Imaging Pearls ❯ January 2025
-- OR -- |
|
3D and Workflow
- ”Cinematic rendering (CR) is an innovative imaging technique that has emerged as a powerful tool in forensic radiology, offering enhanced visualization capabilities for the analysis of skeletal trauma. This article explores the application of CR in the setting of forensic imaging in skeletal injury and its impact on the field of skeletal trauma analysis. The study discusses the advantages of CR over traditional imaging methods and presents a comprehensive overview of the techniques, materials, and results associated with its application. The results indicate that CR has the potential to revolutionize forensic imaging, providing forensic experts with a highly accurate and detailed depiction of skeletal trauma for improved forensic analysis.”
3D CT Cinematic Rendering: Transforming Forensic Imaging with Enhanced Visualization for Skeletal Trauma Analysis.
Wallner-Essl WM, Pfaff JAR, Grimm J.
Int J Forens Sci Res. 2024; 1(1): 1-5. - “Despite its advantages, CR has limitations. Computational complexity may hinder real-time visualization, and accuracy in representing structures can be imperfect due to factors like noise and limitations in resolution. Interpretation could be subjective, impacting standardization. Accessibility might be limited due to specialized hardware and software requirements. Ongoing research aims to address these challenges, potentially leading to broader adoption of CR in clinical practice.”
3D CT Cinematic Rendering: Transforming Forensic Imaging with Enhanced Visualization for Skeletal Trauma Analysis.
Wallner-Essl WM, Pfaff JAR, Grimm J.
Int J Forens Sci Res. 2024; 1(1): 1-5. - “CT cinematic rendering is a relatively new technique that leverages advanced algorithms and computational power to create highly realistic visualizations from CT scan data. By simulating the interaction of light with tissues, cinematic rendering produces visually immersive images that closely resemble real-world appearances. It captures fine details such as surface textures, shading, and subtle changes in tissue density, resulting in lifelike renderings that aid in the understanding and interpretation of anatomical structures. CT cinematic rendering provides enhanced depth perception, allowing for interactive exploration of the scanned anatomy from multiple angles and perspectives.”
3D CT Cinematic Rendering: Transforming Forensic Imaging with Enhanced Visualization for Skeletal Trauma Analysis.
Wallner-Essl WM, Pfaff JAR, Grimm J.
Int J Forens Sci Res. 2024; 1(1): 1-5.
- “Generative artificial intelligence (AI), specifically the large language models (LLMs) that underlie impressive new applications such as ChatGPT, are already fundamentally changing medicine. Unlike more traditional AI systems that produce simple outputs such as a number (say, the predicted length of stay for a patient in the hospital) or a category (say, “malignant” or “benign” for a radiologic system), “generative AI” refers broadly to systems whose outputs take the form of more unstructured media objects, such as images and documents. Under the hood, many of these systems are actually built by executing models that serve a more classical purpose. Generative text models, for example, generate whole documents by iteratively predicting “what word comes next.” But the ability to produce a whole document with desired properties unlocks a host of exciting applications.”
Improving Efficiencies While Also Delivering Better Health Care Outcomes: A Role for Large Language Models.
Rao SK, Fishman EK, Rizk RC, Chu LC, Rowe SP.
J Am Coll Radiol. 2024 Dec;21(12):1913-1915. - “In health care, generative AI can assist, augment, and even automate workflows. Our industry’s challenge will be to apply the correct level of oversight, even regulatory, depending on the aforementioned objective. One way to visualize and differentiate these use cases is with a simple 2*s graph plotting the volume of decisions on the y axis against the potential consequences for inaccurate decisions on the x axis. In general, the quadrants for which there are low consequences for factual inaccuracies would be amenable to automation, whereas whenever there are high consequences, we should be looking for methods in which the LLM assists us (high volume) or augments our abilities (low volume).”
Improving Efficiencies While Also Delivering Better Health Care Outcomes: A Role for Large Language Models.
Rao SK, Fishman EK, Rizk RC, Chu LC, Rowe SP.
J Am Coll Radiol. 2024 Dec;21(12):1913-1915.
Improving Efficiencies While Also Delivering Better Health Care Outcomes: A Role for Large Language Models.
Rao SK, Fishman EK, Rizk RC, Chu LC, Rowe SP.
J Am Coll Radiol. 2024 Dec;21(12):1913-1915.- “The arrival of LLMs that can provide real-time assistance to physicians may allow a remarkable increase in their bandwidth, regardless of specialty. In radiology, leveraging these emerging technologies will potentially allow more scans to be read without adding burden or stress to the interpreting radiologist. We would be in the “high consequences for factual inaccuracies and high volume of decisions” quadrant of Figure 1, where the assistance of an LLM would be its key feature.”
Improving Efficiencies While Also Delivering Better Health Care Outcomes: A Role for Large Language Models.
Rao SK, Fishman EK, Rizk RC, Chu LC, Rowe SP.
J Am Coll Radiol. 2024 Dec;21(12):1913-1915. - “Other advantages coming with LLMs include their ability to transcend languages. For example, a Spanish-speaking patient could access a translation of a CT scan report that was generated by an LLM from the original radiologist’s read. Similarly, lay translations of CT reports may become a common tool for patient communication. Last, LLMs can learn to pick up on personal characteristics of patients, such as their preferred pronouns, which may create a moreinclusive environment that improves patients’ desire to follow-up and remain plugged into the health care system.”
Improving Efficiencies While Also Delivering Better Health Care Outcomes: A Role for Large Language Models.
Rao SK, Fishman EK, Rizk RC, Chu LC, Rowe SP.
J Am Coll Radiol. 2024 Dec;21(12):1913-1915.
Chest
- Among 10,150 participants, 189 died from GI cancers; mean age 75, mostly male smokers. Pancreatic cancer (41.8%) led, followed by esophageal (17.5%) and colon cancer (16.9%). Median time between baseline LDCT and death was 116 months (9.7 years). 82/189 (43.4%) participants died within 5 years of their last LDCT screening, with pancreatic cancer again prominent (45.1%). In 79 pancreatic cancer deaths, 17.7% occurred within 24 months post-LDCT. A re-review identified previously undetected pancreatic findings, with 4 out of 14 participants (28.6%) showing abnormalities. This underscores the potential of lung cancer screening programs to provide insights beyond lung health. This study of over 10,000 participants in a lung cancer screening program reveals that they are at risk for GI cancer deaths, particularly pancreatic cancer. Re-reviews of LDCT scans revealed previously undocumented pancreatic findings in a third of participants who died from pancreatic cancer, underscoring the need to identify, document, and follow up on these findings.
GI cancer mortality in participants in low dose CT screening for lung cancer with a focus on pancreatic cancer
Louis Gros, Rowena Yip, Yeqing Zhu, et al.
Scientific Reports | (2024) 14:29851 - A re-review identified previously undetected pancreatic findings, with 4 out of 14 participants (28.6%) showing abnormalities. This underscores the potential of lung cancer screening programs to provide insights beyond lung health. This study of over 10,000 participants in a lung cancer screening program reveals that they are at risk for GI cancer deaths, particularly pancreatic cancer. Re-reviews of LDCT scans revealed previously undocumented pancreatic findings in a third of participants who died from pancreatic cancer, underscoring the need to identify, document, and follow up on these findings.
GI cancer mortality in participants in low dose CT screening for lung cancer with a focus on pancreatic cancer
Louis Gros, Rowena Yip, Yeqing Zhu, et al.
Scientific Reports | (2024) 14:29851 - “On re-review of the baseline LDCTs for these 14 participants (median time 31.5 months, IQR 20–75, before death), 4 participants (28.6%) (compared to 0/14 in the original report, p = 0.098) were found to have pancreatic lesions: one with calcifications, two with atrophy, and one with both calcifications and atrophy. Among them, 3/4 had stable pancreatic findings on the last LDCT (median 26 months later, IQR 14-37.5), while one showed worsening atrophy.”
GI cancer mortality in participants in low dose CT screening for lung cancer with a focus on pancreatic cancer
Louis Gros, Rowena Yip, Yeqing Zhu, et al.
Scientific Reports | (2024) 14:29851 - “This underscores the need to follow a well-defined protocol for detecting and interpreting pancreatic findings, along with providing appropriate follow-up recommendations, especially for participants with a significant smoking history and diabetes; associated with an increased risk of pancreatic cancer41. The retrospective nature of this study, despite the prospective data collection, presents an inherent limitation. Relying on mortality data may introduce a bias, especially for pancreatic cancer, which, while relatively uncommon, is exceptionally deadly. This bias could lead to a distortion in the apparent frequency of pancreatic cancer compared to other cancers within our cohort. The entire pancreas may not be fully visualized in LDCT scans performed for lung cancer screening. Furthermore, image quality and soft tissue resolution may be affected by the use of LDCT. However, our study demonstrates that pancreatic findings can still be detected using LDCT. ”
GI cancer mortality in participant in low dose CT screening for lung cancer with a focus on pancreatic cancer
Louis Gros, Rowena Yip, Yeqing Zhu, et al.
