Adding a pretreatment MRI deep-learning risk score to a baseline clinical model significantly improved the prediction of breast cancer recurrence (C-index 0.71 vs 0.64; p=0.007).
Observational (n=433)
Yes
Does a transfer-learning-based DenseNet121 MRI model improve the prediction of breast cancer recurrence in patients undergoing NAT compared to standard clinical factors?
A transfer-learning MRI model provides added value beyond standard clinical factors for predicting 3- and 5-year recurrence in breast cancer patients.
Absolute Event Rate: 0.71% vs 0.64%
p-value: p=0.007
Abstract Background: MRI features have demonstrated prognostic value in predicting future breast cancer recurrence. However, deep learning studies remain limited particularly those evaluating performance across tumor subtypes and different time horizons in large multicenter datasets. Materials and Methods: We used pretreatment DCE-MRI exams from the multicenter MAMA-MIA dataset (433 breast cancer patients who underwent NAT; 115 with recurrence events, 318 recurrence-free) to evaluate a transfer-learning framework based on DenseNet121 pretrained on ImageNet. Middle tumor-containing slices were bias-field corrected, resampled, cropped to the tumor regions, and resized to 224×224 pixels. The top 10% of DenseNet121 layers were unfrozen for model fine-tuning for recurrence prediction. Five-fold stratified cross-validation preserved site distribution across data splits. Model performance was evaluated using Harrell’s C-index and time-dependent AUCs at 3 and 5 year horizons. Correlated C-indices were compared using the two-sided Kang et al. test. We also assessed the added value by our deep-learning risk score to a baseline prognostic model based on the established clinical factors HR and HER2. Model performance was also assessed across tumor subtypes. Results: Our deep learning model achieved a C-index of 0.67±0.03 with 3 and 5 year AUCs of 0.69±0.04 and 0.67±0.10, respectively. Adding our deep-learning risk score to the baseline model significantly improved performance from 0.64 to 0.71 (p=0.007). Subtype-specific evaluations (Table 1) showed variable performances with the highest performance in HER2-pure and TNBC patients. Conclusion: Our findings highlight the potential of a transfer-learning-based DenseNet121 MRI model to predict 3 and 5 year recurrences in breast cancer patients, providing added value beyond standard clinical factors. Future optimizations will aim at improving subtype-specific performance in large multicenter datasets. Citation Format: Kanika Bhalla, Adrian Sanchez, José Marcio Luna, Tabassum Ahmad, Debbie L. Bennett, Andrew A. Davis, Aimilia Gastounioti, . Assessing the risk of breast cancer recurrence with pre-treatment MRI: A transfer learning study on multicenter data abstract. In: Proceedings of the American Association for Cancer Research Annual Meeting 2026; Part 1 (Regular Abstracts); 2026 Apr 17-22; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2026;86(7 Suppl):Abstract nr 2785.
Bhalla et al. (Fri,) conducted a observational in Breast cancer (n=433). Deep-learning risk score based on pretreatment DCE-MRI vs. Baseline prognostic model based on clinical factors HR and HER2 was evaluated on C-index for recurrence prediction (p=0.007). Adding a pretreatment MRI deep-learning risk score to a baseline clinical model significantly improved the prediction of breast cancer recurrence (C-index 0.71 vs 0.64; p=0.007).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: