Enhancing Contrastive Learning for Retinal Imaging via Adjusted Augmentation Scales
This work addresses the challenge of applying contrastive learning to medical imaging, which is incremental as it adapts existing methods to a specific domain.
The paper tackled the suboptimal performance of contrastive learning in medical imaging by investigating augmentation strategies, finding that weak augmentation outperforms strong augmentation, improving AUROC from 0.838 to 0.848 and AUPR from 0.523 to 0.597 on the MESSIDOR2 dataset.
Contrastive learning, a prominent approach within self-supervised learning, has demonstrated significant effectiveness in developing generalizable models for various applications involving natural images. However, recent research indicates that these successes do not necessarily extend to the medical imaging domain. In this paper, we investigate the reasons for this suboptimal performance and hypothesize that the dense distribution of medical images poses challenges to the pretext tasks in contrastive learning, particularly in constructing positive and negative pairs. We explore model performance under different augmentation strategies and compare the results to those achieved with strong augmentations. Our study includes six publicly available datasets covering multiple clinically relevant tasks. We further assess the model's generalizability through external evaluations. The model pre-trained with weak augmentation outperforms those with strong augmentation, improving AUROC from 0.838 to 0.848 and AUPR from 0.523 to 0.597 on MESSIDOR2, and showing similar enhancements across other datasets. Our findings suggest that optimizing the scale of augmentation is critical for enhancing the efficacy of contrastive learning in medical imaging.