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.
@article{arxiv.2512.00198,
title = {Mammo-FM: Breast-specific foundational model for Integrated Mammographic Diagnosis, Prognosis, and Reporting},
author = {Shantanu Ghosh and Vedant Parthesh Joshi and Rayan Syed and Param Budhraja and Aya Kassem and Katelyn C. Morrison and Alex Tang and Ho Cheung Aiden Wong and Abhishek Varshney and Payel Basak and Weicheng Dai and Judy Wawira Gichoya and Hari M. Trivedi and Imon Banerjee and Shyam Visweswaran and Clare B. Poynton and Kayhan Batmanghelich},
journal= {arXiv preprint arXiv:2512.00198},
year = {2026}
}