Radiology-Artificial Intelligence最新文献

{"title":"Breast Cancers Detected and Missed by AI-CAD: Results from the AI-STREAM Trial.","authors":"Yun-Woo Chang, Jung Kyu Ryu, Jin Kyung An, Nami Choi, Young Mi Park, Kyung Hee Ko","doi":"10.1148/ryai.250281","DOIUrl":"10.1148/ryai.250281","url":null,"abstract":"<p><p>Purpose To evaluate the characteristics of breast cancers detected and missed by artificial intelligence-based computer-assisted diagnosis (AI-CAD) during screening mammography. Materials and Methods This retrospective secondary analysis was conducted using data from the Artificial Intelligence for Breast Cancer Screening in Mammography trial (ClinicalTrials.gov: NCT05024591), a prospective, multicenter cohort study performed from 2021 to 2022. AI-CAD results were categorized into nine subgroups based on abnormality scores (in 10% increments). Positive predictive values of recall (PPV1s) were calculated for each subgroup and by breast density, and AI-CAD scores were compared with mammographic and pathologic features. Results A total of 24 543 women (mean age ± SD, 59.8 years ± 11.2), including two with bilateral cancer, were included; 148 cancers were confirmed by pathologic evaluation after 1 year of follow-up. AI-CAD results were negative in 23 010 cases (93.8%) and positive in 1535 (6.2%). The overall PPV1 was 8.7% (133 of 1535), with a sensitivity of 89.9% and specificity of 94.3%; PPV1 increased with higher abnormality scores but remained below 3% in groups 1 and 3 for dense breasts. AI-CAD detected 3.4% (five of 148) of cancers missed by radiologists but missed 8.1% (12 of 148) that were detected at radiologist recall. Abnormality scores were lower in patients presenting with mammographic asymmetry (<i>P</i> = .001) and luminal A subtype (<i>P</i> = .032). Conclusion AI-CAD shows potential to improve breast cancer detection in screening programs and to support radiologists in mammogram interpretation. Understanding the imaging and pathologic features of cancers detected or missed by AI-CAD may enhance its effective clinical application. <b>Keywords:</b> Breast Cancer, Mammography, AI CAD Clinical trial registration no. NCT05024591 © RSNA, 2025 See also commentary by Do and Bahl in this issue.</p>","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":" ","pages":"e250281"},"PeriodicalIF":13.2,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145378797","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":"Robust Brain Extraction Tool for Nonenhanced CT and CT Angiography: CTA-BET.","authors":"Mustafa Ahmed Mahmutoglu, Aditya Rastogi, Yeong Chul Yun, Sanya Middha, Julius Kernbach, Martha Foltyn-Dumitru, Gianluca Brugnara, Philipp Vollmuth, Alexander Radbruch, Martin Bendszus, Marianne Schell","doi":"10.1148/ryai.240847","DOIUrl":"10.1148/ryai.240847","url":null,"abstract":"<p><p>Purpose To develop and evaluate a deep learning-based brain extraction model, CTA-BET, capable of providing accurate brain segmentation for CT angiography (CTA) and non-contrast-enhanced CT (NCCT) images. Materials and Methods In this retrospective study, CTA-BET was trained using CTA data from multi-institutional cohorts (<i>n</i> = 100 patients) and validated on an external CTA dataset (<i>n</i> = 50 patients). NCCT validation was performed using the publicly available CQ500 dataset (<i>n</i> = 132 patients). The model's performance was compared with five benchmark noncommercial brain extraction tools. Dice score, Hausdorff distance, and <i>z</i> score-normalized histograms were used to evaluate segmentation performance. Results The CTA-BET model outperformed all benchmark models, achieving a mean Dice score of 0.99 (95% CI: 0.99, 0.99) on CTA data (<i>P</i> < .001 for all comparisons) and 0.98 (95% CI: 0.98, 0.99) on NCCT images (<i>P</i> < .001 for all comparisons). In terms of Hausdorff distance, CTA-BET demonstrated higher performance compared with other benchmark tools on CTA images (<i>P</i> < .001 for all comparisons). Conclusion CTA-BET outperformed benchmark brain extraction tools on both CTA and NCCT images, providing a robust and accurate solution that could enhance automated imaging analysis in clinical and research settings. <b>Keywords:</b> CT-Angiography, Head/Neck, Brain/Brain Stem, Computer Applications-3D, Comparative Studies, Experimental Investigations, Technology Assessment, Segmentation, Convolutional Neural Network (CNN) <i>Supplemental material is available for this article.</i> © RSNA 2025.