Radiology最新文献

{"title":"Prognostic Value of Global Longitudinal Strain using Automated Measurement in Cardiac MRI.","authors":"Elena Sofia Canuti, Solenn Toupin, Thomas Hovasse, Francesca Sanguineti, Thierry Unterseeh, Philippe Garot, Stéphane Champagne, Suzanne Duhamel, Mariama Akodad, Antoinette Neylon, Teodora Chitiboi, Puneet Sharma, Trecy Gonçalves, Raphaël Mirailles, Alexandre Unger, Viviana Maestrini, Théo Pezel, Jérôme Garot","doi":"10.1148/radiol.241147","DOIUrl":"10.1148/radiol.241147","url":null,"abstract":"<p><p></p>","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"316 2","pages":"e241147"},"PeriodicalIF":15.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144822394","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Contemporary Review of Imaging in Arrhythmogenic Cardiomyopathy.","authors":"Mikael Laredo, Etienne Charpentier, Estelle Gandjbakhch, Alban Redheuil, Nadjia Kachenoura","doi":"10.1148/radiol.242190","DOIUrl":"10.1148/radiol.242190","url":null,"abstract":"<p><p>Arrhythmogenic cardiomyopathy (ACM) is a rare inherited disease characterized by fibrofatty replacement of the myocardium, associated with lethal arrhythmias and heart failure. ACM diagnosis is challenging, as it involves clinical, genetic, and multiparametric imaging assessments. Imaging plays a central role in evaluating ACM by targeting the intertwined morphofunctional and tissue abnormalities. Cardiac MRI is the reference technique due to its ability to depict both types of abnormalities comprehensively and without radiation. Over the past decade, advances in regional deformation analysis and tissue characterization have improved detection of early-stage disease and recognition of left ventricular (LV) involvement, expanding beyond the classic right ventricle phenotype and leading to updated diagnostic criteria. CT, with its superior and isotropic spatial resolution, strong native contrast for adipose tissue, and potential dynamic four-dimensional acquisition, could play a key role in ACM diagnosis and characterization, particularly in patients with implanted devices. This review explores the strengths and limitations of cardiac MRI and CT in ACM evaluation, emphasizing LV involvement and new diagnostic criteria. It also addresses key challenges, such as the prognostic value of cardiac MRI and structural disease progression, while discussing the latest advancements and future directions for both modalities.</p>","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"316 2","pages":"e242190"},"PeriodicalIF":15.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144874914","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Sample Size Estimation: Ten Frequently Unanswered Questions.","authors":"Kamyar Moradi, John Eng","doi":"10.1148/radiol.250239","DOIUrl":"10.1148/radiol.250239","url":null,"abstract":"<p><p>Sample size estimation is a critical component in designing rigorous clinical research, ensuring that studies are adequately powered to detect meaningful effects. Despite extensive literature on the topic and the availability of online resources for sample size calculation, researchers may still find the process challenging. This article addresses practical questions that radiology researchers frequently encounter, with the aim of improving awareness among both researchers and journal readers of the study design elements affecting proper sample size estimation.</p>","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"316 2","pages":"e250239"},"PeriodicalIF":15.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144874924","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Clinical and Imaging Factors Impacting Positive Predictive Value of Prostate MRI.","authors":"Simon John Christoph Soerensen, Jarrett Rosenberg, Zachary Franks, Mirabela Rusu, Richard E Fan, Geoffrey A Sonn, Pejman Ghanouni","doi":"10.1148/radiol.250413","DOIUrl":"10.1148/radiol.250413","url":null,"abstract":"","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"316 2","pages":"e250413"},"PeriodicalIF":15.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12405724/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144822388","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cardiac Chamber Interdependence: When Left-to-Right Chamber Volume Ratio Better Predicts Heart Failure, Atrial Fibrillation, and Death.","authors":"Farah Cadour, Jean-Nicolas Dacher","doi":"10.1148/radiol.252169","DOIUrl":"10.1148/radiol.252169","url":null,"abstract":"","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"316 2","pages":"e252169"},"PeriodicalIF":15.