Clinical Imaging最新文献

{"title":"Use of a radiology tool for the diagnosis of pulmonary fibrosis","authors":"Weijia Fan ,&nbsp;Qixuan Chen ,&nbsp;Lyndon Luk ,&nbsp;Benjamin Navot ,&nbsp;Valerie Maccarrone ,&nbsp;Mary Salvatore","doi":"10.1016/j.clinimag.2024.110277","DOIUrl":"10.1016/j.clinimag.2024.110277","url":null,"abstract":"<div><h3>Objective</h3><p>The purpose of this paper was to perform an exploratory reader study to assess the utility of a web-based application in assisting non-chest radiologist in correctly diagnosing the radiographic pattern of pulmonary fibrosis.</p></div><div><h3>Methods</h3><p>Three non-chest radiologists with 5 to 20 years of experience individually reviewed 3 rounds of randomly chosen chest CT scans (round 1: 100 scans, round 2: 50 scans, round 3: 25 scans) from a list of patients with established diagnosis of pulmonary fibrosis. In round 1, radiologists were asked to directly record their diagnosis for the pattern of fibrosis. In round 2 and 3 they were asked to review for features provided in a web-based application and provide diagnosis based on the most likely predicted diagnosis from the application. There was an approximate 1-month interval and relevant tutorials were provided between each round. Diagnosis accuracy is reported by readers at each round.</p></div><div><h3>Results</h3><p>The overall accuracy increased from 63 % (<em>n</em> = 188/299) in round 1 to 74 % in round 3 (<em>n</em> = 52/70) (<em>p</em> = 0.0265). Difficulty in recognition of mosaic attenuation and homogeneous has led to misdiagnosis. Refining the definition for feature homogeneous increased the diagnosis accuracy of NSIP from 42 % (<em>n</em> = 20/48) in round 2 to 65 % (<em>n</em> = 24/37) in round 3(<em>p</em> = 0.0179). The Fleiss Kappa across readers varied from Round 1 to Round 3 with values <em>0.36 to 0.42</em>.</p></div><div><h3>Conclusions</h3><p>Using the web-based application with refined definition for feature homogeneous helps to improve the non-subspecialty radiologist's accuracy in diagnosing different types of fibrosis.</p></div>","PeriodicalId":50680,"journal":{"name":"Clinical Imaging","volume":"115 ","pages":"Article 110277"},"PeriodicalIF":1.8,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142241582","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comment on “Evaluation of responses to cardiac imaging questions by the artificial intelligence large language model ChatGPT”","authors":"Mohd Rafi Lone,&nbsp;Shahab Saquib Sohail","doi":"10.1016/j.clinimag.2024.110272","DOIUrl":"10.1016/j.clinimag.2024.110272","url":null,"abstract":"","PeriodicalId":50680,"journal":{"name":"Clinical Imaging","volume":"114 ","pages":"Article 110272"},"PeriodicalIF":1.8,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142146767","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Can large language models be new supportive tools in coronary computed tomography angiography reporting?","authors":"Eren Çamur ,&nbsp;Turay Cesur ,&nbsp;Yasin Celal Güneş","doi":"10.1016/j.clinimag.2024.110271","DOIUrl":"10.1016/j.clinimag.2024.110271","url":null,"abstract":"<div><p>The advent of large language models (LLMs) marks a transformative leap in natural language processing, offering unprecedented potential in radiology, particularly in enhancing the accuracy and efficiency of coronary artery disease (CAD) diagnosis. While previous studies have explored the capabilities of specific LLMs like ChatGPT in cardiac imaging, a comprehensive evaluation comparing multiple LLMs in the context of CAD-RADS 2.0 has been lacking. This study addresses this gap by assessing the performance of various LLMs, including ChatGPT 4, ChatGPT 4o, Claude 3 Opus, Gemini 1.5 Pro, Mistral Large, Meta Llama 3 70B, and Perplexity Pro, in answering 30 multiple-choice questions derived from the CAD-RADS 2.0 guidelines. Our findings reveal that ChatGPT 4o achieved the highest accuracy at 100 %, with ChatGPT 4 and Claude 3 Opus closely following at 96.6 %. Other models, including Mistral Large, Perplexity Pro, Meta Llama 3 70B, and Gemini 1.5 Pro, also demonstrated commendable performance, though with slightly lower accuracy ranging from 90 % to 93.3 %. This study underscores the proficiency of current LLMs in understanding and applying CAD-RADS 2.0, suggesting their potential to significantly enhance radiological reporting and patient care in coronary artery disease. The variations in model performance highlight the need for further research, particularly in evaluating the visual diagnostic capabilities of LLMs—a critical component of radiology practice. This study provides a foundational comparison of LLMs in CAD-RADS 2.0 and sets the stage for future investigations into their broader applications in radiology, emphasizing the importance of integrating both text-based and visual knowledge for optimal clinical outcomes.