Current problems in diagnostic radiology最新文献

Gallbladder pathologies caused by gallstones are commonly encountered in clinical practice, making accurate diagnosis critical for effective patient management. Radiologists play a key role in differentiating these conditions through imaging interpretation, ensuring that appropriate treatment is initiated. The imaging features of gallstone associated diseases are classified into various categories, such as inflammatory conditions, benign lesions, malignant tumors, and associated complications. A comprehensive understanding of these categories and their radiologic manifestations is essential for accurate diagnosis and management of gallbladder pathology. By integrating clinical knowledge with radiologic findings, clinicians and radiologists will be equipped with practical tools to identify and distinguish between different gallstone causing conditions.

Unless radiologist performance assessment is sufficiently deep, comprehensive, and balanced, it may tend to omit, obscure, or distort key aspects of the important contributions that radiologists make, with adverse consequences for employers, radiologists themselves, and above all, the patients they serve. Here we present a model of performance assessment that includes eight key dimensions, which can be tailored as appropriate to the needs of particular programs and radiologists.

Pursuing medical careers like radiology is challenging even for those with high levels of commitment, discipline, and resilience. Many rely on the guidance and support from mentors whose experiences serve as the roadmap for new generations. Unfortunately, finding a mentor can be difficult in certain parts of the world or when physicians decide to live and practice medicine outside their country of origin. Within the United States, medical education in the United States is very competitive given the high demand of highly qualified aspirants and the lack of enough training positions to accept them all. Having good mentorship not only can help students enhance the skills required to succeed within their fields of interest during the residency and fellowship application processes, but it can also provide counseling as they navigate training and, ultimately, transition to the workplace. "Mentors without Borders" is a program founded by a radiologist to provide free mentorship to those interested in pursuing medical education and training to pursue radiology and other medical careers in and out of the United States. Its primary focus is on strengthening skills needed for academic writing and publication of scientific articles in radiology. This initiative has already benefited several students and physicians from all over the world and is aiming to become a fully structured program with a larger outreach.

Background: Radiologists increasingly use artificial intelligence (AI) to enhance diagnostic accuracy and optimize workflows. However, many lack the technical skills to effectively apply machine learning (ML) and deep learning (DL) algorithms, limiting the accessibility of these methods to radiology researchers who could otherwise benefit from them. Large language models (LLMs), such as GPT-4o, may serve as virtual advisors, offering tailored algorithm recommendations for specific research needs. This study evaluates GPT-4o's effectiveness as a recommender system to enhance radiologists' understanding and implementation of AI in research.

Intervention: GPT-4o was used to recommend ML and DL algorithms based on specific details provided by researchers, including dataset characteristics, modality types, data sizes, and research objectives. The model acted as a virtual advisor, guiding researchers in selecting the most appropriate models for their studies.

Methods: The study systematically evaluated GPT-4o's recommendations for clarity, task alignment, model diversity, and baseline selection. Responses were graded to assess the model's ability to meet the needs of radiology researchers.

Results: GPT-4o effectively recommended appropriate ML and DL algorithms for various radiology tasks, including segmentation, classification, and regression in medical imaging. The model suggested a diverse range of established and innovative algorithms, such as U-Net, Random Forest, Attention U-Net, and EfficientNet, aligning well with accepted practices.

Conclusion: GPT-4o shows promise as a valuable tool for radiologists and early career researchers by providing clear and relevant AI and ML algorithm recommendations. Its ability to bridge the knowledge gap in AI implementation could democratize access to advanced technologies, fostering innovation and improving radiology research quality. Further studies should explore integrating LLMs into routine workflows and their role in ongoing professional development.

Purpose: This study aimed to evaluate the utility of tumor mutational burden (TMB) as a marker for radiologic response to immune checkpoint inhibitor (ICI) therapy at a single tertiary cancer center.

Materials and methods: In this retrospective study, out of 1044 patients treated with ICIs between January 2010 and November 2018, 75 patients (38 males and 37 females) with a mean age of 62 (range 22-87) years, who had information about TMB and adequate imaging, were included. Imaging response was determined according to iRECIST criteria. Predictors of objective response were analysed using non-parametric tests, and progression-free survival and overall survival were analysed using log-rank test.

Results: Median TMB was 7.2 mutations/mb [interquartile range: 4-13.5]. The objective radiologic response rate according to iRECIST was 26.7 % (20 patients) and the median time to best response was 61 days [IQR: 47-88 days]. Median TMB in responders (12.5 [IQR: 5-18] muts/mb) was significantly higher than in non-responders (6 [IQR: 3-12] muts/mb) (p = 0.0293). Median TMB was higher in responders in the subgroup of patients treated with Nivolumab (20 vs 4 muts/mb, P = .0043), but not significantly in those treated with Pembrolizumab (9 vs 6 muts/mb, P = .211). There was no difference in PFS (p = 0.37, Log-Rank) or OS (p = 0.053, Log-Rank) between TMB low and high groups.

Conclusion: Higher TMB was associated with objective response to ICI, however, TMB was an imperfect biomarker for PFS and OS in our study.

Interpreting imaging examinations of the pancreas can be a challenge. Several different entities can mimic or mask pancreatic neoplasms, including normal anatomic variants, non-pancreatic lesions, and both acute and chronic pancreatitis. It is important to distinguish these entities from pancreatic neoplasms, as the management and prognosis of a pancreatic neoplasm, particularly adenocarcinoma, have considerable impact on patients. Normal pancreatic variants that mimic a focal lesion include focal fatty atrophy, annular pancreas, and ectopic pancreas. Extra-pancreatic lesions that can mimic a primary pancreatic neoplasm include vascular lesions, such as arteriovenous malformations and pseudoaneurysms, duodenal diverticula, and intra-pancreatic accessory spleen. Both acute and chronic pancreatitis can mimic or mask a pancreatic neoplasm and are also associated with pancreatic ductal adenocarcinoma. Awareness of these entities and their imaging features will enable the radiologist to narrow the differential diagnosis, provide recommendations that expedite diagnosis and avoid unnecessary work-up or delays in patient care.

The periarticular adipose tissues play a crucial role in knee biomechanics, yet they are often overlooked in daily radiology practice. As the primary mechanical shock absorbers of the knee, intra-articular fat pads reduce the friction between intra-articular structures during joint movement. They also contribute to inflammatory regulation, endocrine secretion, and pain detection. Periarticular fat pads are susceptible to a spectrum of traumatic, degenerative, inflammatory, and neoplastic changes. MRI enables radiologists to assess the anatomy of periarticular fat pads and their related pathologies to make accurate diagnoses and to guide appropriate management. The MRI presentation of these pathologies can be categorized into three groups: (a) signal change and thickening of synovial lining, (b) edema-like change in fat pads, and (c) mass-like lesions. While degeneration and impingement appear as high signal edema-like intensity on fluid-sensitive sequences, inflammatory or infectious synovitis, hemosiderin deposition, and lipoma arborescens can change the signal intensity of the synovial lining. A mass-like lesion arising from these structures could be a true neoplastic lesion, or a variety of non-neoplastic pathologies. A comprehensive understanding of adipose tissues and their pathologies is fundamental for accurate diagnosis and interpretation. In this review, we aim to provide an in-depth assessment of the anatomy and common pathologies of these adipose tissues.

The Anti-Kickback Statute was passed by Congress in the 1970s to reduce the overuse of government-reimbursed medical services. It attempts to eliminate fraud, abuse, and waste of medical services by outlawing the incentive of personal gain when referring patients for government-funded services. Although safe harbors were written into the law to maintain transactions beneficial to society, they require strict adherence. Anti-Kickback Statute violations are subject to the whistleblower provision of the False Claims Act, and violations can yield significant civil and criminal penalties.