Scientific Reports | (2024) 14:29851
Colon
- ”Active bleeding is a clinical emergency that often requires swift action driven by efficient communication. Extravasation of intravenous (IV) contrast on computed tomography (CT) is a hallmark of active hemorrhage. This can be seen on exams performed for a variety of indications and can occur anywhere in the body. As both traumatic and non-traumatic etiologies of significant blood loss are clinical emergencies, exams demonstrating active bleeding are often performed in emergency departments and read by emergency radiologists. Prompt communication of these findings to the appropriate emergency medicine and surgical providers is crucial. Although many types of active hemorrhage can be managed by interventional radiology techniques, endoscopic and surgical management or clinical observation may be appropriate in certain cases. To facilitate optimal care, it is important for emergency radiologists to understand the scope of indications for embolization of bleeding by interventional radiologists (IR) and when an IR consultation is warranted. Similarly, timely comprehensive diagnostic radiology reporting including pertinent positive and negative findings tailored for IR colleagues can expedite the appropriate intervention.”
Clinical management of active bleeding: what the emergency radiologist needs to know
Ryan T. Whitesell · Cory R. Nordman · Sean K. Johnston · Douglas H. Sheafor
Emergency Radiology (2024) 31:903–918 - ”It is estimated that hemorrhage results in more than 60,000 deaths each year in the United States, and roughly 1.9 million deaths each year worldwide. Etiologies of hemorrhage requiring resuscitation via massive transfusion protocols are myriad, with trauma and perioperative bleeding representing the greatest proportions, though causes include obstetric, gastrointestinal, and aneurysmal bleeding, among others. Hemorrhagic shock has been studied extensively in the setting of trauma and is a leading source of both mortality and morbidity for survivors. ”
Clinical management of active bleeding: what the emergency radiologist needs to know
Ryan T. Whitesell · Cory R. Nordman · Sean K. Johnston · Douglas H. Sheafor
Emergency Radiology (2024) 31:903–918 - “The appearance of active bleeding on CT is well known. Active hemorrhage is denoted by the extravasation of intravascular contrast, which is seen at CT as a globular or linear focus of contrast outside of the vessels that increases in size and density on delayed imaging. CT is highly sensitive for the detection of contrast extravasation and can demonstrate bleeding below a rate of 0.4 ml/min, which has led to increased use in emergent settings as a first line diagnostic exam for active bleeding.”
Clinical management of active bleeding: what the emergency radiologist needs to know
Ryan T. Whitesell · Cory R. Nordman · Sean K. Johnston · Douglas H. Sheafor
Emergency Radiology (2024) 31:903–918 - “A benefit of a dual-phase scan is that it allows for the diagnoses of arterial pseudoaneurysm and arteriovenous fistula and their differentiation from active hemorrhage. An arterial pseudoaneurysm is classically described as an enhancing focus which follows the density of the aortic blood pool on multiple phases of contrast, with its washout on venous phase imaging helping to distinguish it from active bleeding, which can be difficult or impossible on a single-phase study. Additionally, a pseudoaneurysm typically has a well-defined, often rounded morphology, with active bleeding appearing more diffuse and amorphous .”
Clinical management of active bleeding: what the emergency radiologist needs to know
Ryan T. Whitesell · Cory R. Nordman · Sean K. Johnston · Douglas H. Sheafor
Emergency Radiology (2024) 31:903–918 - “CT angiography (CTA) is a sensitive and specific first line diagnostic test for the diagnosis of active bleeding throughout the gastrointestinal tract. Specificity and diagnostic yield are improved by protocols which include a non-contrast series and both arterial and portal venous contrast-enhanced series, though virtual non-contrast dual-energy data sets also improve accuracy. Transcatheter endovascular embolization is a safe, effective treatment for gastrointestinal tract hemorrhage and can be used as a primary therapy or as an alternative to surgery in patients who have failed conservative management or endoscopic intervention. Angiography can be performed emergently and requires no bowel preparation, which is key as inadequate bowel preparation is a common cause of non-diagnostic colonoscopy .”
Clinical management of active bleeding: what the emergency radiologist needs to know
Ryan T. Whitesell · Cory R. Nordman · Sean K. Johnston · Douglas H. Sheafor
Emergency Radiology (2024) 31:903–918 - “The treatment of aortic rupture varies, with open surgical and endovascular aortic repair (EVAR) techniques remaining in use. EVAR has been shown to be superior to surgical management for AAA repair in patients with significant cardiopulmonary and renal comorbidities and provides a survival benefit for patients who are otherwise not candidates for surgical repair. While technological advancements continue to expand the pool of patients for whom an endovascular repair can be offered, thoracic aortic aneurysms proximal to or juxtaposed to the left subclavian artery, and abdominal aortic aneurysms with short or highly angulated necks (the neck being defined as the distance between the lowest renal artery and the proximal aneurysmal margin) may not be amenable to endovascular treatment.”
Clinical management of active bleeding: what the emergency radiologist needs to know
Ryan T. Whitesell · Cory R. Nordman · Sean K. Johnston · Douglas H. Sheafor
Emergency Radiology (2024) 31:903–918 - “Active bleeding as diagnosed by CT is a clinical emergency that requires swift action driven by efficient communication. Emergency radiologists are central to this process and must provide guidance to emergency medicine and surgical providers regarding the role interventional radiology should play in the management of these critically ill patients. Indications for IR involvement are broad and include trauma to the solid organs and mesentery, intraluminal GI hemorrhage, rectus sheath hematomas, tumoral bleeding, and gynecological bleeding including postpartum hemorrhage. Bleeding conditions which are less likely to be managed by IR include venous bleeding, intramuscular bleeding, mesenteric and bowel hemorrhage in patients with surgically altered anatomy, and small organ hemorrhage such as lower genitourinary or penile bleeding, for which skilled surgical reconstruction will need to be performed in addition to hemostasis. Local and regional practice patterns may vary, however. Emergency radiologists should be familiar with the information our interventional radiology colleagues often need when consulted on these cases, such as surgical history, differentiation of arterial and venous bleeding, anatomic localization of bleeding to a culprit artery, and coagulation status so that we may facilitate expedient decision making and treatment.”
Clinical management of active bleeding: what the emergency radiologist needs to know
Ryan T. Whitesell · Cory R. Nordman · Sean K. Johnston · Douglas H. Sheafor
Emergency Radiology (2024) 31:903–918
Deep Learning
- “Artificial intelligence should be used as an additivetool to care for patients and to aid in achieving goals in the best interest of the patient’s care. AI may be capable of improving clinical outcomes, and reducing mundane and repetitive unimportant tasks; however, it cannot, and should not, be used to replace the human aspect of the doctor-patient relationship.”
Will artificial intelligence undermine the profession of medicine?
Richard L. Byyny, The Pharos/Autumn 2024 - “As corporate medicine and AI further tighten their grip on medical practice, it would be wise to keep in mindthe admonition that was generated by GPT-4, “For it is in the balance of wisdom and humility that we shall harness AI’s potential for the greater good, lest we become the architects of our own demise.”
Will artificial intelligence undermine the profession
Steven A. Wartman, MD, PhD, MACP; Peter Densen
The Pharos/Autumn 2024 - “We recommend that health systems, health plans, and physician groups review and, if deemed appropriate, adopt AI to augment clinical practice. “Low-hanging fruit” includes enhancement of the doctor–patient interaction, including capture of the recorded patient visit, prioritizing and analysis of test and imaging results, differential diagnosis, plan for therapy and discussion of alternatives, instructions for the patient and caregivers, appointment scheduling and other administrative functions, and responses to patient questions at optimal levels of literacy.”
To do no harm - and the most good - with AI in health care.
Goldberg CB, Adams L, Blumenthal D, et al.
Nat Med. 2024 Mar;30(3):623-627. - “Given such ongoing problems and recent technological leaps, adopting AIH where it could help is a matter of urgency. At a moment when the complexity of modern medicine has surpassed the capacity of the human mind, only AIH will be able to perform many tasks. AIH thus seems to offer unparalleled potential for further medical progress, including for precision medicine — the right therapy, for the right patient, at the right time. Thus, it is in the interest of the public and the medical profession to hasten its adoption, so long as it is used safely and made maximally accessible for all. It is also urgent to determine how AIH can best deliver tangible benefits, including how it can help improvehealth and save lives in ways that will not otherwise happen. The public should not only be aware of this quest but also participate in it.”
To do no harm - and the most good - with AI in health care.
Goldberg CB, Adams L, Blumenthal D, et al.
