论文标题
使用纵向自我监督学习检测糖尿病性视网膜病
Detection of diabetic retinopathy using longitudinal self-supervised learning
论文作者
论文摘要
纵向成像能够捕获静态解剖结构和疾病进展的动态变化，向早期和更好的患者特异性病理学管理。但是，检测糖尿病性视网膜病（DR）的常规方法很少利用纵向信息来改善DR分析。在这项工作中，我们调查了利用纵向诊断目的的纵向性质利用自学学习的好处。我们比较了不同的纵向自我监督学习（LSSL）方法，以模拟从纵向视网膜颜色眼底照片（CFP）进行疾病进展，以使用一对连续考试来检测早期的DR严重性变化。实验是在有或没有那些经过训练的编码器（LSSL）的纵向DR筛选数据集上进行的，该数据集（LSSL）充当纵向借口任务。结果对于基线（从头开始训练）的AUC为0.875，AUC为0.96（95％CI：0.9593-0.9655 DELONG测试），使用P值<2.2e-16在早期融合上使用简单的重新连接构建，具有frozen lssl lssl lss lss lss lss lss lsss lss lss for n forne forne forne forne forne forne for n fort fort forne forn forn forne for。
Longitudinal imaging is able to capture both static anatomical structures and dynamic changes in disease progression towards earlier and better patient-specific pathology management. However, conventional approaches for detecting diabetic retinopathy (DR) rarely take advantage of longitudinal information to improve DR analysis. In this work, we investigate the benefit of exploiting self-supervised learning with a longitudinal nature for DR diagnosis purposes. We compare different longitudinal self-supervised learning (LSSL) methods to model the disease progression from longitudinal retinal color fundus photographs (CFP) to detect early DR severity changes using a pair of consecutive exams. The experiments were conducted on a longitudinal DR screening dataset with or without those trained encoders (LSSL) acting as a longitudinal pretext task. Results achieve an AUC of 0.875 for the baseline (model trained from scratch) and an AUC of 0.96 (95% CI: 0.9593-0.9655 DeLong test) with a p-value < 2.2e-16 on early fusion using a simple ResNet alike architecture with frozen LSSL weights, suggesting that the LSSL latent space enables to encode the dynamic of DR progression.
