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

arXiv: https://arxiv.org/abs/2512.00198 · HTML: https://mlsanity.com/paper/2512.00198/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 51 references that are in the map.
- First posted on arXiv 28 Nov 2025.

## Builds on (most cited first, 21 of 21)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [Contrastive Learning of Medical Visual Representations from Paired Images and Text](https://mlsanity.com/paper/2010.00747/) (2020)
- [RegionCLIP: Region-based Language-Image Pretraining](https://mlsanity.com/paper/2112.09106/) (2021)
- [MedCLIP: Contrastive Learning from Unpaired Medical Images and Text](https://mlsanity.com/paper/2210.10163/) (2022)
- [MedGemma Technical Report](https://mlsanity.com/paper/2507.05201/) (2025)
- [Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm](https://mlsanity.com/paper/2110.05208/) (2021)
- [Generalist Foundation Models from a Multimodal Dataset for 3D Computed Tomography](https://mlsanity.com/paper/2403.17834/) (2024)
- [MedKLIP: Medical Knowledge Enhanced Language-Image Pre-Training in Radiology](https://mlsanity.com/paper/2301.02228/) (2023)
- [GREEN: Generative Radiology Report Evaluation and Error Notation](https://mlsanity.com/paper/2405.03595/) (2024)
- [VinDr-Mammo: A large-scale benchmark dataset for computer-aided diagnosis in full-field digital mammography](https://mlsanity.com/paper/2203.11205/) (2022)
- [CXR-CLIP: Toward Large Scale Chest X-ray Language-Image Pre-training](https://mlsanity.com/paper/2310.13292/) (2023)
- [MedSyn: Text-guided Anatomy-aware Synthesis of High-Fidelity 3D CT Images](https://mlsanity.com/paper/2310.03559/) (2023)
- [ViLLA: Fine-Grained Vision-Language Representation Learning from Real-World Data](https://mlsanity.com/paper/2308.11194/) (2023)
- [LADDER: Language-Driven Slice Discovery and Error Rectification in Vision Classifiers](https://mlsanity.com/paper/2408.07832/) (2024)

## Built on by (most cited first, 5 of 5)

- [Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift](https://mlsanity.com/paper/2607.10358/) (2026)
- [Mammography Foundation Models for Opportunistic Prediction of Major Adverse Cardiovascular Events](https://mlsanity.com/paper/2609.19385/) (2026)
- [Mammo-LIFE: Longitudinal Mammographic Imaging and Clinical Feature Enrichment for Post-Radiotherapy Outcome Prediction](https://mlsanity.com/paper/2609.26443/) (2026)
- [Foundation model embeddings capture pre-diagnostic changes on screening mammograms](https://mlsanity.com/paper/2609.26605/) (2026)
- [MammoClaw: Towards Skill-Evolving Agent Harness for Breast Cancer Mammography Analysis](https://mlsanity.com/paper/2609.31789/) (2026)

## Abstract (arXiv)

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.