Qian Xuejun, Pei Jing, Han Chunguang, Liang Zhiying, Zhang Gaosong, Chen Na, Zheng Weiwei, Meng Fanlun, Yu Dongsheng, Chen Yixuan, Sun Yiqun, Zhang Hanqi, Qian Wei, Wang Xia, Er Zhuoran, Hu Chenglu, Zheng Hui, Shen Dinggang
School of Biomedical Engineering, ShanghaiTech University, Shanghai, China.
State Key Laboratory of Advanced Medical Materials and Devices, ShanghaiTech University, Shanghai, China.
Nat Biomed Eng. 2025 Mar;9(3):356-370. doi: 10.1038/s41551-024-01302-7. Epub 2024 Dec 4.
Machine learning models for the diagnosis of breast cancer can facilitate the prediction of cancer risk and subsequent patient management among other clinical tasks. For the models to impact clinical practice, they ought to follow standard workflows, help interpret mammography and ultrasound data, evaluate clinical contextual information, handle incomplete data and be validated in prospective settings. Here we report the development and testing of a multimodal model leveraging mammography and ultrasound modules for the stratification of breast cancer risk based on clinical metadata, mammography and trimodal ultrasound (19,360 images of 5,216 breasts) from 5,025 patients with surgically confirmed pathology across medical centres and scanner manufacturers. Compared with the performance of experienced radiologists, the model performed similarly at classifying tumours as benign or malignant and was superior at pathology-level differential diagnosis. With a prospectively collected dataset of 191 breasts from 187 patients, the overall accuracies of the multimodal model and of preliminary pathologist-level assessments of biopsied breast specimens were similar (90.1% vs 92.7%, respectively). Multimodal models may assist diagnosis in oncology.
用于乳腺癌诊断的机器学习模型可以促进癌症风险预测以及其他临床任务中的后续患者管理。为了使这些模型能够影响临床实践，它们应该遵循标准工作流程，帮助解读乳房X光检查和超声数据，评估临床背景信息，处理不完整数据，并在前瞻性环境中进行验证。在此，我们报告了一种多模态模型的开发和测试，该模型利用乳房X光检查和超声模块，基于来自多个医疗中心和扫描仪制造商的5025例手术病理确诊患者的临床元数据、乳房X光检查和三模态超声（5216个乳房的19360张图像）对乳腺癌风险进行分层。与经验丰富的放射科医生的表现相比，该模型在将肿瘤分类为良性或恶性方面表现相似，在病理水平的鉴别诊断方面表现更优。在一个前瞻性收集的包含187例患者的191个乳房的数据集上，多模态模型和对活检乳房标本的初步病理学家水平评估的总体准确率相似（分别为90.1%和92.7%）。多模态模型可能有助于肿瘤学诊断。
