolved before PDAC onset. Benchmarking previous images of the pancreas with the focus on FPPA may enable prediction of PDAC. PDAC with FPPA involves widespread high-grade pancreatic intraepithelial neoplasia requiring a wide surgical margin for surgical excision.”
    Focal pancreatic parenchyma atrophy is a harbinger of pancreatic cancer and a clue to the intraductal spreading subtype
    Jun Nakahodo et al.
    Pancreatology 2022 (in press)
  • “Despite these limitations, our study demonstrated that FPPA was present before the clinical onset of pancreatic cancer in a significant proportion of the patients. Some asymptomatic cases of pancreatic cancer may potentially be detected earlier if clinicians are vigilant in their assessment of the patient’s pancreatic health. In line with the results of previous studies, our results indicated that FPPA is a precancerous finding in some cases of pancreatic cancer. Our findings may significantly improve the accuracy of diagnosing PDAC before symptom onset and provide the basis for a future large-scale, multicentric, prospective study. In conclusion, at least 30% of PDAC cases exhibited atrophy before diagnosis. In many cases, PDAC was able to be predicted by benchmarking retrospective images of FPPA findings using past imaging studies to create a timeline. Filling of the atrophy area is likely to indicate the presence of invasive cancer, which may help identify asymptomatic PDAC. A sufficiently wide margin including the atrophic area should be created when performing surgery as the lesions tend to spread widely.”
    Focal pancreatic parenchyma atrophy is a harbinger of pancreatic cancer and a clue to the intraductal spreading subtype
    Jun Nakahodo et al.
    Pancreatology 2022 (in press)
  • “Perivascular soft tissue may be observed following pancreaticoduodenectomy in both malignant and benign etiologies, and the long- or short-axis diameter and enhancement pattern may not help in differentiating malignant versus benign perivascular soft tissue. Benign portal vein stenosis has been described in up to 26–84% of first postoperative CTs of patients who underwent pancreaticoduodenectomy for PDAC and is especially common in patients who required portomesenteric venous resection and reconstruction. While benign portal vein stenosis gradually resolves or remains stable in most patients, the portal vein stenosis associated with tumor recurrence is usually progressive and may develop after the initial postoperative CT.”
    Postoperative surveillance of pancreatic ductal adenocarcinoma (PDAC) recurrence: practice pattern on standardized imaging and reporting from the society of abdominal radiology disease focus panel on PDAC
    Linda C. Chu et al.
    Abdominal Radiology 2022 (in press)
  • “The recommended surveillance interval during the first year for patients at high risk of recurrence is every 3 months or less (S3Q7, 85.7%). The surveillance interval during the first year for patients at low risk of recurrence failed to reach consensus, with 66.7% of panelists favoring every 4–6 months and 33.3% of panelists favoring every 3 months or less (S3Q8). The panelists failed to reach consensus for surveillance interval during the second year for patients at high risk of recurrence, with 71.4% of panelists favoring every 4–6 months and 28.6% of panelists favoring every 3 months or less (S3Q9). The panelists agreed that the surveillance interval during the second year for patients at low risk of recurrence should be every 4–6 months (S3Q10, 95.2%).”
    Postoperative surveillance of pancreatic ductal adenocarcinoma (PDAC) recurrence: practice pattern on standardized imaging and reporting from the society of abdominal radiology disease focus panel on PDAC
    Linda C. Chu et al.
    Abdominal Radiology 2022 (in press)
  • "Postoperative imaging following PDAC resection is challenging to interpret due to the presence of confounding postoperative inflammatory changes, which may be further exacerbated by the adjuvant or neoadjuvant treatmentinduced fibrosis. Some of the existing guidelines address recommended imaging surveillance intervals but do not provide guidance about the risk of recurrence based on specific imaging features. This SAR PDAC DFP consensus document aims to begin the groundwork for defining imaging features that should be considered suspicious for tumor recurrence. These imaging findings should be interpreted in conjunction with CA19-9 to improve specificity. Future work is needed to standardize the lexicon in describing postoperative findings to refine the tumor recurrence risk assessment.”