</p></div>","PeriodicalId":50680,"journal":{"name":"Clinical Imaging","volume":"114 ","pages":"Article 110271"},"PeriodicalIF":1.8,"publicationDate":"2024-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142136400","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dr. Carolyn Meltzer: Pioneer, innovator, mentor, and 2023 ACR Gold Medal winner","authors":"Nina S. Collier ,&nbsp;Patrick M. Colletti","doi":"10.1016/j.clinimag.2024.110270","DOIUrl":"10.1016/j.clinimag.2024.110270","url":null,"abstract":"<div><p>Dr. Carolyn Meltzer is an extraordinary radiologist, researcher, mentor, and distinguished leader who deserves recognition for her immense impact on the discipline of radiology. This article serves to acknowledge and celebrate Dr. Meltzer for winning the 2023 American College of Radiology (ACR) Gold Medal. The ACR Gold Medal award is the highest honor awarded to distinguished radiologists with exceptional contributions to the field, and Dr. Meltzer is no exception. She is the 14th woman to win this prestigious award, compared to 191 male winners, although it began as an annual tradition in 1927. Throughout this piece, Dr. Meltzer discusses her journey to where she is today as the dean of Keck School of Medicine at USC, the guidance and development that lead her to this point and provides sound advice for those who seek to follow in her footsteps as a leader and mentor committed to seeking ways to advance and contribute immensely to the field of radiology.</p></div>","PeriodicalId":50680,"journal":{"name":"Clinical Imaging","volume":"114 ","pages":"Article 110270"},"PeriodicalIF":1.8,"publicationDate":"2024-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142146768","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The science and practice of imaging-based screening: What the radiologist needs to know","authors":"Hannah S. Milch ,&nbsp;Linda B. Haramati","doi":"10.1016/j.clinimag.2024.110266","DOIUrl":"10.1016/j.clinimag.2024.110266","url":null,"abstract":"<div><p>Imaging-based screening is an important public health focus and a fundamental part of Diagnostic Radiology. Hence, radiologists should be familiar with the concepts that drive imaging-based screening practice including goals, risks, biases and clinical trials. This review article discusses an array of imaging-based screening exams including the key epidemiology and evidence that drive screening guidelines for abdominal aortic aneurysm, breast cancer, carotid artery disease, colorectal cancer, coronary artery disease, lung cancer, osteoporosis, and thyroid cancer. We will provide an overview on societal interests in screening, screening-related inequities, and opportunities to address them. Emerging evidence for opportunistic screening and the role of AI in imaging-based screening will be explored. In-depth knowledge and formalized training in imaging-based screening strengthens radiologists as clinician scientists and has the potential to broaden our public health leadership opportunities.</p></div><div><h3>Summary sentence</h3><p>An overview of key screening concepts, the evidence that drives today's imaging-based screening practices, and the need for radiologist leadership in screening policies and evidence development.</p></div>","PeriodicalId":50680,"journal":{"name":"Clinical Imaging","volume":"114 ","pages":"Article 110266"},"PeriodicalIF":1.8,"publicationDate":"2024-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142098941","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predictors of discordance between CT-derived fractional flow reserve (CT-FFR) and △CT-FFR in deep coronary myocardial bridging","authors":"Qingbo Sun ,&nbsp;Jing Zhang ,&nbsp;Wanbing Wang ,&nbsp;Yeqing Qi ,&nbsp;Jinhao Lyu ,&nbsp;Xinghua Zhang ,&nbsp;Tao Li ,&nbsp;Xin Lou","doi":"10.1016/j.clinimag.2024.110264","DOIUrl":"10.1016/j.clinimag.2024.110264","url":null,"abstract":"<div><h3>Objective</h3><p>To compare the performance between CT-derived fractional flow reserve (CT-FFR) and ΔCT-FFR measurements in patients with deep myocardial bridging (MB) along the left anterior descending artery, and explore the potential predictors of discordance.</p></div><div><h3>Methods</h3><p>175 patients with deep MB who underwent coronary computed tomography angiography (CCTA) and CT-FFR assessment were included. Clinical, anatomical and atherosclerotic variables were compared between patients with concordant and discordant CT-FFR and ΔCT-FFR.