Predicting 5-Year Breast Cancer Risk From Longitudinal Digital Breast Tomosynthesis
Background: Imaging-based breast cancer risk prediction models primarily use full-field digital mammography (FFDM). Although digital breast tomosynthesis (DBT) has become a predominant screening modality in the United States, its potential for long-term breast cancer risk prediction remains underexplored. Objective: The aim of this study was to develop and evaluate a deep learning model that uses longitudinal DBT examinations to predict long-term breast cancer risk. Methods: This retrospective study included 313,335 DBT examinations from 161,077 women (mean age, 58.5 ± 11.7 years) between January 2016 and August 2020 at a single health institution. A DBT-based risk prediction (DRP) model was developed to estimate 2- to 5-year breast cancer risk using longitudinal DBT examinations, patient age, and breast density. Model performance was compared with a single-timepoint DBT model, the Mirai model using same-day FFDM, and the Tyrer-Cuzick model using the AUC, time-dependent concordance index, and integrated Brier score. Results: In an independent test set (n = 34,570), the longitudinal DRP model achieved a 5-year AUC of 0.721 (95% CI, 0.698–0.744), improving on the single-timepoint DRP model (AUC, 0.707; 95% CI, 0.683–0.730; p < .001) and the Mirai model (AUC, 0.687; 95% CI, 0.663–0.710; p < .001). In a matched case-control cohort (n = 432), the DRP model achieved a 5-year AUC of 0.676 (95% CI, 0.626–0.726), compared with 0.563 (95% CI, 0.509–0.619; p < .001) for the Tyrer-Cuzick model. Among examinations of women with extremely dense breasts, the model classified 39.7% (746/1877) as average risk, with an observed 5-year cancer incidence of 0.8% (6/746). Among examinations of women with fatty breasts, the model classified 14.8% (386/2605) as high risk, with an observed 5-year cancer incidence of 2.6% (10/386). Conclusion: A deep learning model using longitudinal DBT examinations improved long-term breast cancer risk prediction compared with FFDM-based and clinical risk models. Clinical Impact: Longitudinal DBT-based risk prediction has the potential to inform dynamic risk assessment using screening images and to support future personalized screening strategies.
Authors
- Yiqiu Shen (ORCID: https://orcid.org/0000-0002-7726-2514)
- Krzysztof J. Geras (ORCID: https://orcid.org/0000-0003-0549-1446)
- Yanqi Xu (ORCID: https://orcid.org/0009-0003-8713-8853)
- Jungkyu Park (ORCID: https://orcid.org/0000-0001-5117-9651)
- Linda P. Moy (ORCID: https://orcid.org/0000-0001-9564-9360)
- Freya Ruth Schnabel (ORCID: https://orcid.org/0000-0002-6393-7453)
- Laura C. Heacock (ORCID: https://orcid.org/0000-0002-0900-0459)
- Alana Amarosa Lewin (ORCID: https://orcid.org/0000-0002-7990-4701)
- Lei Qi (ORCID: https://orcid.org/0000-0001-6277-2864)
- Felicia L. Pasadyn (ORCID: https://orcid.org/0000-0003-1733-7489)
- Laura Heacock
- Qi Lei
- Linda Moy
- Freya Schnabel
- Alana Lewin
- Krzysztof Jerzy Geras
Institutions
- NYU Langone Health (US)
- Hinge Health (US)
- New York University (US)
Publication Details
- Journal
- American Journal of Roentgenology
- Published
- 2026-11-18
- DOI
- https://doi.org/10.2214/ajr.26.34951
- Citations
- 2
- Primary Topic
- Digital Radiography and Breast Imaging
- Type
- article
- Field-Weighted Citation Impact
- 4.65