    Postoperative surveillance of pancreatic ductal adenocarcinoma (PDAC) recurrence: practice pattern on standardized imaging and reporting from the society of abdominal radiology disease focus panel on PDAC
    Linda C. Chu et al.
    Abdominal Radiology 2022 (in press)
PET-CT

  • “CR of PET/CT data provides a photorealistic means of visualizing complex fusion imaging datasets. Such visualizations may aid anatomic understanding for surgical or procedural applications, may improve teaching of trainees, and may allow improved communication with patients.”
    Photorealistic three‑dimensional visualization of fusion datasets: cinematic rendering of PET/CT
    Steven P. Rowe · Martin G. Pomper · Jeffrey P. Leal · Robert Schneider · Sebastian Krüger · Linda C. Chu · Elliot K. Fishman 
  • The external light used for CR is emitted from a high dynamic range (HDR) lightmap that defines the environment of the rendering. Because CR is based on the enhanced rendering equation, it can support the option that external light can not only be scattered and reflected, but internal light can also be emitted by a volume or a segmentation. In the current algorithm, we added a parameter for the PET dataset that defines how much light is emitted by the PET, which can also be set to zero so that in such a case no internal light is emitted at all. To have more flexibility to influence internal versus external light, we also added a parameter that scales the intensity of the external light emitted from the lightmap.
    Photorealistic three‑dimensional visualization of fusion datasets: cinematic rendering of PET/CT
    Steven P. Rowe · Martin G. Pomper · Jeffrey P. Leal · Robert Schneider · Sebastian Krüger · Linda C. Chu ·Elliot K. Fishman
    Abdominal Radiology (2022) 47:3916–3920 
  • “There are potential limitations of the described technique. The creation of PET/CT CR images may add significant time to the interpretation of cases until the reader develops the necessary experience to quickly utilize presets and adjust those presets as needed. Although there is no specific expertise required for the successful deployment of PET/CT CR images, there is a learning curve and readers may need to make the time to familiarize themselves with the software and develop a facility with the presets and their manual manipulation. Further, key pathology can be obscured by overlapping structures in the CR images, necessitating diligent correlation to the 2D reconstructions and the use of cut planes and multiple presets to ensure important findings are well displayed. Of course, potential applications will need to be studied. Nonetheless, the presented technology is promising. The ultimate utility of this technology will depend upon its widespread availability and acceptance by imaging specialists.”
    Photorealistic three‑dimensional visualization of fusion datasets: cinematic rendering of PET/CT
    Steven P. Rowe · Martin G. Pomper · Jeffrey P. Leal · Robert Schneider · Sebastian Krüger · Linda C. Chu ·Elliot K. Fishman
    Abdominal Radiology (2022) 47:3916–3920 
Practice Management

  • Background and Purpose: Medical errors can result in significant morbidity and mortality. The goal of our study is to evaluate correlation between shift volume and errors made by attending neuroradiologists at an academic medical center, using a large data set.
    Materials and Methods: CT and MRI reports from our Neuroradiology Quality Assurance database (years 2014   2020) were searched for attending physician errors. Data were collected on shift volume, category of missed findings, error type, interpretation setting, exam type, clinical significance.
    Conclusion: Errors were associated with higher volume shifts, were primarily perceptual and clinically significant. We need National guidelines establishing a range of what is a safe number of interpreted cross-sectional studies per day.
    Impact of Shift Volume on Neuroradiology Diagnostic Errors at a Large Tertiary Academic Center
    Vladimir Ivanovic et al.
    Acad Radiol 2022 (in press)
  • Results: 654 reports contained diagnostic error. There was a significant difference between mean volume of interpreted studies on shifts when an error was made compared with shifts in which no error was documented (46.58 (SD=22.37) vs 34.09 (SD=18.60), p<0.00001); and between shifts when perceptual error was made compared with shifts when interpretive errors were made (49.50 (SD=21.9) vs 43.26 (SD=21.75), p=0.0094). 59.6% of errors occurred in the emergency/inpatient setting, 84% were perceptual and 91.1% clinically significant. Categorical distribution of errors was: vascular 25.8%, brain 23.4%, skull base 13.8%, spine 12.4%, head/neck 11.3%, fractures 10.2%, other 3.1%. Errors were detected most often on brain MRI (25.4%), head CT (18.7%), head/neck CTA (13.8%), spine MRI (13.7%).