</p>","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":" ","pages":"e240847"},"PeriodicalIF":13.2,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145379122","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":"The Economic Realism of AI in Radiology.","authors":"Alireza Amindarolzarbi, Eliot L Siegel","doi":"10.1148/ryai.250925","DOIUrl":"10.1148/ryai.250925","url":null,"abstract":"","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":"8 1","pages":"e250925"},"PeriodicalIF":13.2,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145769479","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":"Rethinking Adnexal Mass Diagnosis with Dynamic Contrast-enhanced US and Deep Learning.","authors":"Thomas Huber, Lisa C Adams","doi":"10.1148/ryai.250977","DOIUrl":"10.1148/ryai.250977","url":null,"abstract":"","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":"8 1","pages":"e250977"},"PeriodicalIF":13.2,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145669988","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":"Adnexal Lesion Discrimination Using Deep Learning Analysis of Dynamic Contrast-enhanced US Images.","authors":"Manli Wu, Hong Yang, Ying Chen, Shuangyu Wu, Tianming Liang, Man Zhang, Enze Qu, Xiaofeng Sun, Rui Zhang, Mu Liang, Li Xiao, Hong Wen, Ruili Wang, Tingting Liu, Xiaotao Meng, Manting Su, Ying Wang, Jian Gu, Sijia Chen, Yaping Wang, Qinghong Zhao, Juan Liu, Ping Cheng, Ruixuan Wang, Jianfang Hu, Xinling Zhang","doi":"10.1148/ryai.240786","DOIUrl":"10.1148/ryai.240786","url":null,"abstract":"<p><p>Purpose To develop a multimodality deep learning model (Ovarian Cancer Network [OCNet]) using dynamic contrast-enhanced US images to classify adnexal lesions. Materials and Methods This retrospective study included patients with pathologically confirmed adnexal lesions detected at US across 14 hospitals in China between January 2018 and July 2023. Data were divided into the training set (<i>n</i> = 275), internal testing set (<i>n</i> = 57), and external testing set (<i>n</i> = 63). Two deep learning models (OCNet_manual and OCNet_automated) were developed and compared with Ovarian-Adnexal Reporting and Data System (O-RADS) US and the Assessment of Different Neoplasias in the Adnexa (ADNEX) model. Diagnostic performances of radiologists with and without assistance of OCNet were also assessed. Results A total of 395 female patients (median age, 43 years; IQR, 31-55 years) were included (252 benign and 143 malignant lesions). OCNet_manual and OCNet_automated achieved an area under the receiver operating characteristic curve (AUC) of 0.94 (95% CI: 0.89, >0.99) and 0.91 (95% CI: 0.83, 0.99), respectively, outperforming O-RADS US (AUC, 0.79; 95% CI: 0.68, 0.89; <i>P</i> = .002 and <i>P</i> = .03, respectively) and the ADNEX model (AUC, 0.86; 95% CI: 0.77, 0.95; <i>P</i> = .04 and <i>P</i> = .36, respectively). Additionally, the assistance of OCNet enhanced diagnostic performance for junior radiologists, improving the average AUC from 0.86 to 0.94 and the average specificity from 52% to 73%. Conclusion The OCNet model achieved higher performance than O-RADS US and the ADNEX model for classifying adnexal lesions and improved the diagnostic performance of junior radiologists. <b>Keywords:</b> Adnexal Lesion, Deep Learning, Contrast-enhanced US, Multimodal <i>Supplemental material is available for this article.</i> © RSNA 2025 See also commentary by Huber and Adams in this issue.</p>","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":" ","pages":"e240786"},"PeriodicalIF":13.2,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145446105","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":"Gastric Neoplasm Detection at Contrast-enhanced CT with Deep Learning.","authors":"Xin Chen, Yingda Xia, Lisha Yao, Suyun Li, Yanting Liang, Zhilin Zheng, Mingze Yuan, Jiawen Yao, Ruiping Zhang, Wenting Tu, Yongmei Guo, Dan Liang, Zelan Ma, Dandan Chen, Lisha Lai, Xiaowen Xie, Yifan Yu, Yanlian Jia, Ling Zhang, Zaiyi Liu","doi":"10.1148/ryai.250145","DOIUrl":"10.1148/ryai.250145","url":null,"abstract":"<p><p>Purpose To develop and validate a deep learning-based approach, Gastric Neoplasm Detection with Artificial Intelligence (GANDA), for automated detection, diagnosis, and segmentation of gastric neoplasms at clinical routine contrast-enhanced CT. Materials and Methods In this retrospective study, GANDA, a joint segmentation and classification three-dimensional deep learning model, was developed by using CT data of 1683 patients with or without gastric neoplasms from one hospital between January 2007 and June 2019. Performance was evaluated in an internal test cohort (January 2019 to June 2019), an external test cohort (April 2015 to December 2022) from four external centers, and a real-world test cohort (March 2023 to May 2023) from one hospital. Model performance for tumor detection and diagnosis was assessed using receiver operating characteristic