Nat Med. 2024 Mar;30(3):623-627.
- “Artificial intelligence (AI) and its recent increasing healthcare integration has created both new opportunities and challenges in the practice of radiology and medical imaging. Recent advancements in AI technology have allowed for more workplacenefficiency, higher diagnostic accuracy, and overall improvements in patient care. Limitations of AI such as data imbalances, the unclear nature of AI algorithms, and the challenges in detecting certain diseases make it difficult for its widespread adoption. This review article presents cases involving the use of AI models to diagnose intracranial hemorrhage, spinal fractures,and rib fractures, while discussing how certain factors like, type, location, size, presence of artifacts, calcification, and post-surgical changes, affect AI model performance and accuracy. While the use of artificial intelligence has the potential to improve the practice of emergency radiology, it is important to address its limitations to maximize its advantages while ensuring the safety of patients overall.”
Potential strength and weakness of artificial intelligence integration in emergency radiology: a review of diagnostic utilizations and applications in patient care optimization.
Fathi M, Eshraghi R, Behzad S, et al..
Emerg Radiol. 2024 Dec;31(6):887-901. - 1. The recent developments of AI technologies create significant potential for increasing efficiency in radiology, improving the diagnostic accuracy of radiologists using various imaging modalities, and most importantly, bettering overall patient care.
2. To encourage the use of AI in radiology, challenges of its use such as the unclear nature of AI algorithms, present data imbalances, and limitations in detecting specific diseases, must be further researched and addressed.
3. This review article highlights the need of understanding factors that affect AI model performance, such as type, location, size, artifacts, calcifications, and post-surgical changes, in order to efficiently and accurately diagnose conditions like intracranial hemorrhage, spinal fractures, and rib fractures in the context of emergency radiology.
Potential strength and weakness of artificial intelligence integration in emergency radiology: a review of diagnostic utilizations and applications in patient care optimization.
Fathi M, Eshraghi R, Behzad S, et al..
Emerg Radiol. 2024 Dec;31(6):887-901. - Question Is the use of artificial intelligence (AI) in radiology practice associated with radiologist burnout?
Findings In this cross-sectional study, the use of AI was associated with burnout among radiologists, exhibiting a dose-response association. This association was particularly pronounced in radiologists with high workload and those with low AI acceptance.
Meaning These findings suggest the need for harmonious integration of AI tools with radiologists to effectively mitigate burnout in radiology practice.
Artificial Intelligence and Radiologist Burnout
Hui Liu, et al.
JAMA Network Open. 2024;7(11):e2448714. doi:10.1001/jamanetworkopen.2024.48714 - OBJECTIVE To estimate the association between AI use in radiology and radiologist burnout.
DESIGN, SETTING, AND PARTICIPANTS This cross-sectional study conducted a questionnaire survey between May and October 2023, using the national quality control system of radiology in China. Participants included radiologists from 1143 hospitals. Radiologists reporting regular or consistent AI use were categorized as the AI group. Statistical analysis was performed from October 2023 to May 2024.
CONCLUSIONS AND RELEVANCE In this cross-sectional study of radiologist burnout, frequent AI use was associated with an increased risk of radiologist burnout, particularly among those with high workload or lower AI acceptance. Further longitudinal studies are needed to provide more evidence.
Artificial Intelligence and Radiologist Burnout
Hui Liu, et al.
JAMA Network Open. 2024;7(11):e2448714. doi:10.1001/jamanetworkopen.2024.48714 - “Burnout encompasses emotional exhaustion (EE), depersonalization (DP), and a diminished sense of personal accomplishment. Physician burnout has emerged as a global issue, primarily driven by work overload, conflicts between home and work life, and job dissatisfaction. A previous systematic review has linked physician burnout to career disengagement, high physician turnover, and reduced quality of patient care. Radiologists exhibit higher burnout rates compared with other medical specialists. In Germany, over 75% of radiologists have reported experiencing burnout, while approximately40%of their US counterparts report similar conditions. A recent analysis estimated that 83%of radiologists exhibit at least 1 symptom of burnout. Moreover, elevated burnout levels have been documented across various radiology subspecialties, including interventional, musculoskeletal, pediatric, and breast.”
Artificial Intelligence and Radiologist Burnout
Hui Liu, et al.
JAMA Network Open. 2024;7(11):e2448714. doi:10.1001/jamanetworkopen.2024.48714 - “To our knowledge, this study is the first to investigate the association between AI use and radiologist burnout using a large, nationwide cross-sectional sample. We found that AI use was associated with increased odds of burnout among radiologists, exhibiting a significant dose-response association. Moreover, joint exposure to AI use alongside either high workload or low AI acceptance was associated with an additional risk of burnout. These results underscore the need to reassess the role of AI technology in mitigating radiologist burnout. Balancing AI use with an appropriate radiology workforce and maintaining psychological acceptance of AI technology in clinical practice is essential.”
Artificial Intelligence and Radiologist Burnout
Hui Liu, et al.
JAMA Network Open. 2024;7(11):e2448714. doi:10.1001/jamanetworkopen.2024.48714 - ”Our results indicate that the association of AI use with burnout may be exacerbated by increasing workload. The integration of AI technology in hospitals could lead to higher consultation volumes and increase radiologists’ workload. Although data to substantiate this are limited, policymakers are considering increasing radiology capacity with AI to address rising care demands, particularly in tertiary hospitals. For radiologists, the inherently isolated and sedentary nature of their work contributes to higher burnout rates compared with other specialties. AI may further exacerbate these challenges by diminishing opportunities for peer collaboration and patient interaction, while fears of job displacement and uncertainties surrounding AI use heighten stress. Joint association analyses showed that the risk of burnout associated with AI use was particularly pronounced among radiologists with high workloads, highlighting the urgent need to explore effective coordination strategies between radiologists and AI.”
Artificial Intelligence and Radiologist Burnout
Hui Liu, et al.
JAMA Network Open. 2024;7(11):e2448714. doi:10.1001/jamanetworkopen.2024.48714 - “Radiologists, already in short supply, are overwhelmed by rapidly growing health care needs and medical imaging data. In China, the annual growth rate of medical imaging data are 7.5 times that of radiologists. Therefore, radiologists’ workload and burnout are receiving unprecedented attention. AI technology offers a potential solution to the shortage of radiologists. Policymakers and researchers are planning or have implemented AI strategies in radiology to address the supply demand imbalance while maintaining the same or a slowly growing radiology workforce. However, the excitement and expectations surrounding technological advances should not overshadow the challenges that remain before AI can be routinely applied in radiology practice. AI tools must provide clinical results that radiologists can understand and trust to truly reduce workload. Few AI technologies have been rigorously validated in randomized clinical trials.37 Furthermore, integrating AI tools into the radiology workflow should be a key research task.”
Artificial Intelligence and Radiologist Burnout
Hui Liu, et al.
JAMA Network Open. 2024;7(11):e2448714. doi:10.1001/jamanetworkopen.2024.48714 - “There has been an increase in the number of imaging studies performed worldwide over the past 2 decades. There has been a simultaneous increase in the number of artificial intelligence (AI) models approved by the Food and Drug Administration (FDA) in the United States, with over 75%of these models approved for use in radiology. AI has been used to assist with interpretative tasks (detection, diagnosis, prognosis) and noninterpretive tasks (creating reports, protocols, contacting ordering clinicians, scheduling) in radiology. It is reasonable to assume that AI would be a useful adjunct for radiologists, increase radiologist efficiency, and decrease radiologist burnout. However, some reports, including the report by Liu et al, suggest that this may not be true.”
Artificial Intelligence Impact on Burnout in Radiologists— Alleviation or Exacerbation?
Farid Ghareh Mohammadi, PhD; Ronnie Sebro
JAMA Network Open. 2024;7(11):e2448720. - Burnout is a syndrome caused by unmanaged chronic workplace stress, characterized by 3 main dimensions: (1) energy depletion or exhaustion, (2) increased mental detachment or negativity toward one’s job, and (3) a sense of ineffectiveness and lack of achievement. The burnout rate in radiologists is high.
Artificial Intelligence Impact on Burnout in Radiologists— Alleviation or Exacerbation?
Farid Ghareh Mohammadi, PhD; Ronnie Sebro
JAMA Network Open. 2024;7(11):e2448720. - “To examine the association between AI use and burnout, the authors used propensity score–based multivariable logistic regression. They assessed workload (working hours on image interpretation, the amount of image interpretation, device type, role in the reporting workflow, and hospital level) and categorized radiologists into 3 groups based on their scores: low (0-2), medium (3), and high (4-5), which assumes a linear relationship between scores. Personal and professional characteristics were gathered through a self-designed questionnaire while researchers evaluated radiologists based on psychological factors using the Gallup Q12 Employee Engagement scale, measuring perceived control, spiritual rewards, work values, organizational support, and coworker support. The authors examined the association between AI use and burnout, adjusting for personal and professional characteristics, workload score, AI acceptance, and psychological factors. AI use was treated as both categorical and continuous to show the dose-response association.”
