Radiology-Artificial Intelligence最新文献

{"title":"Seeing beyond CT: Multimodal Data and the Next Frontier of AI for Bone Metastasis Detection.","authors":"Pegah Khosravi","doi":"10.1148/ryai.260247","DOIUrl":"10.1148/ryai.260247","url":null,"abstract":"","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":"8 3","pages":"e260247"},"PeriodicalIF":20.1,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147692589","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Imaging the Breast Cancer Microenvironment: Toward Interpretable MRI Biomarkers for Treatment Response.","authors":"Tician Schnitzler","doi":"10.1148/ryai.260266","DOIUrl":"10.1148/ryai.260266","url":null,"abstract":"","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":"8 3","pages":"e260266"},"PeriodicalIF":20.1,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147783347","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"When Framing Shapes the Answer: Cognitive Bias and Large Language Model Reliability in Radiology.","authors":"Soroosh Tayebi Arasteh, Daniel Truhn","doi":"10.1148/ryai.260346","DOIUrl":"10.1148/ryai.260346","url":null,"abstract":"","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":"8 3","pages":"e260346"},"PeriodicalIF":20.1,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147843383","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Accelerated Aging and Aging Velocity from Deep Learning-based Chest Radiograph-derived Age for Predicting Cause-specific Mortality.","authors":"Yoosoo Chang, Hyungjin Kim, Seungho Lee, Hong Seok Lee, Soon Ho Yoon, Seungho Ryu","doi":"10.1148/ryai.250609","DOIUrl":"10.1148/ryai.250609","url":null,"abstract":"<p><p>Purpose To assess the prognostic value of deep learning-derived radiographic age and aging velocity for predicting mortality in an Asian cohort. Materials and Methods This retrospective cohort study included Korean adults who underwent posteroanterior chest radiography between January 2006 and December 2020. Radiographic age was estimated using AgeNet, a deep learning model trained on the data of healthy asymptomatic individuals. Accelerated aging was defined as radiographic age exceeding chronological age by ≥5 years and aging velocity as the annual change in radiographic age from serial radiographs. Multivariable Cox and Fine-Gray models were used to estimate adjusted hazard ratios (HRs) for all-cause and cause-specific mortality. Mortality rate ratios were estimated using Poisson regression. Results A total of 421 894 adults were included (mean age, 47.4 years ± 8.8 [SD]; 227 427 [53.9%] male). During a median follow-up of 8.5 years, 6506 deaths occurred (953 cardiovascular, 3024 cancer, 1043 respiratory). Accelerated aging was associated with increased all-cause and cause-specific mortality, with stronger associations in female participants (<i>P</i> = .008 for interaction); the HRs for all-cause mortality were 1.26 (<i>P</i> < .001) for male participants and 1.52 (<i>P</i> < .001) for female participants. Among 179 667 individuals with three or more scans, aging velocity predicted mortality regardless of baseline status (adjusted cumulative mortality ratio per 1-SD increase: male participants, 1.24; female participants, 1.35; all <i>P</i> < .001). Compared with stable aging (1 year/year ± 0.5), decelerated velocity (<0.5 year/year) was associated with lower mortality risk (mortality rate ratios: male participants, 0.90, <i>P</i> = .18; female participants, 0.50, <i>P</i> < .001), whereas accelerated velocity (≥1.5 years/year) increased mortality risk (mortality rate ratios: male participants, 1.51; female participants, 1.71; both <i>P</i> < .001). Conclusion Radiographic age-based accelerated aging and aging velocity independently predicted all-cause and cause-specific mortality. <b>Keywords:</b> Conventional Radiography, Thorax, Epidemiology, Convolutional Neural Network <i>Supplemental material is available for this article.</i> © RSNA, 2026 See also the commentary by Babyn in this issue.</p>","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":" ","pages":"e250609"},"PeriodicalIF":20.1,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147595266","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ROADMAP: An Ontology of Medical AI Models and Datasets.","authors":"Abhinav Suri, Marcelo Straus Takahashi, Tara Retson, Ricardo A Gonzales, Seong Ho Park, Charles E Kahn","doi":"10.1148/ryai.260069","DOIUrl":"10.1148/ryai.260069","url":null,"abstract":"<p><p>Successful development, regulatory review, and clinical implementation of artificial intelligence (AI) systems in medicine require clear, unambiguous communication about AI models and datasets. The Radiology Ontology of AI Datasets, Models and Projects (ROADMAP) was developed to provide a machine-interpretable framework to describe medical AI resources by formally defining the attributes of AI models and datasets and their allowable values. ROADMAP builds upon generalized \"model cards\" and \"datasheets for datasets\" by incorporating features that support multimodal data, including medical images, structured data, and unstructured text. ROADMAP references concepts from widely used ontologies, coding schemes, and common data elements to improve the discoverability, interoperability, and reuse of AI resources. The ontology can facilitate matching of appropriate AI models with relevant datasets and support the detection of potential sources of bias in AI resources; it is available at <i><i>https://bioportal.bioontology.org/ontologies/ROADMAP</i></i>. <i>Supplemental material is available for this article.</i> © RSNA, 2026 See also special report on ROADMAP and metrics.