Domain generalization in deep learning-based mass detection in mammography: A large-scale multi-center study
This work addresses the critical problem of deploying AI systems in varying clinical settings for breast cancer detection, though it is incremental as it builds on existing methods with a new analysis and pipeline.
The study tackled domain generalization in deep learning-based mass detection for mammography by comparing eight state-of-the-art methods across multiple unseen domains, showing that their workflow outperformed transfer learning in four out of five domains and reduced domain shift from acquisition protocols and scanners.
Computer-aided detection systems based on deep learning have shown great potential in breast cancer detection. However, the lack of domain generalization of artificial neural networks is an important obstacle to their deployment in changing clinical environments. In this work, we explore the domain generalization of deep learning methods for mass detection in digital mammography and analyze in-depth the sources of domain shift in a large-scale multi-center setting. To this end, we compare the performance of eight state-of-the-art detection methods, including Transformer-based models, trained in a single domain and tested in five unseen domains. Moreover, a single-source mass detection training pipeline is designed to improve the domain generalization without requiring images from the new domain. The results show that our workflow generalizes better than state-of-the-art transfer learning-based approaches in four out of five domains while reducing the domain shift caused by the different acquisition protocols and scanner manufacturers. Subsequently, an extensive analysis is performed to identify the covariate shifts with bigger effects on the detection performance, such as due to differences in patient age, breast density, mass size, and mass malignancy. Ultimately, this comprehensive study provides key insights and best practices for future research on domain generalization in deep learning-based breast cancer detection.