Artificial Intelligence Impact on Burnout in Radiologists— Alleviation or Exacerbation?
Farid Ghareh Mohammadi, PhD; Ronnie Sebro
JAMA Network Open. 2024;7(11):e2448720. - “The use of AI was associated with higher odds of burnout among radiologists. This association exhibited a dose-response association, meaning that as AI use increased, so did the likelihood of experiencing burnout. While there was an association between AI use and burnout, this was a crosssectional study and thus it is unclear the temporal order and cause and effect. One assumption could be that AI use causes burnout; however, an alternative and equally plausible assumption is that radiologists with burnout are more likely to use AI, perhaps to decrease burnout. The findings by Liu et al indicate that higher levels of AI use may be associated with an increase in burnout among radiologists.”
Artificial Intelligence Impact on Burnout in Radiologists— Alleviation or Exacerbation?
Farid Ghareh Mohammadi, PhD; Ronnie Sebro
JAMA Network Open. 2024;7(11):e2448720. - “It is unclear whether the AI models evaluated in this study performed both interpretive and noninterpretive tasks. Human-machine interaction (HMI) refers to how humans and machines interact and communicate with each other. This article highlights that the health care community has not yet learned how to effectively work with AI to harness the power of AI to reduce burnout. The nuances of HMI are still in its infancy, and until we are more effective at HMI, AI will not be a panacea to reduce radiologist burnout.”
Artificial Intelligence Impact on Burnout in Radiologists— Alleviation or Exacerbation?
Farid Ghareh Mohammadi, PhD; Ronnie Sebro
JAMA Network Open. 2024;7(11):e2448720.
- This review article highlights the need of understanding factors that affect AI model performance, such as type, location, size, artifacts, calcifications, and post-surgical changes, in order to efficiently and accurately diagnose conditions like intracranial hemorrhage, spinal fractures, and rib fractures in the context of emergency radiology.
Potential strength and weakness of artificial intelligence integration in emergency radiology: a review of diagnostic utilizations and applications in patient care optimization.
Fathi M, Eshraghi R, Behzad S, et al..
Emerg Radiol. 2024 Dec;31(6):887-901. - “Intracranial Hemorrhage (ICH) is a common and serious medical condition that needs quick diagnosis as patients who are left unattended deteriorate rapidly within just a few hours. The gold standard imaging modality for this condition’s diagnosis is a CT scan without contrast. Due to the increase in imaging demands, a radiologist may be overwhelmed with many other emergent imaging ordered, delaying the diagnosis of cerebral hemorrhage on CT scans. Additionally, it is plausible that increases in planned CT scans within late-hour shifts may jeopardize the complete accuracy of the radiologists’ reports.”
Potential strength and weakness of artificial intelligence integration in emergency radiology: a review of diagnostic utilizations and applications in patient care optimization.
Fathi M, Eshraghi R, Behzad S, et al..
Emerg Radiol. 2024 Dec;31(6):887-901. - There is great promise and potential for the integration of artificial intelligence into modern clinical practice, especially in emergency situations. In this paper, we showcased various factors that may affect the performance of AI models used in diagnostic imaging of emergency pathology. It should be known that AI should be used as a diagnostic tool rather than as a complete replacement for skillful and experienced radiologists. As AI technologies have been increasingly introduced into the healthcare setting, it is critical for clinicians and radiologists to understand the process of how AI systems are developed and organized. This includes understanding the present strengths, weaknesses, and limitations of such models. By doing so, we can more readily integrate artificial intelligence into the clinical setting and reap the benefits of such technology in our daily practice. Ultimately, radiologists and AI working together has the potential to advance the field of radiology while significantly improving patient care and healthcare outcomes.
Potential strength and weakness of artificial intelligence integration in emergency radiology: a review of diagnostic utilizations and applications in patient care optimization.
Fathi M, Eshraghi R, Behzad S, et al..
Emerg Radiol. 2024 Dec;31(6):887-901. - In a study by Kundisch et al., the radiological reports using AIDOC, which is a commercially available software approved by the FDA for the detection of ICH, was compared to the reports of a neuroradiologist. The neuroradiologist was deemed the gold standard in this study. The reported acceptable sensitivity and specificity of AIDOC in identifying ICH was shown to be roughly over 90%. The study also showed that on call shifts accounted for 85% of missed ICHs from reading radiologists. With the increase of emergency head CTs performed at the ED during night shifts, it is sensible to find solutions to lower stress and errors during these times to avoid negative patient outcomes. However, AI models do have limitations: while radiologists can identify ICHs by using their practical knowledge and experience.”
Potential strength and weakness of artificial intelligence integration in emergency radiology: a review of diagnostic utilizations and applications in patient care optimization.
Fathi M, Eshraghi R, Behzad S, et al..
Emerg Radiol. 2024 Dec;31(6):887-901. - BACKGROUND. Retrospective studies evaluating artificial intelligence (AI) algorithms for intracranial hemorrhage (ICH) detection on noncontrast CT (NCCT) have shown promising results but lack prospective validation.
OBJECTIVE. The purpose of this article was to evaluate the impact on radiologists’ real-world aggregate performance for ICH detection and report turnaround times for ICH-positive examinations of a radiology department’s implementation of an AI triageand notification system for ICH detection on head NCCT examinations.
CONCLUSION. An AI triage system for ICH detection did not improve radiologists’ diagnostic performance or report turnaround times.
CLINICAL IMPACT. This large prospective real-world study does not support use of AI assistance for ICH detection.
Prospective Evaluation of Artificial Intelligence Triage of Intracranial Hemorrhage on Noncontrast Head CT Examinations.
Savage CH, Tanwar M, Elkassem AA, et al.
AJR Am J Roentgenol. 2024 Nov 27:1-13. - RESULTS. A total of 9954 examinations from 7371 patients (mean age, 54.8 Å} 19.8 [SD] years; 3773 women, 3598 men) were included. In phases 1 and 2, 19.8% (735/3716) and 21.9% (1368/6238) of examinations, respectively, were positive for ICH (p = .01). Radiologists without versus with AI showed no significant difference in accuracy (99.5% vs 99.2%), sensitivity (98.6% vs 98.9%), PPV (99.0% vs 97.5%), or NPV (99.7% vs 99.7%) (all p > .01); specificity was higher for radiologists without than with AI (99.8% vs 99.3%, respectively, p = .004). Mean report turnaround time for ICH-positive examinations was 147.1 minutes without AI versus 149.9 minutes with AI (p = .11).
Prospective Evaluation of Artificial Intelligence Triage of Intracranial Hemorrhage on Noncontrast Head CT Examinations.
Savage CH, Tanwar M, Elkassem AA, et al.
AJR Am J Roentgenol. 2024 Nov 27:1-13. - Key Finding
- In a prospective study of 7371 patients who underwent 9954 noncontrast head CT examinations, radiologists without versus with AI assistance showed no significant difference in accuracy for ICH detection (99.5% vs 99.2%) or in mean report turnaround time for ICH-positive examinations (147.1 vs 149.9 minutes). Importance
- A radiology department’s clinical implementation of a widely used AI triage system failed to improve radiologists’ accuracy for ICH detection on noncontrast head CT examinations.
Prospective Evaluation of Artificial Intelligence Triage of Intracranial Hemorrhage on Noncontrast Head CT Examinations.
Savage CH, Tanwar M, Elkassem AA, et al.
AJR Am J Roentgenol. 2024 Nov 27:1-13. - “In conclusion, use of a commercial AI triage tool did not improve radiologists’ real-world diagnostic performance for detecting ICH on head NCCT examinations or report process times for ICH-positive examinations. Additionally, radiologists alone had greater diagnostic performance than AI alone for ICH detection.Such findings challenge the intended benefits from implementation of an AI triage system.”
Prospective Evaluation of Artificial Intelligence Triage of Intracranial Hemorrhage on Noncontrast Head CT Examinations.
Savage CH, Tanwar M, Elkassem AA, et al.
AJR Am J Roentgenol. 2024 Nov 27:1-13.
GU Misc
- “Cross-sectional CT imaging depicts SVAs as uni- or bilateral gland enlargement with thick irregular enhancing wall, internal hypoattenuating regions and adjacent fat inflammatory changes. Imaging features of bladder and prostatic infection are frequently associated.”
Cross-sectional imaging of complicated urinary infections affecting the lower tract and male genital organs
Massimo Tonolini, Sonia Ippolito
Insights Imaging (2016) 7:689–711 - “In the current antibiotic era, seminal vesicle abscesses (SVAs) are even more uncommon than PAs, and are frequently associated with ABP or epididymo-orchitis. SVAs may present with haemospermia or unspecific symptoms of UTI. However, both PAs and SVAs are often insidious and clinically unsuspected; therefore, a high index of suspicion is recommended when interpreting CT studies with the usual risk factors.”
