[论文解读] Gradient based Severity Labeling for Biomarker Classification in OCT

Kiran Kokilepersaud, Mohit Prabhushankar+3 more|arXiv (Cornell University)|Feb 23, 2026

Retinal Imaging and Analysis被引用 0

一句话总结

论文提出基于严重度的伪标签策略，用健康自编码器的梯度响应对未标记的OCT扫描进行伪标签，并训练一个监督对比编码器以提升OCT生物标志物分类性能。

ABSTRACT

In this paper, we propose a novel selection strategy for contrastive learning for medical images. On natural images, contrastive learning uses augmentations to select positive and negative pairs for the contrastive loss. However, in the medical domain, arbitrary augmentations have the potential to distort small localized regions that contain the biomarkers we are interested in detecting. A more intuitive approach is to select samples with similar disease severity characteristics, since these samples are more likely to have similar structures related to the progression of a disease. To enable this, we introduce a method that generates disease severity labels for unlabeled OCT scans on the basis of gradient responses from an anomaly detection algorithm. These labels are used to train a supervised contrastive learning setup to improve biomarker classification accuracy by as much as 6% above self-supervised baselines for key indicators of Diabetic Retinopathy.

研究动机与目标

• 在有限标记数据条件下，推动OCT中生物标志物检测的准确性。
• 利用梯度响应开发基于严重度的伪标签机制。
• 利用监督对比学习提升生物标志物分类性能。
• 评估严重度分箱选择对多种OCT生物标志物检测的影响。

提出的方法

• 在健康OCT上训练自编码器，使健康样本的梯度对齐通过GradCON。
• 对未标记的OCT图像计算严重度分数SS = -L_recon + α L_grad，α = 0.03。
• 将严重度分数离散化为N个区间以为未标记数据分配严重度标签SL。
• 使用严重度标签训练带有监督对比损失的ResNet-18编码器。
• 冻结编码器权重，在标记的生物标志物数据上微调线性分类器。

Fig. 1 : OCT Scans of biomarkers from the Prime + TREX DME datasets. The biomarkers are A) Intraretinal Hyperreflective Foci (IRHRF), B) Intraretinal Fluid (IRF) and Diabetic Macular Edema (DME) C) Partially Attached Vitreous Face (PAVF), and D) Fully Attached Vitreous Face (FAVF). The white arrows

实验结果

研究问题

• RQ1 基于健康分布的梯度严重度标签是否能提升OCT生物标志物的表征学习？
• RQ2 严重度区间数N如何影响多标签AUC与每个生物标志物的性能？
• RQ3 基于严重度的监督对比表示是否在OCT生物标志物任务上优于自监督基线？
• RQ4 使用不同的异常检测器生成严重度标签的影响是什么？

主要发现

• 基于严重度标签的监督对比学习在多标签均值AUC和生物标志物准确率方面优于自监督基线。
• 改变严重度区间数量N会影响性能；中等N（如5000–10000）通常比极端值获得更好的多标签AUC。
• 用于严重度标签的不同异常检测器显示SL（严重度标签）方法在多标签结果上总体优于其他方法。
• 最佳的每个生物标志物性能取决于具体生物标志物，有些受益于较高的区间数（如DME、IRF），有些则受益于中等区间数。

Fig. 2 : From a healthy manifold learned from a trained auto-encoder, we can compute distance to the manifold of more severely diseased cases via a Severity Score (SS). Severity Score is calculated via some model response and increases as a sample is more anomalous compared to the learned healthy ma