</p></div><div><h3>Results</h3><p>30.9 % patients were discordantly classified, in which 94.4 % patients were classified as CT-FFR+/△CT-FFR-. The discordant group showed significantly higher upstream stenosis degree, distance from MB to the aorta, △CT-FFR (<em>P</em> 0.007, 0.009 and 0.002, respectively), and lower CT-FFR (<em>P</em> &lt; 0.001). In multivariate analysis, upstream stenosis degree (<em>P</em> 0.023, OR 1.628, 95 % CI: 1.068–2.481) and distance from MB to the aorta (<em>P</em> 0.001, OR 1.04, 95 % CI: 1.016–1.064) were independent predictors for discordance between CT-FFR and ΔCT-FFR.</p></div><div><h3>Conclusion</h3><p>The discordance between CT-FFR and ΔCT-FFR measurements underscores the challenges in clinical decision-making, necessitating tailored approaches for MB evaluation.</p></div>","PeriodicalId":50680,"journal":{"name":"Clinical Imaging","volume":"114 ","pages":"Article 110264"},"PeriodicalIF":1.8,"publicationDate":"2024-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142098940","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"“One a penny, two a penny”, I saw the hot cross bun sign”","authors":"Ryan Johnson ,&nbsp;John Lausch ,&nbsp;Dakota Degenstein ,&nbsp;Boris Reznikov","doi":"10.1016/j.clinimag.2024.110251","DOIUrl":"10.1016/j.clinimag.2024.110251","url":null,"abstract":"<div><p>The hot cross bun sign is a radiological sign seen on MRI due to pontocerebellar demyelination and loss of neurons along with preservation of the pontine tegmentum and corticospinal tracts which is classically seen in Multiple System Atrophy (MSA). Hot cross buns have been in existence since as early as the 14th century up until the point when Schrag et al. (1998) coupled the appearance of this age-old bread with the T2 imaging characteristics of MSA. Over time the radiological sign has expanded with a differential diagnosis of spinocerebellar ataxia, progressive multifocal leukoencephalopathy, paraneoplastic cerebellar degeneration, and variant Creutzfeldt-Jakob disease.</p></div>","PeriodicalId":50680,"journal":{"name":"Clinical Imaging","volume":"114 ","pages":"Article 110251"},"PeriodicalIF":1.8,"publicationDate":"2024-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141993262","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Commentary on mentorship in residency with novel program: Mentorship Expanded Networking and Teaching to Integrate and Enhance Residency (MEN-TIER)","authors":"Makayla Kochheiser,&nbsp;Jenny Yan,&nbsp;Nicole A. Lamparello,&nbsp;Kimberly Scherer,&nbsp;Bradley Pua,&nbsp;Benjamin May,&nbsp;Brian Currie","doi":"10.1016/j.clinimag.2024.110265","DOIUrl":"10.1016/j.clinimag.2024.110265","url":null,"abstract":"<div><h3>Background</h3><p>Mentorship is the foundation for training and career development.</p><p>However, only about half of interventional radiology (IR) residency programs in the United States have a formal mentorship program at their institution. A new tiered mentorship program was introduced at our institution.</p></div><div><h3>Methods</h3><p>A structured mentorship program was created at our institution in 2020 for IR residents to pair 1–2 faculty advisors with a group of residents, one from each PGY class, based on personal interests and career paths. A quality improvement survey with Likert scale format (1–5) was sent to IR residents and faculty members.</p></div><div><h3>Results</h3><p>Responses were recorded from 11 IR residents in addition to all 6 IR faculty mentors. IR respondents reported satisfaction with feeling more assimilated in the department and all would recommend the current mentorship model to other institutions. Most respondents agreed the program made them comfortable conducting effective mentorship relationships as an attending and that the tiered structured of being mentee and mentor simultaneously was beneficial. Both IR residents and faculty agreed that the program helped prevent burnout.</p></div><div><h3>Conclusions</h3><p>The tiered mentorship model has had a positive impact on the IR program by providing structured mentoring and longitudinal relationships. The most notable benefits for IR residents is the early integration into the program, sustained mentorships relationships, and the prevention of burnout. Similar models can help other programs establish structured faculty and peer mentorship for residents early in training.</p></div>","PeriodicalId":50680,"journal":{"name":"Clinical Imaging","volume":"114 ","pages":"Article 110265"},"PeriodicalIF":1.8,"publicationDate":"2024-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142084376","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Differentiation of intrathoracic lymph node histopathology by volumetric dual energy CT radiomic analysis","authors":"Sophie L. Washer ,&nbsp;William H. Moore ,&nbsp;Thomas O'Donnell ,&nbsp;Jane P. Ko ,&nbsp;Priya Bhattacharji ,&nbsp;Lea Azour","doi":"10.1016/j.clinimag.2024.110252","DOIUrl":"10.1016/j.clinimag.2024.110252","url":null,"abstract":"<div><h3>Purpose</h3><p>To determine the performance of volumetric dual energy low kV and iodine radiomic features for the differentiation of intrathoracic lymph node histopathology, and influence of contrast protocol.