analysis and compared with that of 10 board-certified radiologists (median experience, 8.5 years [IQR: 5.25-14]). Model segmentation performance was assessed using the Dice coefficient. Results A total of 4606 patients were included in the study (median age, 57 years [IQR: 48-66]; 2554 male patients). In the internal test cohort (<i>n</i> = 266), GANDA achieved 87.3% sensitivity and 87.2% specificity for tumor detection. The model demonstrated significantly higher diagnostic accuracy (top-1 accuracy, 85.3%; 95% CI: 81.2, 89.1) compared with radiologists (mean accuracy, 74.2%; 95% CI: 70.5, 77.6; <i>P</i> = .002). In the external test cohort (<i>n</i> = 2657), GANDA distinguished between patients with gastric neoplasms and controls with 77.4% sensitivity and 89.8% specificity. The mean Dice coefficient in the internal test cohort was 0.52 for gastric cancer and 0.45 for non-gastric cancer. In the real-world test cohort (<i>n</i> = 7695), GANDA achieved 83.2% sensitivity and 93.1% specificity for tumor detection. Conclusion GANDA enabled the detection and segmentation of gastric neoplasms at routine clinical CT scans. <b>Keywords:</b> CT, Computed Tomography, Abdomen/GI, Stomach, Screening, Gastric Neoplasm, Deep Learning <i>Supplemental material is available for this article.</i> ©RSNA, 2025.</p>","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":" ","pages":"e250145"},"PeriodicalIF":13.2,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145606743","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":"Rethinking Privacy in Medical Imaging AI: From Metadata and Pixel-Level Identification Risks to Federated Learning and Synthetic Data Challenges.","authors":"Konstantina Giouroukou, Kostas Marias, Manolis Tsiknakis, Michail E Klontzas","doi":"10.1148/ryai.250273","DOIUrl":"10.1148/ryai.250273","url":null,"abstract":"<p><p>Metadata, which refers to nonimage information such as patient identifiers, acquisition parameters, and institutional details, have long been the primary focus of de-identification efforts when constructing datasets for artificial intelligence applications in medical imaging. However, it is now evident that information intrinsic to the image itself, at the pixel level (eg, intensity values), can also be exploited by deep learning models, potentially revealing sensitive patient data and posing privacy risks. This report discusses both metadata and sources of identifiable information in medical imaging studies, highlighting the potential risks of overlooking their presence. Privacy-preserving approaches such as federated learning and synthetic data generation are also reviewed, with emphasis on their limitations-particularly vulnerabilities to model inversion and inference attacks-that must be considered when developing and deploying artificial intelligence in medical imaging. <b>Keywords:</b> Privacy, Metadata, Synthetic, Federated Learning, Anonymization De-identification ©RSNA, 2025.</p>","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":" ","pages":"e250273"},"PeriodicalIF":13.2,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145606753","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":"An Explainable Deep Learning Model for Focal Liver Lesion Diagnosis Using Multiparametric MRI.","authors":"Zhehan Shen, Lingzhi Chen, Lilong Wang, Shunjie Dong, Fakai Wang, Yaning Pan, Jiahao Zhou, Yikun Wang, Xinxin Xu, Huanhuan Chong, Huimin Lin, Weixia Li, Ruokun Li, Haihong Ma, Jing Ma, Yixing Yu, Lianjun Du, Xiaosong Wang, Shaoting Zhang, Fuhua Yan","doi":"10.1148/ryai.240531","DOIUrl":"10.1148/ryai.240531","url":null,"abstract":"<p><p>Purpose To assess the effectiveness of an explainable deep learning model, developed using multiparametric MRI features, in improving diagnostic accuracy and efficiency of radiologists for classification of focal liver lesions (FLLs). Materials and Methods FLLs 1 cm or larger in diameter at multiparametric MRI were included in the study. The nn-Unet and Liver Imaging Feature Transformer models were developed using retrospective data from the Ruijin Hospital (January 2018-August 2023). The nnU-Net was used for lesion segmentation and the Liver Imaging Feature Transformer model for FLL classification. External testing was performed on data from the Xinjiang Production and Construction Corps Hospital, the First Affiliated Hospital of Soochow University, and Xinrui Hospital (January 2018-December 2023), with a prospective test set obtained from January to April 2024. Model performance was compared with radiologists, and impact of model assistance on junior and senior radiologist performance was assessed. Evaluation metrics included the Dice similarity coefficient and accuracy. Results