    Impact of Shift Volume on Neuroradiology Diagnostic Errors at a Large Tertiary Academic Center
    Vladimir Ivanovic et al.
    Acad Radiol 2022 (in press)
  • “There was a significant difference between mean volume of interpreted studies on shifts when an error was made compared with shifts in which no error was documented (46.58 (SD=22.37) vs 34.09 (SD=18.60), p<0.00001); and between shifts when perceptual error was made compared with shifts when interpretive errors were made (49.50 (SD=21.9) vs 43.26 (SD=21.75), p=0.0094). 59.6% of errors occurred in the emergency/inpatient setting, 84% were perceptual and 91.1% clinically significant.”
    Impact of Shift Volume on Neuroradiology Diagnostic Errors at a Large Tertiary Academic Center
    Vladimir Ivanovic et al.
    Acad Radiol 2022 (in press)
  • “This study, diagnostic errors were found to significantly correlate with higher volume shifts. Most errors were perceptual, clinically significant and occurred in the emergency/inpatient setting (which tend to be our busiest shifts). To our knowledge, this study is the largest reported on neuroradiology attending physician errors, and our findings of association of busier shifts and errors is similar to other publications. In thoracic radiology, higher error rates have been associated with increasing number of interpreted studies per workday, or with decreased interpretation time per study. When interpreting abdominal CT studies, error rates more than double with increasing volume of interpreted studies.”
    Impact of Shift Volume on Neuroradiology Diagnostic Errors at a Large Tertiary Academic Center
    Vladimir Ivanovic et al.
    Acad Radiol 2022 (in press)
  • “Our data suggests that a workflow adjustment aiming at limiting the number of studies per shift below a critical threshold might be beneficial in reducing error rate. Based on the findings of this study, we are considering instituting a ceiling of around 40 studies per day within our Neuroradiology Division once we are able to be fully staffed. Having to interpret CT/MRI exams in excess of the proposed institution-specific ceiling in a single shift may result in worsened patient and institutional outcomes based on the above published data.”
    Impact of Shift Volume on Neuroradiology Diagnostic Errors at a Large Tertiary Academic Center
    Vladimir Ivanovic et al.
    Acad Radiol 2022 (in press)
  • “In conclusion, the majority of errors noted in our series occurred on higher volume shifts and were clinically significant. We need National guidelines establishing a range of what is asafe number of interpreted cross-sectional studies per day per radiologist, and the number of hours worked per shift.”
    Impact of Shift Volume on Neuroradiology Diagnostic Errors at a Large Tertiary Academic Center
    Vladimir Ivanovic et al.
    Acad Radiol 2022 (in press)
  • “What are the most important medical challenges in 2022? I believe they were aging, disparities in health, and the high cost of medical care. No one could have predicted COVID-19. In the last year, I have come to believe the most important challenge is humanizing medicine. I am reminded of Osler, who said, “The good doctor treats the disease, the great doctor treats the person with the disease.” Francis Peabody said, “One of the essential qualities of the clinician is interest in humanity, for the secret of the care of the patient is caring for the patient.”
    Renegades, Rebels, and Revolutionaries: Making Medicine a Better Public Trust
    David B. Hellmann, Elliot K. Fishman, Elias Lugo-Fagundo, Linda C. Chu, Steven P. Rowe
    Journal of the American College of Radiology 2022 (in press)
  • “However, most patients are not known as people. Most physicians are not excellent at knowing their patients. Most doctors do not listen (67% of doctors interrupt). There are many system impediments to listening, such as the constant use of the electronic medical record. Not knowing patients as people is associated with worse outcomes in chronic diseases such as diabetes, higher cost, lower patient and family satisfaction, and burnout among doctors and nurses. Dehumanization in medicine leads to many indignities.”