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144874916","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Case 340: Pulmonary Necrobiotic Nodules as a Lung Manifestation of Crohn Disease.","authors":"Nuno Lupi Manso, José Laert, Tomás França de Santana, João Alpendre","doi":"10.1148/radiol.241894","DOIUrl":"https://doi.org/10.1148/radiol.241894","url":null,"abstract":"<p><strong>History: </strong>A 36-year-old woman with an otherwise unremarkable medical history was diagnosed with moderate to severe Crohn disease and was started on infliximab. One year later, infliximab was discontinued due to intolerance, and the patient began azathioprine and mesalazine treatment, achieving stable disease. Eight months after discontinuing infliximab, during a Crohn disease flare-up, an urgent abdominal CT examination was performed, partially documenting the lung bases. The patient maintained her therapy, with remission of the flare-up. Sixteen months after discontinuing infliximab and 8 months after initial abdominal CT, she presented to the emergency department with pleuritic chest pain and occasional dyspnea. She was afebrile, and her physical examination and routine laboratory test results were unremarkable. Chest CT was performed. The patient was started on analgesics and referred to a pulmonology appointment, where biopsy of the lesion was recommended. One month after chest CT, while awaiting the biopsy results, the patient again presented to the emergency department with recurring similar symptoms after a brief period of symptomatic improvement. Physical examination and laboratory test results remained unremarkable. This visit prompted a new chest CT examination.</p>","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"316 2","pages":"e241894"},"PeriodicalIF":15.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144966449","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparison of a Specialized Large Language Model with GPT-4o for CT and MRI Radiology Report Summarization.","authors":"Sunyi Zheng, Nannan Zhao, Jing Wang, Tao Yu, Dongsheng Yue, Wenjia Zhang, Shuxuan Fan, Xiaolei Wang, Guilin Tang, Yuxuan Sun, Hongwei Wang, Shui Liu, Jiaxin Liu, Keyi Bian, Yuwei Zhang, Geertruida H de Bock, Matthijs Oudkerk, Xiaonan Cui, Rozemarijn Vliegenthart, Zhaoxiang Ye","doi":"10.1148/radiol.243774","DOIUrl":"https://doi.org/10.1148/radiol.243774","url":null,"abstract":"<p><p>Background Although the general-purpose large language model (LLM) GPT-4o (OpenAI) has shown promise in radiology language processing, it remains unclear whether the performance of GPT-4o in report summarization is better than that of an LLM specifically designed for this task. Purpose To compare the performance of a specialized LLM with that of GPT-4o in the comprehensive summarization of radiology reports. Materials and Methods A specialized LLM for report summarization (LLM-RadSum) was developed using retrospectively collected reports from a hospital, divided into training and internal test sets (9:1 ratio). The F1 scores based on the longest common subsequences were evaluated on the internal test set and an external test set of reports from four other hospitals. Only CT and MRI reports containing findings and impressions sections were included. For comparison with GPT-4o, a human evaluation set included 1800 reports randomly selected from the internal and external test sets, ensuring balanced coverage of imaging modalities (CT, MRI) and anatomic sites (chest, neck, head, pelvis, abdomen, breast). Three senior radiologists and two clinicians assessed this set, focusing on factual consistency, impression coherence, medical safety, and clinical use. A <i>t</i> test was performed to compare F1 scores between models. Results The training, internal test, and external test sets were composed of 956 219, 106 247, and 17 091 reports, respectively. The developed LLM-RadSum achieved median F1 scores for report summarization of 0.75 and 0.44 on the internal and external test sets and 0.58 on the human evaluation set (<i>n</i> = 1800). More than 81.5% (1467 of 1800) of outputs from LLM-RadSum met the standards of senior radiologists and clinicians regarding factual consistency, impression coherence, medical safety, and clinical use. In contrast, at least 27.8% (501 of 1800) of outputs from GPT-4o required adjustments in these aspects. Overall, LLM-RadSum achieved a higher median F1 score for report summarization compared with GPT-4o (0.58 [IQR: 0.44-0.77] vs 0.30 [IQR: 0.23-0.37]; <i>P</i> < .001); superior performance from LLM-RadSum was observed across anatomic regions, modalities, sexes, ages, and impression lengths (all <i>P</i> < .001). Conclusion A specialized LLM for report summarization had better performance than GPT-4o, a general-purpose LLM, in generating radiology report summaries. © RSNA, 2025 <i>Supplemental material is available for this article.