Gradient based Severity Labeling for Biomarker Classification in OCT

TL;DR

This paper introduces a gradient-based method to generate disease severity labels for OCT scans, enhancing contrastive learning for biomarker classification and improving accuracy in diabetic retinopathy detection.

Contribution

It presents a novel severity labeling strategy using gradient responses, tailored for medical images, to improve contrastive learning in biomarker classification.

Findings

Achieved up to 6% accuracy improvement over self-supervised methods.

Demonstrated effectiveness on diabetic retinopathy biomarkers.

Introduced a new approach for severity-based sample selection.

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.