首个乳腺影像通用模型，统一诊断、定位与报告生成
Mammo-FM: Breast-specific foundational model for Integrated Mammographic Diagnosis, Prognosis, and Reporting
- 基于14万患者数据训练，专为乳腺影像设计的通用模型
- 在多种任务中优于现有通用模型，参数少三分之一却更高效
- 适合临床医生和研究人员用于乳腺癌诊断与报告自动化
乳腺癌是全球女性主要死因之一。我们提出Mammo-FM，首个专为乳腺摄影设计的通用模型，基于迄今最大最多样化的数据集——来自美国四家机构的140,677名患者（共821,326张钼靶片）进行预训练。Mammo-FM为乳腺影像核心临床任务提供统一框架，涵盖癌症诊断、病灶定位、结构化报告生成及癌症风险预测。其图像与文本的对齐机制实现视觉与文本双重可解释性，提升透明度与临床可审计性，助力真实场景落地。我们在分布内与分布外数据集上严格评估该模型在诊断、预后与报告生成任务中的表现。尽管处理原始分辨率图像且仅使用现有顶尖通用模型约三分之一的参数量，Mammo-FM仍持续优于多个公开与私有基准。结果表明，围绕临床任务全谱系设计的领域专用通用模型具有显著效率与价值，并强调领域对齐评估的重要性。
原文摘要 · Abstract (English)
Breast cancer is one of the leading causes of death among women worldwide. We introduce Mammo-FM, the first foundation model specifically for mammography, pretrained on the largest and most diverse dataset to date - 140,677 patients (821,326 mammograms) across four U.S. institutions. Mammo-FM provides a unified foundation for core clinical tasks in breast imaging, including cancer diagnosis, pathology localization, structured report generation, and cancer risk prognosis within a single framework. Its alignment between images and text enables both visual and textual interpretability, improving transparency and clinical auditability, which are essential for real-world adoption. We rigorously evaluate Mammo-FM across diagnosis, prognosis, and report-generation tasks in in- and out-of-distribution datasets. Despite operating on native-resolution mammograms and using only one-third of the parameters of state-of-the-art generalist FMs, Mammo-FM consistently outperforms them across multiple public and private benchmarks. These results highlight the efficiency and value of domain-specific foundation models designed around the full spectrum of tasks within a clinical domain and emphasize the importance of rigorous, domain-aligned evaluation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。