    Renegades, Rebels, and Revolutionaries: Making Medicine a Better Public Trust
    David B. Hellmann, Elliot K. Fishman, Elias Lugo-Fagundo, Linda C. Chu, Steven P. Rowe
    Journal of the American College of Radiology 2022 (in press)
  • “The second story would be that personomics and humanizing medicine fuels discovery and drives precision medicine. The idea that cancer can cause autoimmune disease was suggested by a patient’s story. The “same,” genetically identical, disease may receive different “precise” treatments. Embracing personomics could lead to record recruitment and retention of nurses and record enrollment and satisfaction of patients in “value-based” health plans. Frequently marginalized patients with diabetes, human immunodeficiency virus, or sickle cell may develop greater trust, greater adherence, and better outcomes.”
    Renegades, Rebels, and Revolutionaries: Making Medicine a Better Public Trust
    David B. Hellmann, Elliot K. Fishman, Elias Lugo-Fagundo, Linda C. Chu, Steven P. Rowe
    Journal of the American College of Radiology 2022 (in press)
  • “Academic medicine and academic radiology must continue to think in revolutionary and creative ways. People who are attracted to academic medicine want to be a part of important ideas and initiatives. Although, at first glance, we think of discovery as the measure of success, caring for patients in a humanizing manner is the true measure of success. Radiology will inevitably continue to evolve into a more patient-facing specialty. Increasing emphasis on interventional radiology, radionuclide therapy, and interactions between diagnostic imagers and patients indicate the need for our specialty to know our patients as people. We should embrace the humanization of medicine as an opportunity to keep our place as key caregivers and stave off the commoditization of radiology.”
    Renegades, Rebels, and Revolutionaries: Making Medicine a Better Public Trust
    David B. Hellmann, Elliot K. Fishman, Elias Lugo-Fagundo, Linda C. Chu, Steven P. Rowe
    Journal of the American College of Radiology 2022 (in press)
  • “Radiology will inevitably continue to evolve into a more patient-facing specialty. Increasing emphasis on interventional radiology, radionuclide therapy, and interactions between diagnostic imagers and patients indicate the need for our specialty to know our patients as people. We should embrace the humanization of medicine as an opportunity to keep our place as key caregivers and stave off the commoditization of radiology.”
    Renegades, Rebels, and Revolutionaries: Making Medicine a Better Public Trust
    David B. Hellmann, Elliot K. Fishman, Elias Lugo-Fagundo, Linda C. Chu, Steven P. Rowe
    Journal of the American College of Radiology 2022 (in press)
  • “These aspects are particularly burdensome for what we refer toas the “sandwich generation”: the busy, working individuals who are caring for elderly parents and grandparents as well as their own children. Companies in this space can perform a variety of tasks for caregivers: they can make appointments,  find the right specialists, and vet in-home care providers, among other responsibilities. With the sandwich generation being an ever increasing demographic, businesses need to be ready to support caregivers across the full spectrum of care, including aging, childcare, special needs, chronic conditions, veteran support, mental health, intersectional needs, and more.”
    Providing Resources for the “Sandwich Generation”: Personalized Help With Care for the Elderly and Disabled
    Lindsay Jurist-Rosner, MBA, Elliot K. Fishman, MD, Linda C. Chu, MD, Steven P. Rowe, MD, PhD
    J Am Coll Radiol. 2022 Aug 12:S1546-1440(22)00567-1. 
  • “One in five working adults serves as a family caregiver, and it is a responsibility that can wear on the physical, emotional, and financial health of individuals who also work full-time. These individuals often epitomize the sandwich generation, with high levels of burnout because of the competing needs of their careers balanced against childcare and elder care. Employees come to work distracted and stressed out and use different kinds of leave to manage care obligations. Caregiving is still primarily a women’s issue. Care became even more complicated with coronavirus disease 2019 (COVID-19) because people had to be careful about who came into their homes.”
