Re-thinking Mammography Transfer Learning: The Dataset-Informed Transfer Learning (DITL) Framework for Breast Cancer Screening and Lesion Diagnosis
2026-07-28 • Machine Learning
Machine Learning
AI summaryⓘ
The authors developed a new method called Dataset-Informed Transfer Learning (DITL) to improve breast cancer image classification in mammograms. Their approach uses information about how difficult each image is based on similar images nearby, helping the model learn better without extra tuning. They tested it on both large and small datasets and found it works better than previous methods for identifying breast density and lesions. This method combines different learning strategies to be flexible and efficient across various mammography tasks.
Transfer LearningMammographyBreast Density ClassificationTriplet LossCross-Entropy Lossk-Nearest NeighborsSelf-Supervised LearningAUCF1-scoreDataset Difficulty
Authors
Adarsh Bhandary Panambur, Siming Bayer, Andreas Maier
Abstract
Enhancing classification performance in mammography remains a persistent challenge across both small curated datasets and large-scale clinical cohorts. Conventional transfer learning approaches often neglect dataset-specific characteristics, while recent neighborhood-informed methods have been restricted to narrow tasks with rigid formulations, limiting their scalability to population-level datasets. To address these challenges, we propose the Dataset-Informed Transfer Learning (DITL) framework, which integrates dataset-derived difficulty signals with neighborhood-based triplet supervision in a unified objective. DITL introduces two adaptive components: (i) Adaptive Difficulty-Weighted Cross-Entropy (A-DWCE), which assigns per-sample weights based on k-nearest neighbor label purity in a self-supervised feature space, and (ii) Adaptive Neighborhood Representation Triplet (A-NR-Triplet), which enforces intra-class compactness and inter-class separation using a learnable margin. Unlike focal loss, DITL requires no hyperparameter tuning, removes heuristic weighting and fixed margins, and incurs negligible computational overhead, yielding a robust and scalable optimization strategy. On the large-scale VinDR-Mammo dataset, DITL achieves state-of-the-art performance for whole-image breast density classification, with significant improvements across accuracy, F1-score, and AUC (p < 0.0001). Beyond large cohorts, DITL also delivers consistent, statistically significant gains on small ROI datasets (p < 0.0001). By bridging small-scale lesion analysis with large-scale density estimation, DITL establishes a clinically relevant, scalable, and generalizable framework for mammography classification, spanning the full breast cancer screening-to-diagnosis spectrum.