</p></div><div><h3>Materials and methods</h3><p>Intrathoracic lymph nodes with histopathologic correlation (neoplastic, granulomatous sarcoid, benign) within 90 days of DECT chest imaging were volumetrically segmented. 1691 volumetric radiomic features were extracted from iodine maps and low-kV images, totaling 3382 features. Univariate analysis was performed using 2-sample <em>t</em>-test and filtered for false discoveries. Multivariable analysis was used to compute AUCs for lymph node classification tasks.</p></div><div><h3>Results</h3><p>129 lymph nodes from 72 individuals (mean age 61 ± 15 years) were included, 52 neoplastic, 51 benign, and 26 granulomatous-sarcoid. Among all contrast enhanced DECT protocol exams (routine, PE and CTA), univariable analysis demonstrated no significant differences in iodine and low kV features between neoplastic and non-neoplastic lymph nodes; in the subset of neoplastic versus benign lymph nodes with routine DECT protocol, 199 features differed (<em>p</em> = .01- &lt; 0.05).</p><p>Multivariable analysis using both iodine and low kV features yielded AUCs &gt;0.8 for differentiating neoplastic from non-neoplastic lymph nodes (AUC 0.86), including subsets of neoplastic from granulomatous (AUC 0.86) and neoplastic from benign (AUC 0.9) lymph nodes, among all contrast protocols.</p></div><div><h3>Conclusions</h3><p>Volumetric DECT radiomic features demonstrate strong collective performance in differentiation of neoplastic from non-neoplastic intrathoracic lymph nodes, and are influenced by contrast protocol.</p></div>","PeriodicalId":50680,"journal":{"name":"Clinical Imaging","volume":"114 ","pages":"Article 110252"},"PeriodicalIF":1.8,"publicationDate":"2024-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0899707124001827/pdfft?md5=57b4ba93e3c0f1113faea058926b4d75&pid=1-s2.0-S0899707124001827-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141977116","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of a multi-modal learning-based lymph node metastasis prediction model for lung cancer","authors":"Jeongmin Park ,&nbsp;Seonhwa Kim ,&nbsp;June Hyuck Lim ,&nbsp;Chul-Ho Kim ,&nbsp;Seulgi You ,&nbsp;Jeong-Seok Choi ,&nbsp;Jun Hyeok Lim ,&nbsp;Jae Won Chang ,&nbsp;Dongil Park ,&nbsp;Myung-won Lee ,&nbsp;Byung-Joo Lee ,&nbsp;Sung-Chan Shin ,&nbsp;Yong-Il Cheon ,&nbsp;Il-Seok Park ,&nbsp;Seung Hoon Han ,&nbsp;Daemyung Youn ,&nbsp;Hye Sang Lee ,&nbsp;Jaesung Heo","doi":"10.1016/j.clinimag.2024.110254","DOIUrl":"10.1016/j.clinimag.2024.110254","url":null,"abstract":"<div><h3>Purpose</h3><p>This study proposed a three-dimensional (3D) multi-modal learning-based model for the automated prediction and classification of lymph node metastasis in patients with non-small cell lung cancer (NSCLC) using computed tomography (CT) images and clinical information.</p></div><div><h3>Methods</h3><p>We utilized clinical information and CT image data from 4239 patients with NSCLC across multiple institutions. Four deep learning algorithm-based multi-modal models were constructed and evaluated for lymph node classification. To further enhance classification performance, a soft-voting ensemble technique was applied to integrate the outcomes of multiple multi-modal models.</p></div><div><h3>Results</h3><p>A comparison of the classification performance revealed that the multi-modal model, which integrated CT images and clinical information, outperformed the single-modal models. Among the four multi-modal models, the Xception model demonstrated the highest classification performance, with an area under the curve (AUC) of 0.756 for the internal test dataset and 0.736 for the external validation dataset. The ensemble model (SEResNet50_DenseNet121_Xception) exhibited even better performance, with an AUC of 0.762 for the internal test dataset and 0.751 for the external validation dataset, surpassing the multi-modal model's performance.</p></div><div><h3>Conclusions</h3><p>Integrating CT images and clinical information improved the performance of the lymph node metastasis prediction models in patients with NSCLC. The proposed 3D multi-modal lymph node prediction model can serve as an auxiliary tool for evaluating lymph node metastasis in patients with non-pretreated NSCLC, aiding in patient screening and treatment planning.</p></div>","PeriodicalId":50680,"journal":{"name":"Clinical Imaging","volume":"114 ","pages":"Article 110254"},"PeriodicalIF":1.8,"publicationDate":"2024-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141993261","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}