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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ghosh, Shantanu, Joshi, Vedant Parthesh, Syed, Rayan, Budhraja, Param, Kassem, Aya, Morrison, Katelyn C., Tang, Alex, Wong, Ho Cheung Aiden, Varshney, Abhishek, Basak, Payel, Dai, Weicheng, Gichoya, Judy Wawira, Trivedi, Hari M., Banerjee, Imon, Visweswaran, Shyam, Poynton, Clare B., Batmanghelich, Kayhan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914493975494656
author Ghosh, Shantanu
Joshi, Vedant Parthesh
Syed, Rayan
Budhraja, Param
Kassem, Aya
Morrison, Katelyn C.
Tang, Alex
Wong, Ho Cheung Aiden
Varshney, Abhishek
Basak, Payel
Dai, Weicheng
Gichoya, Judy Wawira
Trivedi, Hari M.
Banerjee, Imon
Visweswaran, Shyam
Poynton, Clare B.
Batmanghelich, Kayhan
author_facet Ghosh, Shantanu
Joshi, Vedant Parthesh
Syed, Rayan
Budhraja, Param
Kassem, Aya
Morrison, Katelyn C.
Tang, Alex
Wong, Ho Cheung Aiden
Varshney, Abhishek
Basak, Payel
Dai, Weicheng
Gichoya, Judy Wawira
Trivedi, Hari M.
Banerjee, Imon
Visweswaran, Shyam
Poynton, Clare B.
Batmanghelich, Kayhan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_00198
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Mammo-FM: Breast-specific foundational model for Integrated Mammographic Diagnosis, Prognosis, and Reporting
Ghosh, Shantanu
Joshi, Vedant Parthesh
Syed, Rayan
Budhraja, Param
Kassem, Aya
Morrison, Katelyn C.
Tang, Alex
Wong, Ho Cheung Aiden
Varshney, Abhishek
Basak, Payel
Dai, Weicheng
Gichoya, Judy Wawira
Trivedi, Hari M.
Banerjee, Imon
Visweswaran, Shyam
Poynton, Clare B.
Batmanghelich, Kayhan
Computer Vision and Pattern Recognition
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.
title Mammo-FM: Breast-specific foundational model for Integrated Mammographic Diagnosis, Prognosis, and Reporting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.00198