Radiology最新文献

{"title":"Enhancing Practices for Multiparametric MRI in Gastric Cancer: Addressing Clear Criteria for T and N Stage.","authors":"Yan Chen, Quan-Meng Liu","doi":"10.1148/radiol.242222","DOIUrl":"https://doi.org/10.1148/radiol.242222","url":null,"abstract":"","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"314 3","pages":"e242222"},"PeriodicalIF":12.1,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143606265","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":"CT Prognostication across the Whole Spectrum of Fibrotic Interstitial Lung Disease: Implications and Opportunities.","authors":"Athol U Wells","doi":"10.1148/radiol.243763","DOIUrl":"https://doi.org/10.1148/radiol.243763","url":null,"abstract":"","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"314 2","pages":"e243763"},"PeriodicalIF":12.1,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143189960","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":"Association between Cystic Fibrosis and Pericardial Calcification Detected at Chest CT in Adults.","authors":"Sara Rodriguez-Takeuchi, Elizabeth Tullis, Ali Babaei Jandaghi, Andrew T Yan, Errol Colak, David A Hall, Kathy Wong, Laura Jiménez-Juan, Kieran McIntyre, Jenna Sykes, Djeven P Deva, Matias F Callejas","doi":"10.1148/radiol.241793","DOIUrl":"https://doi.org/10.1148/radiol.241793","url":null,"abstract":"<p><p>Background Although pericardial calcification has been observed on chest CT scans in patients with cystic fibrosis (CF), its prevalence and characteristics have not been elucidated. Purpose To determine the prevalence and characteristics of pericardial calcification, and identify clinical variables associated with it, in adult patients with CF and to compare this prevalence with that in individuals without CF. Materials and Methods This was a retrospective, single-center case-control study including consecutive patients with CF who underwent chest CT between January 2021 and December 2022. Control group 1 included individuals without CF matched for age and sex. Control group 2 included individuals with previous <i>Mycobacterium tuberculosis</i> infection and no concomitant diagnosis of CF matched for sex. Control group 3 included patients with primary ciliary dyskinesia. Qualitative and quantitative evaluations of pericardial calcification were performed. The χ² test and Fisher exact test were used for comparisons of categorical variables; the Kruskal-Wallis test and Mann-Whitney <i>U</i> test were used for comparisons of continuous variables. Results Of the 348 adult patients with CF (mean age, 35 years ± 13 [SD]; 193 [55%] male patients), 62 (18%) had pericardial calcification at CT. The prevalence of pericardial calcification was 1% (four of 348) in control group 1, 2% (two of 100) in control group 2, and 4% (one of 24) in control group 3 (<i>P</i> < .001). Pericardial calcification developed de novo in 66% (41 of 62) and progressed in 21% (13 of 62) of patients with CF. The distribution of pericardial calcification in patients with CF was most frequently multifocal (58%; 36 of 62). The median calcium score of pericardial calcification was 65 (IQR, 28-375). In patients with CF, older age, lower forced expiratory volume in 1 second, higher vitamin D level, and a higher prevalence of <i>Burkholderia cenocepacia</i> ET12 infection were associated with pericardial calcification. Conclusion Pericardial calcification was more prevalent in adult patients with CF than in individuals without CF and progressed over time in some patients. © RSNA, 2025 <i>Supplemental material is available for this article.</i></p>","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"314 2","pages":"e241793"},"PeriodicalIF":12.1,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143493344","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":"Cinematic Rendering of a Bronchial Artery Aneurysm.","authors":"Zihao Li, Jingsong Mao","doi":"10.1148/radiol.242488","DOIUrl":"https://doi.org/10.1148/radiol.242488","url":null,"abstract":"","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"314 2","pages":"e242488"},"PeriodicalIF":12.1,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143493353","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":"Erratum for: CT/MRI LI-RADS 2024 Update: Treatment Response Assessment.","authors":"Anum Aslam, Victoria Chernyak, An Tang, Frank H Miller, Mustafa Bashir, Richard Do, Claude Sirlin, Robert J Lewandowski, Charles Y Kim, Ania Zofia Kielar, Avinash R Kambadakone, Hooman Yarmohammadi, Edward Kim, Dawn Owen, Resmi A Charalel, Anuradha Shenoy-Bhangle, Lauren M Burke, Mishal Mendiratta-Lala","doi":"10.1148/radiol.259002","DOIUrl":"10.1148/radiol.259002","url":null,"abstract":"","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"314 2","pages":"e259002"},"PeriodicalIF":12.1,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11868817/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143493365","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":"Transarterial Chemoembolization with Radiofrequency Ablation versus Surgical Resection for Small Late-Recurrence Hepatocellular Carcinoma.","authors":"Yao-Jun Zhang, Jinbin Chen, Zhongguo Zhou, Dandan Hu, Juncheng Wang, Yangxun Pan, Yizhen Fu, Zili Hu, Li Xu, Min-Shan