Purpose: To assess the clinical utility of pelvic computed tomography angiography (CTA) in predicting the need for intervention following blunt traumatic pelvic vascular injury, independent of other trauma severity assessment metrics.

Materials and methods: This retrospective study was IRB approved and HIPAA compliant; informed consent was waived. Eligible patients presented with blunt abdominopelvic trauma and underwent triple-phase pelvic CTA on admission from 1/1/2006 - 8/31/2019. Of the 21,162 eligible patients, 350 met criteria (males 225, females 125, mean age 42 years, range 11-96 years). Vessels were evaluated for contrast extravasation, occlusion, narrowing/spasm, dissection, and pseudoaneurysm. Fisher's exact test was used to compare differences in outcome based on vascular injury on CTA.

Results: 74 of 350 (21%) patients demonstrated vascular injury on CTA. 65 had arterial extravasation, 12 had venous injury, 3 had thrombosis, 3 had pseudoaneurysm, 1 had dissection, and 16 had arterial narrowing/spasm. 42 of 65 (65%) patients with active arterial extravasation on pelvic CTA underwent conventional angiography, and 31 demonstrated active bleeding requiring intervention; 5 patients without extravasation underwent negative conventional angiographies. None of the 276 patients without active arterial extravasation received intervention, and all survived. Contrast extravasation on admission pelvic CTA significantly predicted the need for direct intervention and overall mortality (p<0.0001).

Conclusion: Pelvic CTA can be safely implemented in trauma imaging protocols to diagnose vascular injury and determine the need for subsequent intervention. Absence of contrast extravasation on CTA precludes the need for further intervention, independent of newer trauma severity assessment metrics.

Rationale and objectives: Ultrasound-guided breast biopsies are the most frequently performed imaging-guided breast procedures. During training, learners may lack exposure due to limited volume and sensitive anatomy. Current simulation training often involves the use of manufactured or homemade (chicken or turkey breast) phantoms. Virtual reality is an emerging technology, allowing learners to have flexibility in learning, real-life interactive experiences and measurable feedback. The purpose of this study is to assess the feasibility of a novel virtual reality breast biopsy simulation trainer.

Methods: This was a HIPAA-compliant, IRB-approved prospective feasibility study. The participants were three fellowship-trained breast radiologists with varying years of experience. Participants received an introduction to the virtual reality (VR) breast biopsy simulation and brief training session, describing how to enter the simulation and navigate controls. The participants were instructed to perform as many breast biopsies as possible within a 15-min time period. One biopsy cycle consisted of entering the breast with the biopsy needle, taking a biopsy sample and removing the needle. Time to successfully biopsy the mass was recorded by the VR program, and this data was recorded to assess improvement from start to finish of the simulation. A post-procedure survey was administered to all participants immediately after completion of the simulation. Qualitative open-ended subjective feedback was also obtained via Qualtrics.

Results: All three breast radiologists completed the simulation. There were no complications from the procedure, including no motion sickness or fatigue resulting in simulation termination. Results of data obtained from the simulation showed decreased time to successful biopsy (slope = -19.23) with each subsequent trial for all three participant breast radiologists. A decreased time to biopsy was associated with a higher cumulative number of successful biopsies (p = 0.0037). A higher number of cumulative successful biopsies was associated with decreased number of body entries (p = 0.0332) and biopsy fires (p = 0.0221) before a successful tissue sample. Mean responses for Likert scale survey results were overall high. The radiologists found the simulator to be engaging (4.67/5.00 ± 0.47), realistic (2.67/3.00 ± 0.47) and would recommend the simulation to other healthcare professionals (2.67/3.00 ± 0.47). The radiologists participating in the trial also provided overall favorable subjective feedback.

Conclusions: This study presents a novel approach for ultrasound-guided breast biopsy training with a VR simulation that showed to be successfully capable of recording time-to-completion of each biopsy attempt. Future studies will be directed toward assessing the utility of the simulation in improving trainee skills.