    Providing Resources for the “Sandwich Generation”: Personalized Help With Care for the Elderly and Disabled
    Lindsay Jurist-Rosner, MBA, Elliot K. Fishman, MD, Linda C. Chu, MD, Steven P. Rowe, MD, PhD
    J Am Coll Radiol. 2022 Aug 12:S1546-1440(22)00567-1. 
  • “Every day is learning and growing. We have the unbelievable fortune of being able to change peoples’ lives. People come to us in crisis. We can help them figure it out. People have jobs, kids, and other responsibilities, and they come to us after a fall or another lifechanging event. We send out surveys, people rate us, and we ask for feedback to continue to improve. We make sure all our employees get this feedback too, to see that they are affecting peoples’ lives. We’re a very mission-driven company, and we often attract caregivers who want to be on our team because they have a personal desire to solve these problems.”
    Providing Resources for the “Sandwich Generation”: Personalized Help With Care for the Elderly and Disabled
    Lindsay Jurist-Rosner, MBA, Elliot K. Fishman, MD, Linda C. Chu, MD, Steven P. Rowe, MD, PhD
    J Am Coll Radiol. 2022 Aug 12:S1546-1440(22)00567-1. 
  • “Offering employees help with care for their elderly and disabled loved ones could have important implications for retention, burnout, and other issues, for young academics. These considerations disproportionately affect young women clinician scientists. These issues are not unique to physicians but also affect other radiology staff members, such as nurses and radiologic technologists.People in the health care industry cannot escape caregiving, because they are squeezed between patients and family—a recipe for burnout. People can face compassion fatigue. Traditional care models do not work for many families. Many daycares closed during COVID-19, and many did not reopen. Many families did not want nannies in their homes. It is incumbent upon radiology departments and practices to help their employees find resources to assist with the pressing needs related to caregiving.”
    Providing Resources for the “Sandwich Generation”: Personalized Help With Care for the Elderly and Disabled
    Lindsay Jurist-Rosner, MBA, Elliot K. Fishman, MD, Linda C. Chu, MD, Steven P. Rowe, MD, PhD
    J Am Coll Radiol. 2022 Aug 12:S1546-1440(22)00567-1. 
  • “As the COVID-19 pandemic wanes across much of the United States and some other parts of the world, we are entering the era of “the great resignation.” Medical practices are now finding themselves short of everyone from technologists, to nurses, to radiologists, to front-desk employees. New types of benefits, such as concierge service platforms, may make people feel more valued and could lead to improved engagement, morale, and recruitment and retention.”
    Providing Resources for the “Sandwich Generation”: Personalized Help With Care for the Elderly and Disabled
    Lindsay Jurist-Rosner, MBA, Elliot K. Fishman, MD, Linda C. Chu, MD, Steven P. Rowe, MD, PhD
    J Am Coll Radiol. 2022 Aug 12:S1546-1440(22)00567-1. 
  • “Medical misinformation contributes toa substantial health toll in the US and around the world, and both the harms it causes and the challenge of confronting it have been exacerbated by social media. Mitigating the effects of misinformation requires a multifaceted approach that includes partnerships among clinicians, public health officials, technologists, patient groups, and community leaders. Moving forward will require sustained attention and considerable effort, but the rewards of progress are a shared understanding of what is true and what is not, strengthening the foundation of healthy people and a healthy society.”
    SocialMedia and Medical Misinformation Confronting New Variants of an Old Problem
    Khulliar D
    JAMA Published online September 23, 2022 
  • “The spread of false and misleading health information has increased substantially in recent years. During theCOVID-19 pandemic, for example, misinformation contributed to the use of unproven treatments, nonadherence to mitigation measures, and high levels of vaccine hesitancy. A study based on counterfactual simulation modeling suggested that higher immunization rates could have prevented nearly half of COVID-19–related deathsin the US between January 1, 2021, and April 30, 2022.”