Cross-sectional imaging of complicated urinary infections affecting the lower tract and male genital organs
Massimo Tonolini, Sonia Ippolito
Insights Imaging (2016) 7:689–711 - “The computed tomographic (CT) findings in four cases of seminal vesicle abscess are presented. The predominant infectious organism in two cases was Escherichia coli, one case was probably caused by Mycobacterium tuberculosis, and another by atypical mycobacterium. The CT findings included unilateral (three cases) or bilateral involvement (one case), seminal vesicle enlargement with hypodense areas within the gland (three cases), adjacent perivesicle inflammation (three cases), and associated bladder wall thickening (three cases). Although the diagnosis of seminal vesicle abscess is often overlooked clinically, CT may help suggest the correct diagnosis early thereby helping to initiate therapy.”
Seminal vesicle abscesses: spectrum of computed tomographic findings.
Kang YS, Fishman EK, Kuhlman JE, Goldman SM.
Urol Radiol. 1989;11(3):182-5. - “Seminal vesicle abscesses can be associated with infection elsewhere in the genitourinary tract, such as prostatitis or epididymitis. Predisposing factors include diabetes, an indwelling catheter, and GU instrumentation. An isolated seminal vesicle abscess can also occur, typically when a preexisting seminal vesicle cyst becomes infected. Some cysts are congenital and sometimes occur in association with ipsilateral renal agenesis or ectopic insertion of a ureter. It is believed that cysts can also be acquired, for example, from an obstructed ejaculatory duct. Recently, another rare cause of seminal vesicle abscesses has been reported: a complication of vasectomy. The most common infecting organism appears to be E. coll. In our series, one case involved E. coli in a diabetic man, one a mixed bacterial infection in a patient with an obstructed and infected bladder diverticulum, one with presumed tuberculosis, and one with a possible bacterial or mycobacterial infection.”
Seminal vesicle abscesses: spectrum of computed tomographic findings.
Kang YS, Fishman EK, Kuhlman JE, Goldman SM.
Urol Radiol. 1989;11(3):182-5. - “The above combination of CT findings (i.e., the presence of an irregular low-density mass with extensive inflammation in the surrounding tissues) should lead to the diagnosis of a seminal vesicle abscess, especially in the proper clinical setting. With the correct diagnosis, therapeutic options can be fully explored. If there is improvement on antibiotic therapy, the patient can be followed with CT. In all three cases where there was follow-up CT, dramatic improvement was noted. On the other hand, if the patient is refractory to conservative therapy, then surgical treatment, such as percutaneous, transurethral, or open drainage can be performed, possibly guided by CT.”
Seminal vesicle abscesses: spectrum of computed tomographic findings.
Kang YS, Fishman EK, Kuhlman JE, Goldman SM.
Urol Radiol. 1989;11(3):182-5.
Musculoskeletal
- ”Cinematic rendering (CR) is an innovative imaging technique that has emerged as a powerful tool in forensic radiology, offering enhanced visualization capabilities for the analysis of skeletal trauma. This article explores the application of CR in the setting of forensic imaging in skeletal injury and its impact on the field of skeletal trauma analysis. The study discusses the advantages of CR over traditional imaging methods and presents a comprehensive overview of the techniques, materials, and results associated with its application. The results indicate that CR has the potential to revolutionize forensic imaging, providing forensic experts with a highly accurate and detailed depiction of skeletal trauma for improved forensic analysis.”
3D CT Cinematic Rendering: Transforming Forensic Imaging with Enhanced Visualization for Skeletal Trauma Analysis.
Wallner-Essl WM, Pfaff JAR, Grimm J.
Int J Forens Sci Res. 2024; 1(1): 1-5. - “Despite its advantages, CR has limitations. Computational complexity may hinder real-time visualization, and accuracy in representing structures can be imperfect due to factors like noise and limitations in resolution. Interpretation could be subjective, impacting standardization. Accessibility might be limited due to specialized hardware and software requirements. Ongoing research aims to address these challenges, potentially leading to broader adoption of CR in clinical practice.”
3D CT Cinematic Rendering: Transforming Forensic Imaging with Enhanced Visualization for Skeletal Trauma Analysis.
Wallner-Essl WM, Pfaff JAR, Grimm J.
Int J Forens Sci Res. 2024; 1(1): 1-5. - “CT cinematic rendering is a relatively new technique that leverages advanced algorithms and computational power to create highly realistic visualizations from CT scan data. By simulating the interaction of light with tissues, cinematic rendering produces visually immersive images that closely resemble real-world appearances. It captures fine details such as surface textures, shading, and subtle changes in tissue density, resulting in lifelike renderings that aid in the understanding and interpretation of anatomical structures. CT cinematic rendering provides enhanced depth perception, allowing for interactive exploration of the scanned anatomy from multiple angles and perspectives.”
3D CT Cinematic Rendering: Transforming Forensic Imaging with Enhanced Visualization for Skeletal Trauma Analysis.
Wallner-Essl WM, Pfaff JAR, Grimm J.
Int J Forens Sci Res. 2024; 1(1): 1-5.
Neuroradiology
- This review article highlights the need of understanding factors that affect AI model performance, such as type, location, size, artifacts, calcifications, and post-surgical changes, in order to efficiently and accurately diagnose conditions like intracranial hemorrhage, spinal fractures, and rib fractures in the context of emergency radiology.
Potential strength and weakness of artificial intelligence integration in emergency radiology: a review of diagnostic utilizations and applications in patient care optimization.
Fathi M, Eshraghi R, Behzad S, et al..
Emerg Radiol. 2024 Dec;31(6):887-901. - “Intracranial Hemorrhage (ICH) is a common and serious medical condition that needs quick diagnosis as patients who are left unattended deteriorate rapidly within just a few hours. The gold standard imaging modality for this condition’s diagnosis is a CT scan without contrast. Due to the increase in imaging demands, a radiologist may be overwhelmed with many other emergent imaging ordered, delaying the diagnosis of cerebral hemorrhage on CT scans. Additionally, it is plausible that increases in planned CT scans within late-hour shifts may jeopardize the complete accuracy of the radiologists’ reports.”
Potential strength and weakness of artificial intelligence integration in emergency radiology: a review of diagnostic utilizations and applications in patient care optimization.
Fathi M, Eshraghi R, Behzad S, et al..
Emerg Radiol. 2024 Dec;31(6):887-901. - In a study by Kundisch et al., the radiological reports using AIDOC, which is a commercially available software approved by the FDA for the detection of ICH, was compared to the reports of a neuroradiologist. The neuroradiologist was deemed the gold standard in this study. The reported acceptable sensitivity and specificity of AIDOC in identifying ICH was shown to be roughly over 90%. The study also showed that on call shifts accounted for 85% of missed ICHs from reading radiologists. With the increase of emergency head CTs performed at the ED during night shifts, it is sensible to find solutions to lower stress and errors during these times to avoid negative patient outcomes. However, AI models do have limitations: while radiologists can identify ICHs by using their practical knowledge and experience.”
Potential strength and weakness of artificial intelligence integration in emergency radiology: a review of diagnostic utilizations and applications in patient care optimization.
Fathi M, Eshraghi R, Behzad S, et al..
Emerg Radiol. 2024 Dec;31(6):887-901. - BACKGROUND. Retrospective studies evaluating artificial intelligence (AI) algorithms for intracranial hemorrhage (ICH) detection on noncontrast CT (NCCT) have shown promising results but lack prospective validation.
OBJECTIVE. The purpose of this article was to evaluate the impact on radiologists’ real-world aggregate performance for ICH detection and report turnaround times for ICH-positive examinations of a radiology department’s implementation of an AI triageand notification system for ICH detection on head NCCT examinations.
CONCLUSION. An AI triage system for ICH detection did not improve radiologists’ diagnostic performance or report turnaround times.
CLINICAL IMPACT. This large prospective real-world study does not support use of AI assistance for ICH detection.
Prospective Evaluation of Artificial Intelligence Triage of Intracranial Hemorrhage on Noncontrast Head CT Examinations.
Savage CH, Tanwar M, Elkassem AA, et al.
AJR Am J Roentgenol. 2024 Nov 27:1-13. - RESULTS. A total of 9954 examinations from 7371 patients (mean age, 54.8 Å} 19.8 [SD] years; 3773 women, 3598 men) were included. In phases 1 and 2, 19.8% (735/3716) and 21.9% (1368/6238) of examinations, respectively, were positive for ICH (p = .01). Radiologists without versus with AI showed no significant difference in accuracy (99.5% vs 99.2%), sensitivity (98.6% vs 98.9%), PPV (99.0% vs 97.5%), or NPV (99.7% vs 99.7%) (all p > .01); specificity was higher for radiologists without than with AI (99.8% vs 99.3%, respectively, p = .004). Mean report turnaround time for ICH-positive examinations was 147.1 minutes without AI versus 149.9 minutes with AI (p = .11).