Chen","doi":"10.1148/radiol.241096","DOIUrl":"https://doi.org/10.1148/radiol.241096","url":null,"abstract":"<p><p>Background Radiofrequency ablation (RFA) has comparable clinical outcomes to surgical resection (SR) for treating small recurrent hepatocellular carcinoma (HCC). However, whether combined transarterial chemoembolization (TACE) with RFA (hereafter, TACE-RFA) outperforms SR for treating small late-recurrence HCCs remains unknown. Purpose To compare the clinical outcome of TACE-RFA with that of SR in patients with small late-recurrence HCCs. Materials and Methods This randomized clinical trial recruited patients between July 2013 and March 2019. Patients with small late-recurrence HCCs (a single recurrent HCC nodule [≤ 5 cm in diameter] or three or fewer nodules [each ≤ 3 cm in diameter] and recurrence at least 12 months after radical therapy of primary HCC) were randomly assigned to receive TACE-RFA or SR. The primary end point was overall survival (OS). The secondary end points included recurrence-free survival (RFS) and the incidence of complications. OS and RFS were assessed using the Kaplan-Meier method and log-rank test. Results In the intention-to-treat analysis, 210 patients (mean age, 52 years ± 12 [SD]; 194 male) were included, with 105 patients in each group. The 1-, 3-, and 5-year OS rates were 99%, 81%, and 69%, respectively, in the TACE-RFA group and 96%, 81%, and 76%, respectively, in the SR group (hazard ratio [HR], 1.34; 95% CI: 0.81, 2.23; <i>P</i> = .26). The 1-, 3-, and 5-year RFS rates were 71%, 38%, and 24%, respectively, in the TACE-RFA group and 73%, 43%, and 29%, respectively, in the SR group (HR, 1.05; 95% CI: 0.76, 1.45; <i>P</i> = .78). The incidence of complications was greater in the SR group than in the TACE-RFA group (41% [43 of 104] vs 24% [23 of 96]; <i>P</i> = .01). Conclusion For patients with small late-recurrence HCCs, TACE-RFA did not yield better survival outcomes than SR. However, the incidence of complications was lower in patients who received TACE-RFA therapy. ClinicalTrials.gov Identifier: NCT01833286 © RSNA, 2025 <i>Supplemental material is available for this article.</i> See also the editorial by Ronot in this issue.</p>","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"314 2","pages":"e241096"},"PeriodicalIF":12.1,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143190303","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":"Assessing Completeness of Clinical Histories Accompanying Imaging Orders Using Adapted Open-Source and Closed-Source Large Language Models.","authors":"David B Larson, Arogya Koirala, Lina Y Cheuy, Magdalini Paschali, Dave Van Veen, Hye Sun Na, Matthew B Petterson, Zhongnan Fang, Akshay S Chaudhari","doi":"10.1148/radiol.241051","DOIUrl":"10.1148/radiol.241051","url":null,"abstract":"&lt;p&gt;&lt;p&gt;Background Incomplete clinical histories are a well-known problem in radiology. Previous dedicated quality improvement efforts focusing on reproducible assessments of the completeness of free-text clinical histories have relied on tedious manual analysis. Purpose To adapt and evaluate open-source and closed-source large language models (LLMs) for their ability to automatically extract clinical history elements within imaging orders and to use the best-performing adapted open-source model to assess the completeness of a large sample of clinical histories as a benchmark for clinical practice. Materials and Methods This retrospective single-site study used previously extracted information accompanying CT, MRI, US, and radiography orders from August 2020 to May 2022 at an adult and pediatric emergency department of a 613-bed tertiary academic medical center. Two open-source (Llama 2-7B [Meta], Mistral-7B [Mistral AI]) and one closed-source (GPT-4 Turbo [OpenAI]) LLMs were adapted using prompt engineering, in-context learning, and fine-tuning (open-source only) to extract the elements \"past medical history,\" \"what,\" \"when,\" \"where,\" and \"clinical concern\" from clinical histories. Model performance, interreader agreement using Cohen κ (none to slight, 0.01-0.20; fair, 0.21-0.40; moderate, 0.41-0.60; substantial, 0.61-0.80; almost perfect, 0.81-1.00), and semantic similarity between the models and the adjudicated manual annotations of two board-certified radiologists with 16 and 3 years of postfellowship experience, respectively, were assessed using accuracy, Cohen κ, and BERTScore, an LLM metric that quantifies how well two pieces of text convey the same meaning; 95% CIs were also calculated. The best-performing open-source model was then used to assess completeness on a large dataset of unannotated clinical histories. Results A total of 50 186 clinical histories were included (794 training, 150 validation, 300 initial testing, 48 942 real-world application). Of the two open-source models, Mistral-7B outperformed Llama 2-7B in assessing completeness and was further fine-tuned. Both Mistral-7B and GPT-4 Turbo showed substantial overall agreement with radiologists (mean κ, 0.73 [95% CI: 0.67, 0.78] to 0.77 [95% CI: 0.71, 0.82]) and adjudicated annotations (mean BERTScore, 0.96 [95% CI: 0.96, 0.97] for both models; &lt;i&gt;P&lt;/i&gt; = .38). Mistral-7B also rivaled GPT-4 Turbo in performance (weighted overall mean accuracy, 