Abstract
Foundation models are increasingly used as image feature extractors for mammography, but their robustness under external domain shift remains unclear. We benchmark 15 foundation-model backbones across breast density, BI-RADS severity, and cancer status using a unified frozen-backbone linear-probe protocol, training on 3 source datasets and evaluating on 12 task-compatible out-of-distribution (OOD) datasets after label harmonization. Mammography-specific vision-language models (Mammo-FM and MaMA) provide the strongest mean OOD performance, but robustness is not explained by mammography exposure alone. DINOv3 remains a competitive vision-only baseline, and mammography-adapted pretraining does not consistently improve generalization. Dataset-level analysis further shows that even leading models show heterogeneous performance across datasets. Feature-space inspection reveals that useful representations can preserve clinical signal while retaining dataset and acquisition structure. These findings highlight dataset-level OOD evaluation as a central criterion for assessing mammography representations.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/Deep_Brea3th_014.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: Not Submitted
Link to Open Review
Open Review Page: https://openreview.net/forum?id=rFaTFPqAo3
BibTex
@InProceedings{NguGia_Benchmarking_MICCAISAT2026,
author = { Nguyen, Giang AND Mehta, Raghav AND Stanley, Emma A. M. AND Xia, Tian AND Nguyen, Thi Hao AND Pham, Hieu AND Glocker, Ben},
title = { { Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17256},
month = {pending},
page = {pending}
}