A total of 2131 individuals with FLLs (mean age, 56 years ± 12 [SD]; 1476 female patients) were included in the training, internal test, external test, and prospective test sets. Average Dice similarity coefficient values for liver and tumor segmentation across the three test sets were 0.98 and 0.96, respectively. Average accuracy for features and lesion classification across the three test sets were 93% and 97%, respectively. Readings assisted by the Liver Imaging Feature Transformer model improved diagnostic accuracy (average 5.3% increase, <i>P</i> < .001), reduced reading time (average 34.5 seconds decrease, <i>P</i> < .001), and enhanced confidence (average 0.3-point increase, <i>P</i> < .001) of junior radiologists. Conclusion The proposed deep learning model accurately detected and classified FLLs, improving diagnostic accuracy and efficiency of junior radiologists. <b>Keywords:</b> Liver, MR-Dynamic Contrast Enhanced, Convolutional Neural Network (CNN), Deep Learning Algorithms, Machine Learning Algorithms, Feature Detection, Vision, Application Domain <i>Supplemental material is available for this article.</i> © RSNA, 2025 See also commentary by Adams and Bressem in this issue.</p>","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":" ","pages":"e240531"},"PeriodicalIF":13.2,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145030897","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":"Let's Agree to Be Wrong: Transforming Alzheimer Disease Diagnosis.","authors":"Ilya Nasrallah","doi":"10.1148/ryai.250686","DOIUrl":"10.1148/ryai.250686","url":null,"abstract":"","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":"7 6","pages":"e250686"},"PeriodicalIF":13.2,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145201639","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":"Radiologist and AI Concordance in Screening Mammography and Association with Future Breast Cancer Risk.","authors":"Eun Young Kim, Eun Kyung Park, Mi-Ri Kwon, Minjeong Kim, Junhee Park, Jeonggyu Kang, Yoosun Cho, Sanghyup Lee, Minji Song, Ki Hwan Kim, Tae Soo Kim, Hyeonsoo Lee, Ria Kwon, Ga-Young Lim, JunHyeok Choi, Soo-Youn Ham, Shin Ho Kook, Yoosoo Chang, Seungho Ryu","doi":"10.1148/ryai.240804","DOIUrl":"10.1148/ryai.240804","url":null,"abstract":"<p><p>Purpose To evaluate the association between radiologist and stand-alone AI concordance in screening mammography interpretations and future breast cancer risk and to assess how breast density influences this relationship. Materials and Methods This retrospective study included Korean women who underwent digital screening mammography between January 2009 and December 2018. Incidental breast cancers, defined as those diagnosed within 1 year of screening, were excluded using the National Cancer Registry data. A commercial AI system retrospectively analyzed mammograms, with a 10% malignancy probability threshold. Patients were categorized into four groups based on AI-radiologist concordance: Concordant-Negative, Radiologist-Positive/AI-Negative, Radiologist-Negative/AI-Positive, and Concordant-Positive. Breast density was categorized using Breast Imaging Reporting and Data System classification. Cox proportional hazards models estimated adjusted hazard ratios (HRs) and 95% CIs. Results Over a median 7.3-year follow-up, 1011 breast cancers occurred among 82 899 women (mean age, 43.4 years ± 8.6 [SD]). Breast cancer incidence was the highest in the Concordant-Positive group (5-year cumulative incidence, 37.4 per 1000 person-years) and the lowest in the Concordant-Negative group (5.9 per 1000 person-years). Compared with the Concordant-Negative group, adjusted HRs for incidental breast cancer were 2.30 (<i>P</i> < .001) for the Radiologist-Negative/AI-Positive, 1.15 (<i>P</i> = .17) for the Radiologist-Positive/AI-Negative, and 4.51 (<i>P</i> < .001) for the Concordant-Positive groups. Risk increase in the Concordant-Positive group was consistent across breast densities; in dense breasts, elevated risk occurred only with positive AI. Conclusion Positive screening mammography findings identified by both radiologists and stand-alone AI (Concordant-Positive group) were associated with he highest 5-year breast cancer incidence of 3.74%, exceeding the 3% threshold for considering chemoprevention or supplemental imaging. <b>Keywords:</b> Mammography, Breast Neoplasms, Artificial Intelligence, Screening, Concordance <i>Supplemental material is available for this article.</i> © RSNA, 2025.</p>","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":" ","pages":"e240804"},"PeriodicalIF":13.2,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145293781","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}