    Social Media and Medical Misinformation Confronting New Variants of an Old Problem
    Khulliar D
    JAMA Published online September 23, 2022
Small Bowel

  • “In conclusion, enteric contrast continues to play an important role in the imaging assessment of patients presenting to the emergency department. Although it may no longer be required to ensure diagnostic accuracy on a routine basis, enteric contrast remains valuable, particularly when used in a targeted fashion to address specific clinical questions on a case-by-case basis. Enteric contrast is safe and well-tolerated by most patients with a low risk of serious side effects.”
    The Use of Enteric Contrast in the Emergency Setting
    Mohamed Z. Rajput et al.
    Radiol Clin N Am - (2023) (in press)
  • “A recent survey revealed that most patients (89%) would prefer to drink oral contrast, even with only the slightest likelihood that this will improve diagnostic accuracy, rather than accepting a risk of a missed finding. Radiologists report increased diagnostic confidence and reader reliability in cases in which any type of enteric contrast is used for CT imaging.83 This can be particularly important in the emergency setting, where one encounters critical, life-threatening pathologies requiring confident and accurate diagnoses on a routine basis.”
    The Use of Enteric Contrast in the Emergency Setting
    Mohamed Z. Rajput et al.
    Radiol Clin N Am - (2023) (in press)
  • “Targeted use of enteric contrast for CT imagingin patients presenting to the emergency department is helpful in specific clinical scenarios, especially when assessing for gastrointestinal tract perforation or complications following abdominal surgery.”
    The Use of Enteric Contrast in the Emergency Setting
    Mohamed Z. Rajput et al.
    Radiol Clin N Am - (2023) (in press)
  •   “Enteric contrast continues to play an important role in the imaging assessment of patients presenting to the emergency department, especially when combined with computed tomography in specific clinical situations to improve diagnostic accuracy.   Enteric contrast is particularly helpful in assessing postoperative complications of abdominal surgeries such as anastomotic leaks and fistulas. Although not always administered routinely, enteric contrast can be useful to confirm bowel injuries in the setting of penetrating trauma. Enteric contrast can assist in the identification of the appendix in cases of suspected acute appendicitis. Enteric contrast is also effective at guiding operative versus nonoperative management of patients with small-bowel obstruction. Although enteric contrast is overall safe and well-tolerated, the benefits of using it should be weighed against potential risks to the patient, including the time required to administer enteric contrast potentially resulting in a delay in diagnosis.”
    The Use of Enteric Contrast in the Emergency Setting
    Mohamed Z. Rajput et al.
    Radiol Clin N Am - (2023) (in press)
  • “Melanoma is the most aggressive form of skin cancer, with tendency to spread to any organ of the human body, including the gastrointestinal tract (GIT). The diagnosis of metastases to the GIT can be difficult, as they may be clinically silent for somewhile and may occur years after the initial melanoma diagnosis. CT imaging remains the standard modality for staging and surveillance of melanoma patients, and in most cases, it will be the first imaging modality to identify GIT lesions. However, interpretation of CT studies in patients with melanoma can be challenging as lesions may be subtle and random in distribution, as well as sometimes mimicking other conditions. Even so, early diagnosis of GIT metastases is critical to avoid emergency hospitalisations, whilst surgical intervention can be curative in some cases. In this review, we illustrate the various imaging presentations of melanoma metastases within the GIT, discuss the clinical aspects and offer advice on investigation and management. We offer tips intended to aid radiologists in their diagnostic skills and interpretation of melanoma imaging scans.”
    The different faces of metastatic melanoma in the gastrointestinal tract
    Eva Mendes Serrao et al.
    Insights into Imaging (2022) 13:161
  • • Melanoma is the most common solid tumour metastasizing to the GIT.
    • Melanoma metastases in the GIT can have multiple radiological appearances and mimic other conditions.
    • Radiological identification of melanoma metastases in the GIT is important, as early diagnosis and treatment improve quality and quantity of life, even inpalliative cases.  
    The different faces of metastatic melanoma in the gastrointestinal tract
    Eva Mendes Serrao et al. 
