Peer-Reviewed Publication
Radiology2026;320(2):e254034.August 1, 2026Journal Article
DBT-DINO: Toward Foundation Model-Based Analysis of Digital Breast Tomosynthesis.
Felix J Dorfner1,2, Manon A Dorster1, Ryan Connolly3, Oscar Gentilhomme1,4, Edward Gibbs3, Seth Wander5, Thomas Schultz3, Manisha Bahl6, Dania Daye7, Albert E Kim1,5, Christopher P Bridge1,3
1Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital and Harvard Medical School, 149 Thirteenth St, Charlestown, MA 02129.
2Department of Radiology, Charité - Universitätsmedizin Berlin corporate member of Freie Universität Berlin and Humboldt Universität zu Berlin, Berlin, Germany.
3Mass General Brigham Data Science Office, Boston, Mass.
4Department of Computer Science, Institute for Machine Learning, ETH Zürich, Zürich, Switzerland.
5Massachusetts General Hospital Cancer Center and Harvard Medical School, Boston, Mass.
6Department of Radiology, Massachusetts General Hospital, Boston, Mass.
7Department of Radiology, University of Wisconsin School of Medicine and Public Health, Madison, Wis.
Abstract
Background Foundation models show promise in medical imaging but remain underexplored in three-dimensional modalities. Despite the adoption of digital breast tomosynthesis (DBT) in breast cancer screening, no dedicated foundation model currently exists for this modality. Purpose To develop and evaluate a foundation model for DBT (DBT-DINO) and assess the impact of domain-specific pretraining acros…
Create a free account to keep reading
Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.
Want unlimited research access? See Pro plans