这篇论文提出的DITL方法,在乳腺密度分类上全面超过现有方法,而且不用调参,效果好还省事,值得做医学影像的朋友看看。
论文提出Dataset-Informed Transfer Learning(DITL)框架,整合数据集难度信号与邻域三元组监督。DITL包含自适应难度加权交叉熵(A-DWCE)和自适应邻域表示三元组(A-NR-Triplet),无需超参数调优。在VinDR-Mammo大规模数据集上,DITL在乳腺密度分类的准确率、F1-score和AUC上均取得显著提升(p<0.0001)。在小样本ROI数据集上也获得一致的统计显著增益(p<0.0001)。该方法连接小规模病灶分析与大规模密度估计,形成临床可推广的通用框架。
Re-thinking Mammography Transfer Learning: The Dataset-Informed Transfer Learning (DITL) Framework for Breast Cancer Screening and Lesion Diagnosis
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.