    Insights into Imaging (2022) 13:161
  • “Melanoma in the GIT can also rarely be a true primary tumour arising from the GI mucosa, with this entity being biologically distinct from cutaneous melanoma. In the GIT, they arise most frequently in the anorectal mucosal epithelium (anus 31% and rectum 22%), and less often in the oesophagus (6%), stomach (3%), small intestine (2%) and large intestine (1%), with a high proportion arising in the mucosal linings of the oralnasopharynx(35%).”  
    The different faces of metastatic melanoma in the gastrointestinal tract
    Eva Mendes Serrao et al.
    Insights into Imaging (2022) 13:161
  • “The stomach, after the small bowel and colon, is the third most common GIT site involved by MM. Patients with MM in the stomach can present with nausea, vomiting, gastrointestinal bleeding, weight loss and occasionallwith acute perforation. CT imaging can suggest the diagnosis by the presence of a mural nodule or mass , with or without cavitation, but definitive diagnosis is best achieved by endoscopy and biopsy. However, there is growing evidence that MRI with diffusion weighted imaging (DWI) can provide improved early detection and characterisation of gastric lesions as well as local staging.”
    The different faces of metastatic melanoma in the gastrointestinal tract
    Eva Mendes Serrao et al. 
    Insights into Imaging (2022) 13:161
  • “The small bowel is the most common metastatic site for melanoma in the GIT. Melanoma is the most common solid cancer type to metastasise to the small bowel (SB) with the jejunum and terminal ileum being the most commonly involved segments.”
    The different faces of metastatic melanoma in the gastrointestinal tract
    Eva Mendes Serrao et al. 
    Insights into Imaging (2022) 13:161
  • “Melanoma metastases to the GIT are not uncommon. Oligometastatic lesions can be successfully removed by surgery and offer cure to selected patients, even those whose tumours occur during treatment with modern systemic therapy. CT remains the standard modality for detection, staging and follow-up of these patients. However, detection of GIT metastases can be challenging as they are often subtle, can be multiple and can present with a multitude of morphological appearances.”
    The different faces of metastatic melanoma in the gastrointestinal tract
    Eva Mendes Serrao et al. 
    Insights into Imaging (2022) 13:161
Spleen

  • Splenomegaly: Causes
    - Viral infections, such as mononucleosis
    - Bacterial infections, such as syphilis or an infection of your heart's inner lining (endocarditis)
    - Parasitic infections, such as malaria
    - Cirrhosis and other diseases affecting the liver
    - Various types of hemolytic anemia — a condition characterized by early destruction of red blood cells
    - Blood cancers, such as leukemia and myeloproliferative neoplasms, and lymphomas, such as Hodgkin's disease
    - Metabolic disorders, such as Gaucher disease and Niemann-Pick disease
    - Pressure on the veins in the spleen or liver or a blood clot in these veins
    - Autoimmune conditions, such as lupus or sarcoidosis
  • “Splenomegaly is a common finding in multiple diseases; however, massive enlargement of the spleen is seen in few conditions. Most authors define massive splenomegaly when the spleen reaches the iliac crest, crosses the midline or weights more than 1500 g. The most common aetiologies of massive splenomegaly include haematological disorders (chronic myeloid leukamia, agnogenic myeloid metaplasia, polycythaemia vera, essential thrombocythaemia, indolent lymphomas, hairy cell leukaemia, β-thalassaemia major), infectious diseases (visceral leishmaniasis, malaria) and infiltrative conditions (Gaucher disease).”
    Massive splenomegaly.  
    Paz-Y-Mar HL, Gonzalez-Estrada A, Alraies MC.  
    BMJ Case Rep. 2013 Jul 29;2013:bcr2013200515. 

Privacy Policy

Copyright © 2022 The Johns Hopkins University, The Johns Hopkins Hospital, and The Johns Hopkins Health System Corporation. All rights reserved.
CTisus CT Scanning CTisus CT Scanning CTisus CT Scanning CTisus CT Scanning CTisus CT Scanning CTisus CT Scanning CTisus CT Scanning CTisus CT Scanning CTisus CT Scanning CTisus CT Scanning