MammoDINO: Anatomically Aware Self-Supervision for Mammographic Images

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Sicheng, Wu, Lei, Xiao, Cao, Bhatia, Parminder, Kass-Hout, Taha
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909843620626432
author Zhou, Sicheng
Wu, Lei
Xiao, Cao
Bhatia, Parminder
Kass-Hout, Taha
author_facet Zhou, Sicheng
Wu, Lei
Xiao, Cao
Bhatia, Parminder
Kass-Hout, Taha
contents Self-supervised learning (SSL) has transformed vision encoder training in general domains but remains underutilized in medical imaging due to limited data and domain specific biases. We present MammoDINO, a novel SSL framework for mammography, pretrained on 1.4 million mammographic images. To capture clinically meaningful features, we introduce a breast tissue aware data augmentation sampler for both image-level and patch-level supervision and a cross-slice contrastive learning objective that leverages 3D digital breast tomosynthesis (DBT) structure into 2D pretraining. MammoDINO achieves state-of-the-art performance on multiple breast cancer screening tasks and generalizes well across five benchmark datasets. It offers a scalable, annotation-free foundation for multipurpose computer-aided diagnosis (CAD) tools for mammogram, helping reduce radiologists' workload and improve diagnostic efficiency in breast cancer screening.
format Preprint
id arxiv_https___arxiv_org_abs_2510_11883
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MammoDINO: Anatomically Aware Self-Supervision for Mammographic Images
Zhou, Sicheng
Wu, Lei
Xiao, Cao
Bhatia, Parminder
Kass-Hout, Taha
Computer Vision and Pattern Recognition
Artificial Intelligence
1.2
Self-supervised learning (SSL) has transformed vision encoder training in general domains but remains underutilized in medical imaging due to limited data and domain specific biases. We present MammoDINO, a novel SSL framework for mammography, pretrained on 1.4 million mammographic images. To capture clinically meaningful features, we introduce a breast tissue aware data augmentation sampler for both image-level and patch-level supervision and a cross-slice contrastive learning objective that leverages 3D digital breast tomosynthesis (DBT) structure into 2D pretraining. MammoDINO achieves state-of-the-art performance on multiple breast cancer screening tasks and generalizes well across five benchmark datasets. It offers a scalable, annotation-free foundation for multipurpose computer-aided diagnosis (CAD) tools for mammogram, helping reduce radiologists' workload and improve diagnostic efficiency in breast cancer screening.
title MammoDINO: Anatomically Aware Self-Supervision for Mammographic Images
topic Computer Vision and Pattern Recognition
Artificial Intelligence
1.2
url https://arxiv.org/abs/2510.11883