DoSReMC: Domain Shift Resilient Mammography Classification using Batch Normalization Adaptation
This work addresses the critical issue of domain shift for deploying AI in clinical mammography, offering a practical solution to improve model robustness across diverse healthcare settings, though it is incremental as it builds on existing adaptation techniques.
The paper tackles the problem of domain shift in mammography classification, where deep learning models perform poorly on data from different domains, and presents DoSReMC, a batch normalization adaptation framework that improves cross-domain generalization by fine-tuning only BN and FC layers, achieving enhanced performance without full retraining.
Numerous deep learning-based solutions have been developed for the automatic recognition of breast cancer using mammography images. However, their performance often declines when applied to data from different domains, primarily due to domain shift - the variation in data distributions between source and target domains. This performance drop limits the safe and equitable deployment of AI in real-world clinical settings. In this study, we present DoSReMC (Domain Shift Resilient Mammography Classification), a batch normalization (BN) adaptation framework designed to enhance cross-domain generalization without retraining the entire model. Using three large-scale full-field digital mammography (FFDM) datasets - including HCTP, a newly introduced, pathologically confirmed in-house dataset - we conduct a systematic cross-domain evaluation with convolutional neural networks (CNNs). Our results demonstrate that BN layers are a primary source of domain dependence: they perform effectively when training and testing occur within the same domain, and they significantly impair model generalization under domain shift. DoSReMC addresses this limitation by fine-tuning only the BN and fully connected (FC) layers, while preserving pretrained convolutional filters. We further integrate this targeted adaptation with an adversarial training scheme, yielding additional improvements in cross-domain generalizability while reducing the computational cost of model training. DoSReMC can be readily incorporated into existing AI pipelines and applied across diverse clinical environments, providing a practical pathway toward more robust and generalizable mammography classification systems.