Prospective Evaluation of Artificial Intelligence Triage of Intracranial Hemorrhage on Noncontrast Head CT Examinations.
Savage CH, Tanwar M, Elkassem AA, et al.
AJR Am J Roentgenol. 2024 Nov 27:1-13. - Key Finding
- In a prospective study of 7371 patients who underwent 9954 noncontrast head CT examinations, radiologists without versus with AI assistance showed no significant difference in accuracy for ICH detection (99.5% vs 99.2%) or in mean report turnaround time for ICH-positive examinations (147.1 vs 149.9 minutes). Importance
- A radiology department’s clinical implementation of a widely used AI triage system failed to improve radiologists’ accuracy for ICH detection on noncontrast head CT examinations.
Prospective Evaluation of Artificial Intelligence Triage of Intracranial Hemorrhage on Noncontrast Head CT Examinations.
Savage CH, Tanwar M, Elkassem AA, et al.
AJR Am J Roentgenol. 2024 Nov 27:1-13. - “In conclusion, use of a commercial AI triage tool did not improve radiologists’ real-world diagnostic performance for detecting ICH on head NCCT examinations or report process times for ICH-positive examinations. Additionally, radiologists alone had greater diagnostic performance than AI alone for ICH detection.Such findings challenge the intended benefits from implementation of an AI triage system.”
Prospective Evaluation of Artificial Intelligence Triage of Intracranial Hemorrhage on Noncontrast Head CT Examinations.
Savage CH, Tanwar M, Elkassem AA, et al.
AJR Am J Roentgenol. 2024 Nov 27:1-13.
OB GYN
- Ovarian Vein Thrombosis:Risk Factors
- pregnancy: most common risk factor
- oral contraceptives
- pelvic infection
- malignancy
- recent surgery
- Idiopathic (under 6%) - Ovarian Vein Thrombosis: Pearls
- in ~80-90% of cases, the right ovarian vein is involved, possibly due to retrograde flow in the left vein preventing stasis and ascending infection
- ~14% of cases can have bilateral involvement
- ~6% of cases involve the left ovarian vein only
- tubular structure with an enhancing wall and low-attenuation thrombus in the expected location of the ovarian vein
- Right ovarian vein drains into IVC and Left gonadal vein into the left renal vein - “Ovarian vein thrombosis (OVT) is a rare type of venous thromboembolism. The most common risk factors for OVT include pregnancy, oral contraceptives, malignancies, recent surgery, and pelvic infections; however, in 4 to 16% of cases, it can be classified as idiopathic. Most of the available information regards pregnancy-related OVT, which has been reported to complicate 0.01 to 0.18% of pregnancies and to peak around 2 to 6 days after delivery or miscarriage/abortion. The right ovarian vein is more frequently involved (70-80% of cases). Clinical features of OVT include abdominal pain and tenderness, fever, and gastrointestinal symptoms. The most typical finding is the presence of a palpable abdominal mass, although reported in only 46% of cases. OVT can be the cause of puerperal fever in approximately a third of women.”
Riva N, Calleja-Agius J.
Ovarian Vein Thrombosis: A Narrative Review.
Riva N, Calleja-Agius J. Hamostaseologie. 2021 Aug;41(4):257-266. doi: 10.1055/a-1306-4327. Epub 2020 Dec 21. PMID: 33348392. - The incidence of OVT during pregnancy has been studied, particularly in the postpartum period, which was found to occur in ~1/600 to 1/2000 pregnancies . In pregnancy-related OVTs, it has been found that it usually involves the right ovarian vein (70-−90%) followed by bilateral ovarian vein involvement (11–14%). The most likely explanations for this finding are that the longer right ovarian vein lacks competent valves, the effect of the gravid uterus, and the retrograde flow in the left ovarian vein prevents stasis and ascending infection, thus making the left-sided vein less vulnerable to thrombosis.
Clinical Characteristics and Management of Ovarian Vein Thrombosis: A Case Series.
Alsheef M, Abuzied Y, Alosaimi M, et al
Front. Cardiovasc. Med. 9:916920. doi: 10.3389/fcvm.2022.916920 - “Ovarian vein thrombosis (OVT) is an uncommon condition that occurs mainly in the peripartum period. Hyper-coagulable conditions have been reported to cause OVT outside the peripartum period. The clinical presentation is usually nonspecific pain, but it can be asymptomatic in patients with underlying malignancy. Imaging plays an important role in diagnosis. Ultrasound is the initial imaging modality, but it is operator-dependent and has limited sensitivity. Computed tomography (CT) is the most commonly used modality for diagnosis. CT can show the luminal filling defect within the thrombosed vein and assess the extension of the thrombosis. MRI can show the thrombosed vein as a filling defect on post-contrast images; also, diffusion-weighted images may help in the diagnosis. Complications include extension into the inferior vena cava or renal veins. Pulmonary embolism is the most serious complication. Treatment includes anticoagulation plus antibiotics. Early diagnosis is essential to prevent complications.”
El-Diasty MT, Noorelahi Y. Imaging Findings of Ovarian Vein Thrombosis.
El-Diasty MT, Noorelahi Y.
Cureus. 2023 Nov 11;15(11):e48672. doi: 10.7759/cureus.48672. PMID: 38024035; PMCID: PMC10640670.
Pancreas
- Among 10,150 participants, 189 died from GI cancers; mean age 75, mostly male smokers. Pancreatic cancer (41.8%) led, followed by esophageal (17.5%) and colon cancer (16.9%). Median time between baseline LDCT and death was 116 months (9.7 years). 82/189 (43.4%) participants died within 5 years of their last LDCT screening, with pancreatic cancer again prominent (45.1%). In 79 pancreatic cancer deaths, 17.7% occurred within 24 months post-LDCT. A re-review identified previously undetected pancreatic findings, with 4 out of 14 participants (28.6%) showing abnormalities. This underscores the potential of lung cancer screening programs to provide insights beyond lung health. This study of over 10,000 participants in a lung cancer screening program reveals that they are at risk for GI cancer deaths, particularly pancreatic cancer. Re-reviews of LDCT scans revealed previously undocumented pancreatic findings in a third of participants who died from pancreatic cancer, underscoring the need to identify, document, and follow up on these findings.
GI cancer mortality in participants in low dose CT screening for lung cancer with a focus on pancreatic cancer
Louis Gros, Rowena Yip, Yeqing Zhu, et al.
Scientific Reports | (2024) 14:29851 - A re-review identified previously undetected pancreatic findings, with 4 out of 14 participants (28.6%) showing abnormalities. This underscores the potential of lung cancer screening programs to provide insights beyond lung health. This study of over 10,000 participants in a lung cancer screening program reveals that they are at risk for GI cancer deaths, particularly pancreatic cancer. Re-reviews of LDCT scans revealed previously undocumented pancreatic findings in a third of participants who died from pancreatic cancer, underscoring the need to identify, document, and follow up on these findings.
GI cancer mortality in participants in low dose CT screening for lung cancer with a focus on pancreatic cancer
Louis Gros, Rowena Yip, Yeqing Zhu, et al.
Scientific Reports | (2024) 14:29851 - “On re-review of the baseline LDCTs for these 14 participants (median time 31.5 months, IQR 20–75, before death), 4 participants (28.6%) (compared to 0/14 in the original report, p = 0.098) were found to have pancreatic lesions: one with calcifications, two with atrophy, and one with both calcifications and atrophy. Among them, 3/4 had stable pancreatic findings on the last LDCT (median 26 months later, IQR 14-37.5), while one showed worsening atrophy.”
GI cancer mortality in participants in low dose CT screening for lung cancer with a focus on pancreatic cancer
Louis Gros, Rowena Yip, Yeqing Zhu, et al.
Scientific Reports | (2024) 14:29851 - “This underscores the need to follow a well-defined protocol for detecting and interpreting pancreatic findings, along with providing appropriate follow-up recommendations, especially for participants with a significant smoking history and diabetes; associated with an increased risk of pancreatic cancer41. The retrospective nature of this study, despite the prospective data collection, presents an inherent limitation. Relying on mortality data may introduce a bias, especially for pancreatic cancer, which, while relatively uncommon, is exceptionally deadly. This bias could lead to a distortion in the apparent frequency of pancreatic cancer compared to other cancers within our cohort. The entire pancreas may not be fully visualized in LDCT scans performed for lung cancer screening. Furthermore, image quality and soft tissue resolution may be affected by the use of LDCT. However, our study demonstrates that pancreatic findings can still be detected using LDCT. ”
GI cancer mortality in participant in low dose CT screening for lung cancer with a focus on pancreatic cancer
Louis Gros, Rowena Yip, Yeqing Zhu, et al.
