Predicting short- to long-term breast cancer risk from longitudinal mammographic screening history.
Authors
Affiliations (12)
Affiliations (12)
- Department of Radiology, The Netherlands Cancer Institute, 1066 CX, Amsterdam, The Netherlands.
- GROW School for Oncology and Development Biology, Maastricht University, P. O. Box 616, 6200 MD, Maastricht, The Netherlands.
- Department of Diagnostic Imaging, Radboud University Medical Center, 6525 GA, Nijmegen, The Netherlands.
- Faculty of Applied Sciences, Macao Polytechnic University, 999078, Macao, China. [email protected].
- Erasmus Medical Center, Erasmus University, 3015 GD, Rotterdam, The Netherlands.
- Department of Radiation Oncology, The Netherlands Cancer Institute, 1066 CX, Amsterdam, The Netherlands.
- ScreenPoint Medical, Nijmegen, 6525 EC, The Netherlands.
- Dipartimento di Diagnostica per Immagini, Radioterapia Oncologica ed Ematologia, Fondazione Policlinico Universitario A. Gemelli, IRCCS, 00168, Rome, Italy.
- Department of Surgical Oncology, The Netherlands Cancer Institute, 1066 CX, Amsterdam, The Netherlands.
- Division of Molecular Pathology, The Netherlands Cancer Institute, 1066 CX, Amsterdam, The Netherlands.
- Department of Epidemiology, The Netherlands Cancer Institute, 1066 CX, Amsterdam, The Netherlands.
- Department of Medical Imaging, Radboud University Medical Center, 6500 HB, Nijmegen, The Netherlands.
Abstract
Breast cancer (BC) risk assessment aims to enhance individualized screening and prevention strategies. While recent deep learning (DL) models based on mammography have shown promise in short-term risk prediction, they primarily rely on single-time-point (STP) exams, ignoring temporal changes in breast tissue from sequence exams. We present the Multi-Time Point Breast Cancer Risk Model (MTP-BCR), a novel DL approach that integrates traditional risk factors and longitudinal mammography data to capture subtle tissue changes indicative of future malignancy. Using a large in-house dataset with 171,168 mammograms from 9133 women, MTP-BCR achieved superior performance in 10-year risk prediction, with an AUC of 0.80 (95% CI, 0.78-0.82) at the patient level, outperforming STP-based and traditional risk models. External validation on the CSAW-CC dataset confirmed its robustness. Further analysis demonstrates the advantages of the MTP-BCR method in diverse populations. MTP-BCR also excels in risk stratification and offers heatmaps to enhance clinical interpretability.