91% [95% CI: 89, 93] vs 92% [95% CI: 90, 94]; &lt;i&gt;P&lt;/i&gt; = .31) despite being a smaller model. Using Mistral-7B, 26.2% (12 803 of 48 942) of unannotated clinical histories were found to contain all five elements. Conclusion An easily deployable fine-tuned open-source LLM (Mistral-7B), rivaling GPT-4 Turbo in performance, could effectively extract clinical history elements with substantial agreement with radiologists and produce a benchmark for completeness of a large sample of clinical histories. The model and code will be fully open-sourced","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"314 2","pages":"e241051"},"PeriodicalIF":12.1,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11868845/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143493342","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":"TotalSegmentator MRI: Robust Sequence-independent Segmentation of Multiple Anatomic Structures in MRI.","authors":"Tugba Akinci D'Antonoli, Lucas K Berger, Ashraya K Indrakanti, Nathan Vishwanathan, Jakob Weiss, Matthias Jung, Zeynep Berkarda, Alexander Rau, Marco Reisert, Thomas Küstner, Alexandra Walter, Elmar M Merkle, Daniel T Boll, Hanns-Christian Breit, Andrew Phillip Nicoli, Martin Segeroth, Joshy Cyriac, Shan Yang, Jakob Wasserthal","doi":"10.1148/radiol.241613","DOIUrl":"https://doi.org/10.1148/radiol.241613","url":null,"abstract":"<p><p>Background Since the introduction of TotalSegmentator CT, there has been demand for a similar robust automated MRI segmentation tool that can be applied across all MRI sequences and anatomic structures. Purpose To develop and evaluate an automated MRI segmentation model for robust segmentation of major anatomic structures independent of MRI sequence. Materials and Methods In this retrospective study, an nnU-Net model (TotalSegmentator MRI) was trained on MRI and CT scans to segment 80 anatomic structures relevant for use cases such as organ volumetry, disease characterization, surgical planning, and opportunistic screening. Images were randomly sampled from routine clinical studies to represent real-world examples. Dice scores were calculated between the predicted segmentations and expert radiologist segmentations to evaluate model performance on an internal test set and two external test sets and against two publicly available models and TotalSegmentator CT. The Wilcoxon signed rank test was used to compare model performance. The proposed model was applied to a separate internal dataset containing abdominal MRI scans to investigate age-dependent volume changes. Results A total of 1143 scans (616 MRI, 527 CT; median patient age, 61 years [IQR, 50-72 years]) were split into a training set (<i>n</i> = 1088; CT and MRI) and an internal test set (<i>n</i> = 55; MRI only). The two external test sets (AMOS and CHAOS) contained 20 MRI scans each, and the aging-study dataset contained 8672 abdominal MRI scans (median patient age, 59 years [IQR, 45-70 years]). The proposed model had a Dice score of 0.839 for the 80 anatomic structures in the internal test set and outperformed two other models (Dice score of 0.862 vs 0.759 for 40 anatomic structures and 0.838 vs 0.560 for 13 anatomic structures; <i>P</i> < .001 for both). On the TotalSegmentator CT test set (89 CT scans), the performance of the proposed model almost matched that of TotalSegmentator CT (Dice score, 0.966 vs 0.970; <i>P</i> < .001). The aging study demonstrated a strong correlation between age and organ volume (eg, age and liver volume: ρ = -0.096; <i>P</i> < .0001). Conclusion The proposed open-source, easy-to-use model allows for automatic, robust segmentation of 80 structures, extending the capabilities of TotalSegmentator to MRI scans from any MRI sequence. The ready-to-use online tool is available at <i>https://totalsegmentator.com</i>; the model, at <i>https://github.com/wasserth/TotalSegmentator</i>; and the dataset, at <i>http://zenodo.org/records/14710732</i>. © RSNA, 2025 <i>Supplemental material is available for this article.</i> See also the editorial by Kitamura in this issue.</p>","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"314 2","pages":"e241613"},"PeriodicalIF":12.1,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143441882","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":"Dice the Slice: MRI and CT Segmentation in Radiology.","authors":"Felipe C Kitamura","doi":"10.1148/radiol.250143","DOIUrl":"https://doi.org/10.1148/radiol.250143","url":null,"abstract":"","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"314 2","pages":"e250143"},"PeriodicalIF":12.1,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143441812","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":"Erratum for: Interventional Oncology Meets Immuno-oncology: Combination Therapies for Hepatocellular Carcinoma.","authors":"Ryan Bitar, Riad Salem, Richard Finn, Tim F Greten, S Nahum Goldberg, Julius Chapiro","doi":"10.1148/radiol.259004","DOIUrl":"10.1148/radiol.259004","url":null,"abstract":"","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"314 2","pages":"e259004"},"PeriodicalIF":12.1,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11868818/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143493380","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}