DBT-DINO: Toward Foundation Model–Based Analysis of Digital Breast Tomosynthesis

Radiology 2026 Open access

Read full text
Authors: Felix J. Dorfner, Manon A. Dorster, Ryan Connolly, Oscar Gentilhomme, Edward Gibbs, Seth Andrew Wander, Thomas Schultz, Manisha Bahl, Dania Daye, Albert E. Kim, Christopher P. Bridge
DOI: 10.1148/radiol.254034
Cited by: 1
References: 25

Abstract

DBT-DINO, a foundation model for digital breast tomosynthesis (DBT) pretrained on 487 975 volumes from 27 990 patients, demonstrated the potential of self-supervised pretraining in DBT analysis.

Fields of Study & Subjects

Digital Radiography and Breast Imaging Anatomy and Medical Technology Medical Imaging Techniques and Applications

Publication details

Journal / source
Radiology
Publisher
Radiological Society of North America (RSNA)
Volume
320
Issue
2
Pages
e254034–e254034
Publication date
1 August 2026
Language
EN