弱增强策略更适配视网膜图像对比学习，提升模型泛化能力。
Enhancing Contrastive Learning for Retinal Imaging via Adjusted Augmentation Scales
- 采用弱增强策略优化对比学习中的图像变换尺度
- 在MESSIDOR2数据集上AUROC达0.848，AUPR提升至0.597
- 适用于医学图像自监督学习，尤其视网膜影像分析
对比学习作为自监督学习的重要方法，在自然图像领域表现优异，但在医学影像领域效果不佳。本文探究其原因，认为医学图像密集分布特性给对比学习的正负样本构建带来挑战。研究比较了不同增强策略下的模型性能，使用六个公开数据集覆盖多种临床任务，并进行外部评估。结果表明，使用弱增强预训练的模型优于强增强模型：在MESSIDOR2数据集上，AUROC从0.838提升至0.848，AUPR从0.523提升至0.597，其他数据集也呈现类似提升。研究证明，优化增强尺度对提升医学影像对比学习效果至关重要。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。