An interpretable AI system reduces false-positive MRI diagnoses by stratifying high-risk breast lesions

作者：Yanting Liang, Zhitao Wei, Dai Yi, Xiaobo Chen, Siyao DU, Chinting Wong, Zeyan Xu, Weibo Gao, Chu Han, Kexin Chen, Ke Han, Jiayi Liao, Yuelang Zhang, Lina Zhang, Siyao Du, Zaiyi Liu, Yan Zhang, Yan Zhang, Ying Wang, Changhong Liang, Zhenwei Shi · 发表于：Nature Communications · 年份：2026 · DOI：10.1038/s41467-026-69212-7 · 被引用次数：3 · 研究领域：MRI in cancer diagnosis、Radiomics and Machine Learning in Medical Imaging、AI in cancer detection

Breast cancer diagnosis using magnetic resonance imaging remains limited by high false-positive rates and substantial inter-reader variability, especially for lesions classified as Breast Imaging Reporting and Data System (BI-RADS) category 4, often leading to unnecessary biopsies. Here we show that the BI-RADS 4 Lesions Analysis System (BL4AS), an artificial intelligence system powered by foundation models and leveraging the rich spatiotemporal information of dynamic contrast-enhanced MRI, addresses these diagnostic challenges. Developed on a multicenter dataset of 2,803 lesions from 2,686 female patients, BL4AS demonstrates robust performance with areas under the curve of 0.892-0.930 and significantly outperforms radiologists in specificity (0.889 versus 0.491). BL4AS-assisted interpretation significantly improves diagnostic accuracy for both senior and junior radiologists, reducing inter-reader variability by 24.5% and decreasing false-positive rates by 27.3%. BL4AS further stratifies lesions into subcategories (4 A, 4B and 4 C) for refined risk assessment, offering a practical tool for precision breast cancer management. Diagnosing breast cancer through MRI is limited by high false-positive rates and inter- reader variability, leading to unnecessary biopsies. In here, the authors find that the BI-RADS 4 Lesions Analysis System (BL4AS) model improves diagnostic accuracy and reduces unnecessary biopsies as well as inter-reader variability