DOI: 10.1148/radiol.254034 ISSN: 0033-8419
DBT-DINO: Toward Foundation Model–Based Analysis of Digital Breast Tomosynthesis
Felix J. Dorfner, Manon A. Dorster, Ryan Connolly, Oscar Gentilhomme, Edward Gibbs, Seth Wander, Thomas Schultz, Manisha Bahl, Dania Daye, Albert E. Kim, Christopher P. BridgeDBT-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.