Scientific Reports | (2024) 14:29851
Small Bowel
- ”Active bleeding is a clinical emergency that often requires swift action driven by efficient communication. Extravasation of intravenous (IV) contrast on computed tomography (CT) is a hallmark of active hemorrhage. This can be seen on exams performed for a variety of indications and can occur anywhere in the body. As both traumatic and non-traumatic etiologies of significant blood loss are clinical emergencies, exams demonstrating active bleeding are often performed in emergency departments and read by emergency radiologists. Prompt communication of these findings to the appropriate emergency medicine and surgical providers is crucial. Although many types of active hemorrhage can be managed by interventional radiology techniques, endoscopic and surgical management or clinical observation may be appropriate in certain cases. To facilitate optimal care, it is important for emergency radiologists to understand the scope of indications for embolization of bleeding by interventional radiologists (IR) and when an IR consultation is warranted. Similarly, timely comprehensive diagnostic radiology reporting including pertinent positive and negative findings tailored for IR colleagues can expedite the appropriate intervention.”
Clinical management of active bleeding: what the emergency radiologist needs to know
Ryan T. Whitesell · Cory R. Nordman · Sean K. Johnston · Douglas H. Sheafor
Emergency Radiology (2024) 31:903–918 - ”It is estimated that hemorrhage results in more than 60,000 deaths each year in the United States, and roughly 1.9 million deaths each year worldwide. Etiologies of hemorrhage requiring resuscitation via massive transfusion protocols are myriad, with trauma and perioperative bleeding representing the greatest proportions, though causes include obstetric, gastrointestinal, and aneurysmal bleeding, among others. Hemorrhagic shock has been studied extensively in the setting of trauma and is a leading source of both mortality and morbidity for survivors. ”
Clinical management of active bleeding: what the emergency radiologist needs to know
Ryan T. Whitesell · Cory R. Nordman · Sean K. Johnston · Douglas H. Sheafor
Emergency Radiology (2024) 31:903–918 - “The appearance of active bleeding on CT is well known. Active hemorrhage is denoted by the extravasation of intravascular contrast, which is seen at CT as a globular or linear focus of contrast outside of the vessels that increases in size and density on delayed imaging. CT is highly sensitive for the detection of contrast extravasation and can demonstrate bleeding below a rate of 0.4 ml/min, which has led to increased use in emergent settings as a first line diagnostic exam for active bleeding.”
Clinical management of active bleeding: what the emergency radiologist needs to know
Ryan T. Whitesell · Cory R. Nordman · Sean K. Johnston · Douglas H. Sheafor
Emergency Radiology (2024) 31:903–918 - “A benefit of a dual-phase scan is that it allows for the diagnoses of arterial pseudoaneurysm and arteriovenous fistula and their differentiation from active hemorrhage. An arterial pseudoaneurysm is classically described as an enhancing focus which follows the density of the aortic blood pool on multiple phases of contrast, with its washout on venous phase imaging helping to distinguish it from active bleeding, which can be difficult or impossible on a single-phase study. Additionally, a pseudoaneurysm typically has a well-defined, often rounded morphology, with active bleeding appearing more diffuse and amorphous .”
Clinical management of active bleeding: what the emergency radiologist needs to know
Ryan T. Whitesell · Cory R. Nordman · Sean K. Johnston · Douglas H. Sheafor
Emergency Radiology (2024) 31:903–918 - “CT angiography (CTA) is a sensitive and specific first line diagnostic test for the diagnosis of active bleeding throughout the gastrointestinal tract. Specificity and diagnostic yield are improved by protocols which include a non-contrast series and both arterial and portal venous contrast-enhanced series, though virtual non-contrast dual-energy data sets also improve accuracy. Transcatheter endovascular embolization is a safe, effective treatment for gastrointestinal tract hemorrhage and can be used as a primary therapy or as an alternative to surgery in patients who have failed conservative management or endoscopic intervention. Angiography can be performed emergently and requires no bowel preparation, which is key as inadequate bowel preparation is a common cause of non-diagnostic colonoscopy .”
Clinical management of active bleeding: what the emergency radiologist needs to know
Ryan T. Whitesell · Cory R. Nordman · Sean K. Johnston · Douglas H. Sheafor
Emergency Radiology (2024) 31:903–918 - “The treatment of aortic rupture varies, with open surgical and endovascular aortic repair (EVAR) techniques remaining in use. EVAR has been shown to be superior to surgical management for AAA repair in patients with significant cardiopulmonary and renal comorbidities and provides a survival benefit for patients who are otherwise not candidates for surgical repair. While technological advancements continue to expand the pool of patients for whom an endovascular repair can be offered, thoracic aortic aneurysms proximal to or juxtaposed to the left subclavian artery, and abdominal aortic aneurysms with short or highly angulated necks (the neck being defined as the distance between the lowest renal artery and the proximal aneurysmal margin) may not be amenable to endovascular treatment.”
Clinical management of active bleeding: what the emergency radiologist needs to know
Ryan T. Whitesell · Cory R. Nordman · Sean K. Johnston · Douglas H. Sheafor
Emergency Radiology (2024) 31:903–918 - “Active bleeding as diagnosed by CT is a clinical emergency that requires swift action driven by efficient communication. Emergency radiologists are central to this process and must provide guidance to emergency medicine and surgical providers regarding the role interventional radiology should play in the management of these critically ill patients. Indications for IR involvement are broad and include trauma to the solid organs and mesentery, intraluminal GI hemorrhage, rectus sheath hematomas, tumoral bleeding, and gynecological bleeding including postpartum hemorrhage. Bleeding conditions which are less likely to be managed by IR include venous bleeding, intramuscular bleeding, mesenteric and bowel hemorrhage in patients with surgically altered anatomy, and small organ hemorrhage such as lower genitourinary or penile bleeding, for which skilled surgical reconstruction will need to be performed in addition to hemostasis. Local and regional practice patterns may vary, however. Emergency radiologists should be familiar with the information our interventional radiology colleagues often need when consulted on these cases, such as surgical history, differentiation of arterial and venous bleeding, anatomic localization of bleeding to a culprit artery, and coagulation status so that we may facilitate expedient decision making and treatment.”
Clinical management of active bleeding: what the emergency radiologist needs to know
Ryan T. Whitesell · Cory R. Nordman · Sean K. Johnston · Douglas H. Sheafor
Emergency Radiology (2024) 31:903–918
Trauma
- “Artificial intelligence (AI) and its recent increasing healthcare integration has created both new opportunities and challenges in the practice of radiology and medical imaging. Recent advancements in AI technology have allowed for more workplacenefficiency, higher diagnostic accuracy, and overall improvements in patient care. Limitations of AI such as data imbalances, the unclear nature of AI algorithms, and the challenges in detecting certain diseases make it difficult for its widespread adoption. This review article presents cases involving the use of AI models to diagnose intracranial hemorrhage, spinal fractures,and rib fractures, while discussing how certain factors like, type, location, size, presence of artifacts, calcification, and post-surgical changes, affect AI model performance and accuracy. While the use of artificial intelligence has the potential to improve the practice of emergency radiology, it is important to address its limitations to maximize its advantages while ensuring the safety of patients overall.”
Potential strength and weakness of artificial intelligence integration in emergency radiology: a review of diagnostic utilizations and applications in patient care optimization.
Fathi M, Eshraghi R, Behzad S, et al..
Emerg Radiol. 2024 Dec;31(6):887-901. - 1. The recent developments of AI technologies create significant potential for increasing efficiency in radiology, improving the diagnostic accuracy of radiologists using various imaging modalities, and most importantly, bettering overall patient care.
2. To encourage the use of AI in radiology, challenges of its use such as the unclear nature of AI algorithms, present data imbalances, and limitations in detecting specific diseases, must be further researched and addressed.
3. This review article highlights the need of understanding factors that affect AI model performance, such as type, location, size, artifacts, calcifications, and post-surgical changes, in order to efficiently and accurately diagnose conditions like intracranial hemorrhage, spinal fractures, and rib fractures in the context of emergency radiology.
Potential strength and weakness of artificial intelligence integration in emergency radiology: a review of diagnostic utilizations and applications in patient care optimization.
Fathi M, Eshraghi R, Behzad S, et al..
Emerg Radiol. 2024 Dec;31(6):887-901. - This review article highlights the need of understanding factors that affect AI model performance, such as type, location, size, artifacts, calcifications, and post-surgical changes, in order to efficiently and accurately diagnose conditions like intracranial hemorrhage, spinal fractures, and rib fractures in the context of emergency radiology.