</i> See also the editorial by Huisman and Rasoolzadeh in this issue.</p>","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"316 2","pages":"e243774"},"PeriodicalIF":15.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144966470","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Performance of Algorithms Submitted in the 2023 RSNA Screening Mammography Breast Cancer Detection AI Challenge.","authors":"Yan Chen, George J W Partridge, Maryam Vazirabad, Robyn L Ball, Hari M Trivedi, Felipe Campos Kitamura, Helen M L Frazer, Tara A Retson, Luyan Yao, Iain T Darker, Tatiana Kelil, John Mongan, Ritse M Mann, Linda Moy","doi":"10.1148/radiol.241447","DOIUrl":"https://doi.org/10.1148/radiol.241447","url":null,"abstract":"<p><p>Background The 2023 RSNA Screening Mammography Breast Cancer Detection AI Challenge invited participants to develop artificial intelligence (AI) models capable of independently interpreting mammograms. Purpose To assess the performance of the submitted algorithms, explore the potential for improving performance by combining the best-performing AI algorithms, and investigate how performance was influenced by the demographic and clinical characteristics of the evaluation cohort. Materials and Methods A total of 1687 AI algorithms were submitted from November 2022 to February 2023. Of these, 1537 algorithms were assessed using an evaluation dataset from two sites-one in the United States and one in Australia. Cancer cases were identified at screening and confirmed with pathologic examination; noncancer cases were followed up for at least 1 year. Results for ensemble models of top algorithms were computed by recalling a case when any of the included algorithms indicated recall. Odds ratios (ORs) were used to investigate differences in AI performance when the dataset was stratified by clinical or demographic characteristics. Results The evaluation dataset consisted of 5415 women (median age, 59 years [IQR, 52-66 years]). Among the 1537 AI algorithms, the median recall rate, sensitivity, specificity, and positive predictive value (PPV) were 1.7%, 27.6%, 98.7%, and 36.9%, respectively. For the top-ranked algorithm, the recall rate, sensitivity, specificity, and PPV were 1.5%, 48.6%, 99.5%, and 64.6%, respectively. Ensemble models of the top 3 and top 10 algorithms had a sensitivity of 60.7% and 67.8%, respectively; the corresponding recall rates were 2.4% and 3.5%, and the corresponding specificities were 98.8% and 97.8%. Lower sensitivity was observed for the U.S. dataset than for the Australian dataset (top 3 ensemble model: 52.0% vs 68.1%; OR = 0.51; <i>P</i> = .02), and greater sensitivity was observed for invasive cancers than for noninvasive cancers (top 3 ensemble model: 68.0% vs 43.8%; OR = 2.73; <i>P</i> = .001). Conclusion The different AI algorithms identified different cancers during screening mammography, and ensemble models had increased sensitivity while maintaining low recall rates. © RSNA, 2025 <i>Supplemental material is available for this article.</i></p>","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"316 2","pages":"e241447"},"PeriodicalIF":15.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144822393","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"When AI Knows Its Limits.","authors":"Pascal A T Baltzer","doi":"10.1148/radiol.252198","DOIUrl":"10.1148/radiol.252198","url":null,"abstract":"","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"316 2","pages":"e252198"},"PeriodicalIF":15.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144874925","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Extending Risk Assessment to Outcomes of Lung Cancer Screening with Low-Dose CT Scans.","authors":"Francine L Jacobson,Suzanne C Byrne","doi":"10.1148/radiol.252166","DOIUrl":"https://doi.org/10.1148/radiol.252166","url":null,"abstract":"","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"724 1","pages":"e252166"},"PeriodicalIF":19.7,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144778013","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}