Semantic Data Augmentation Enhanced Invariant Risk Minimization for Medical Image Domain Generalization
This work addresses the challenge of data heterogeneity in medical image classification, which is a significant problem for clinicians and researchers working with medical imaging data.
The authors tackled the problem of out-of-distribution generalization in medical image classification, achieving improved performance with their novel method, particularly under limited data conditions and significant domain heterogeneity, outperforming state-of-the-art approaches. Their approach reduced domain discrepancies and enhanced generalization performance.
Deep learning has achieved remarkable success in medical image classification. However, its clinical application is often hindered by data heterogeneity caused by variations in scanner vendors, imaging protocols, and operators. Approaches such as invariant risk minimization (IRM) aim to address this challenge of out-of-distribution generalization. For instance, VIRM improves upon IRM by tackling the issue of insufficient feature support overlap, demonstrating promising potential. Nonetheless, these methods face limitations in medical imaging due to the scarcity of annotated data and the inefficiency of augmentation strategies. To address these issues, we propose a novel domain-oriented direction selector to replace the random augmentation strategy used in VIRM. Our method leverages inter-domain covariance as a guider for augmentation direction, guiding data augmentation towards the target domain. This approach effectively reduces domain discrepancies and enhances generalization performance. Experiments on a multi-center diabetic retinopathy dataset demonstrate that our method outperforms state-of-the-art approaches, particularly under limited data conditions and significant domain heterogeneity.