Potential strength and weakness of artificial intelligence integration in emergency radiology: a review of diagnostic utilizations and applications in patient care optimization.
Fathi M, Eshraghi R, Behzad S, et al..
Emerg Radiol. 2024 Dec;31(6):887-901. - “Intracranial Hemorrhage (ICH) is a common and serious medical condition that needs quick diagnosis as patients who are left unattended deteriorate rapidly within just a few hours. The gold standard imaging modality for this condition’s diagnosis is a CT scan without contrast. Due to the increase in imaging demands, a radiologist may be overwhelmed with many other emergent imaging ordered, delaying the diagnosis of cerebral hemorrhage on CT scans. Additionally, it is plausible that increases in planned CT scans within late-hour shifts may jeopardize the complete accuracy of the radiologists’ reports.”
Potential strength and weakness of artificial intelligence integration in emergency radiology: a review of diagnostic utilizations and applications in patient care optimization.
Fathi M, Eshraghi R, Behzad S, et al..
Emerg Radiol. 2024 Dec;31(6):887-901. - In a study by Kundisch et al., the radiological reports using AIDOC, which is a commercially available software approved by the FDA for the detection of ICH, was compared to the reports of a neuroradiologist. The neuroradiologist was deemed the gold standard in this study. The reported acceptable sensitivity and specificity of AIDOC in identifying ICH was shown to be roughly over 90%. The study also showed that on call shifts accounted for 85% of missed ICHs from reading radiologists. With the increase of emergency head CTs performed at the ED during night shifts, it is sensible to find solutions to lower stress and errors during these times to avoid negative patient outcomes. However, AI models do have limitations: while radiologists can identify ICHs by using their practical knowledge and experience,
Potential strength and weakness of artificial intelligence integration in emergency radiology: a review of diagnostic utilizations and applications in patient care optimization.
Fathi M, Eshraghi R, Behzad S, et al..
Emerg Radiol. 2024 Dec;31(6):887-901. - There is great promise and potential for the integration of artificial intelligence into modern clinical practice, especially in emergency situations. In this paper, we showcased various factors that may affect the performance of AI models used in diagnostic imaging of emergency pathology. It should be known that AI should be used as a diagnostic tool rather than as a complete replacement for skillful and experienced radiologists. As AI technologies have been increasingly introduced into the healthcare setting, it is critical for clinicians and radiologists to understand the process of how AI systems are developed and organized. This includes understanding the present strengths, weaknesses, and limitations of such models. By doing so, we can more readily integrate artificial intelligence into the clinical setting and reap the benefits of such technology in our daily practice. Ultimately, radiologists and AI working together has the potential to advance the field of radiology while significantly improving patient care and healthcare outcomes.
Potential strength and weakness of artificial intelligence integration in emergency radiology: a review of diagnostic utilizations and applications in patient care optimization.
Fathi M, Eshraghi R, Behzad S, et al..
Emerg Radiol. 2024 Dec;31(6):887-901. - ”Cinematic rendering (CR) is an innovative imaging technique that has emerged as a powerful tool in forensic radiology, offering enhanced visualization capabilities for the analysis of skeletal trauma. This article explores the application of CR in the setting of forensic imaging in skeletal injury and its impact on the field of skeletal trauma analysis. The study discusses the advantages of CR over traditional imaging methods and presents a comprehensive overview of the techniques, materials, and results associated with its application. The results indicate that CR has the potential to revolutionize forensic imaging, providing forensic experts with a highly accurate and detailed depiction of skeletal trauma for improved forensic analysis.”
3D CT Cinematic Rendering: Transforming Forensic Imaging with Enhanced Visualization for Skeletal Trauma Analysis.
Wallner-Essl WM, Pfaff JAR, Grimm J.
Int J Forens Sci Res. 2024; 1(1): 1-5. - “Despite its advantages, CR has limitations. Computational complexity may hinder real-time visualization, and accuracy in representing structures can be imperfect due to factors like noise and limitations in resolution. Interpretation could be subjective, impacting standardization. Accessibility might be limited due to specialized hardware and software requirements. Ongoing research aims to address these challenges, potentially leading to broader adoption of CR in clinical practice.”
3D CT Cinematic Rendering: Transforming Forensic Imaging with Enhanced Visualization for Skeletal Trauma Analysis.
Wallner-Essl WM, Pfaff JAR, Grimm J.
Int J Forens Sci Res. 2024; 1(1): 1-5. - “CT cinematic rendering is a relatively new technique that leverages advanced algorithms and computational power to create highly realistic visualizations from CT scan data. By simulating the interaction of light with tissues, cinematic rendering produces visually immersive images that closely resemble real-world appearances. It captures fine details such as surface textures, shading, and subtle changes in tissue density, resulting in lifelike renderings that aid in the understanding and interpretation of anatomical structures. CT cinematic rendering provides enhanced depth perception, allowing for interactive exploration of the scanned anatomy from multiple angles and perspectives.”
3D CT Cinematic Rendering: Transforming Forensic Imaging with Enhanced Visualization for Skeletal Trauma Analysis.
Wallner-Essl WM, Pfaff JAR, Grimm J.
Int J Forens Sci Res. 2024; 1(1): 1-5.
Vascular
- Ovarian Vein Thrombosis:Risk Factors
- pregnancy: most common risk factor
- oral contraceptives
- pelvic infection
- malignancy
- recent surgery
- Idiopathic (under 6%) - Ovarian Vein Thrombosis: Pearls
- in ~80-90% of cases, the right ovarian vein is involved, possibly due to retrograde flow in the left vein preventing stasis and ascending infection
- ~14% of cases can have bilateral involvement
- ~6% of cases involve the left ovarian vein only
- tubular structure with an enhancing wall and low-attenuation thrombus in the expected location of the ovarian vein
- Right ovarian vein drains into IVC and Left gonadal vein into the left renal vein - “Ovarian vein thrombosis (OVT) is a rare type of venous thromboembolism. The most common risk factors for OVT include pregnancy, oral contraceptives, malignancies, recent surgery, and pelvic infections; however, in 4 to 16% of cases, it can be classified as idiopathic. Most of the available information regards pregnancy-related OVT, which has been reported to complicate 0.01 to 0.18% of pregnancies and to peak around 2 to 6 days after delivery or miscarriage/abortion. The right ovarian vein is more frequently involved (70-80% of cases). Clinical features of OVT include abdominal pain and tenderness, fever, and gastrointestinal symptoms. The most typical finding is the presence of a palpable abdominal mass, although reported in only 46% of cases. OVT can be the cause of puerperal fever in approximately a third of women.”
Riva N, Calleja-Agius J.
Ovarian Vein Thrombosis: A Narrative Review.
Riva N, Calleja-Agius J. Hamostaseologie. 2021 Aug;41(4):257-266. doi: 10.1055/a-1306-4327. Epub 2020 Dec 21. PMID: 33348392. - The incidence of OVT during pregnancy has been studied, particularly in the postpartum period, which was found to occur in ~1/600 to 1/2000 pregnancies . In pregnancy-related OVTs, it has been found that it usually involves the right ovarian vein (70-−90%) followed by bilateral ovarian vein involvement (11–14%). The most likely explanations for this finding are that the longer right ovarian vein lacks competent valves, the effect of the gravid uterus, and the retrograde flow in the left ovarian vein prevents stasis and ascending infection, thus making the left-sided vein less vulnerable to thrombosis.
Clinical Characteristics and Management of Ovarian Vein Thrombosis: A Case Series.
Alsheef M, Abuzied Y, Alosaimi M, et al
Front. Cardiovasc. Med. 9:916920. doi: 10.3389/fcvm.2022.916920 - “Ovarian vein thrombosis (OVT) is an uncommon condition that occurs mainly in the peripartum period. Hyper-coagulable conditions have been reported to cause OVT outside the peripartum period. The clinical presentation is usually nonspecific pain, but it can be asymptomatic in patients with underlying malignancy. Imaging plays an important role in diagnosis. Ultrasound is the initial imaging modality, but it is operator-dependent and has limited sensitivity. Computed tomography (CT) is the most commonly used modality for diagnosis. CT can show the luminal filling defect within the thrombosed vein and assess the extension of the thrombosis. MRI can show the thrombosed vein as a filling defect on post-contrast images; also, diffusion-weighted images may help in the diagnosis. Complications include extension into the inferior vena cava or renal veins. Pulmonary embolism is the most serious complication. Treatment includes anticoagulation plus antibiotics. Early diagnosis is essential to prevent complications.”
El-Diasty MT, Noorelahi Y. Imaging Findings of Ovarian Vein Thrombosis.
El-Diasty MT, Noorelahi Y.
Cureus. 2023 Nov 11;15(11):e48672. doi: 10.7759/cureus.48672. PMID: 38024035; PMCID: PMC10640670.