</p>","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":" ","pages":"e260069"},"PeriodicalIF":20.1,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147436159","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AI Triage of Normal Chest Radiographs: A Silent Trial and Failure Analysis.","authors":"Mathew Storey, Anthony Chung, Jack Packer, Ann-Marie Bartsch, Anita Rhodes, Rafal Colta, Simon Rickaby, Christina Malamateniou, Geraldine Dean, Susan Shelmerdine","doi":"10.1148/ryai.250964","DOIUrl":"10.1148/ryai.250964","url":null,"abstract":"<p><p>Chest radiography is the most frequently performed imaging examination worldwide, and increasing demand has contributed to reporting delays in many health systems. This prospective multicenter silent trial evaluated the diagnostic performance of a commercially available artificial intelligence (AI) model for triaging normal chest radiographs across five National Health Service hospital sites in the United Kingdom over a 12-month period. A total of 63 083 adult chest radiographs were analyzed. The AI model classified 50 661 examinations (80%) as abnormal and 12 422 (20%) as normal. The model achieved 97% sensitivity, 35% specificity, 57% positive predictive value, and 94% negative predictive value for detecting abnormal chest radiographs. Expert review of discrepant cases, after exclusion of 412 natural language processing labeling errors, identified 31 clinically significant AI misses, corresponding to an estimated clinically significant miss rate of 0.05%. Most missed findings involved subtle or overlapping lesions. Concordance between the AI model and radiologist reports for normal examinations occurred in 18.5% of chest radiographs, indicating that nearly one-fifth of examinations could potentially be deprioritized for reporting. These findings suggest that AI-assisted triage of chest radiographs may help prioritize reporting workflows while maintaining a low rate of clinically significant missed findings, although further research is warranted to evaluate clinical implementation. <b>Keywords:</b> Artificial Intelligence, Chest Radiography, Computer-aided Diagnosis, Thorax <i>Supplemental material is available for this article.</i> © RSNA, 2026.</p>","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":" ","pages":"e250964"},"PeriodicalIF":20.1,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147783324","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Teaching MRI to Read the Report: Text-Image Alignment for Brain MRI at Scale.","authors":"Satyam Ghodasara","doi":"10.1148/ryai.250962","DOIUrl":"10.1148/ryai.250962","url":null,"abstract":"","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":"8 2","pages":"e250962"},"PeriodicalIF":13.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146120427","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fetal Brain in B-Mode: AIRFRAME Model Takes on Posterior Fossa Malformation Detection.","authors":"Patricia Piazza Rafful","doi":"10.1148/ryai.260042","DOIUrl":"10.1148/ryai.260042","url":null,"abstract":"","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":"8 2","pages":"e260042"},"PeriodicalIF":13.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147356701","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Interpretable Machine Learning Model Using Digitized US Features for Classifying Complex Thyroid Nodules.","authors":"Zhuyao Li, Yu Yan, Xiang Li, Kezhou Wu, Xiubo Lu","doi":"10.1148/ryai.250383","DOIUrl":"10.1148/ryai.250383","url":null,"abstract":"<p><p>Purpose To develop a digitized integrated feature-based interpretable machine learning classification model to accurately recognize complex thyroid nodules while efficiently diagnosing conventional thyroid nodules (thyroid nodules with typical benign or malignant US features). Materials and Methods Thyroid US images depicting pathologically confirmed nodules were retrospectively collected from seven medical centers in China (January 2011-December 2021). An interpretable classification model consisting of two independent masks was developed and defined as \"UltraMC.\" The front-end network was trained to identify conventional thyroid nodules using four digitized features, and the back-end network collected nodules classified as benign in the previous framework for secondary analysis to clarify their final diagnosis. UltraMC performance was evaluated using accuracy, sensitivity, specificity, and confusion matrices. Results The total dataset included 73 826 patients with thyroid US images (mean age, 45.56 years ± 11.21 [SD]; 54 398 female). Diagnostic accuracy of the front-end network for detecting conventional thyroid nodules was 92.9% (13 718 of 14 765), and accuracy of the back-end network for classifying mummified thyroid nodules (MTNs) was 88.5% (652 of 737). The overall diagnostic accuracy of the US MTN classification model (UltraMC) was 91.8% (14 228 of 15 502). The areas under the receiver operating characteristic curve of the front-end network and UltraMC in identifying conventional thyroid nodules were 0.98 (95% CI: 0.98, 0.98) and 0.96 (95% CI: 0.96, 0.97), respectively. Conclusion The proposed two-layer interpretable classification model achieved high diagnostic accuracy for both conventional and mummified thyroid nodules. These findings demonstrate that digitized US features integrated into a white box framework can effectively support classification of complex thyroid nodules. <b>Keywords:</b> Ultrasound, Head/Neck, Thyroid, Diagnosis, Convolutional Neural Network (CNN), K-Means, Random Forest, Thyroid Nodule, Interpretable, Digital, Mummified Thyroid Nodules <i>Supplemental material is available for this article.</i> © RSNA, 2026.</p>","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":" ","pages":"e250383"},"PeriodicalIF":20.1,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146120405","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Editor's Recognition Awards.","authors":"Charles E Kahn","doi":"10.1148/ryai.260178","DOIUrl":"https://doi.org/10.1148/ryai.260178","url":null,"abstract":"","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":"8 2","pages":"e260178"},"PeriodicalIF":13.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147436150","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}