Mammo-FM: Breast-specific foundational model for Integrated Mammographic Diagnosis, Prognosis, and Reporting

TL;DR

Mammo-FM is a pioneering breast-specific foundation model trained on a large, diverse dataset that enhances mammography diagnosis, prognosis, and reporting with improved interpretability and outperforms generalist models.

Contribution

This paper introduces Mammo-FM, the first dedicated foundation model for mammography, integrating multiple clinical tasks within a single, efficient framework.

Findings

Mammo-FM outperforms state-of-the-art generalist models on multiple benchmarks.

It achieves high interpretability through image-text alignment.

The model operates efficiently with only one-third of the parameters of comparable models.

Abstract

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.