{"ID":6536459,"CreatedAt":"2026-07-14T01:21:01.169441415Z","UpdatedAt":"2026-07-14T15:22:39.611211464Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.10358","arxiv_id":"2607.10358","title":"Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift","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. Our code is publicly available: https://github.com/biomedia-mira/mammo-ood.","short_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...","url_abs":"https://arxiv.org/abs/2607.10358","url_pdf":"https://arxiv.org/pdf/2607.10358v1","authors":"[\"Giang Nguyen\",\"Raghav Mehta\",\"Emma A. M. Stanley\",\"Tian Xia\",\"Thi Hao Nguyen\",\"Hieu Pham\",\"Ben Glocker\"]","published":"2026-07-11T15:31:47Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"Language Model\"]","has_code":false,"code_links":[{"ID":614169,"CreatedAt":"2026-07-14T01:21:01.169441415Z","UpdatedAt":"2026-07-14T01:21:01.169441415Z","DeletedAt":null,"paper_id":6536459,"paper_url":"https://arxiv.org/abs/2607.10358","paper_title":"Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift","repo_url":"https://github.com/biomedia-mira/mammo-ood","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}