Enhancing Retinal Disease Classification from OCTA Images via Active Learning Techniques

TL;DR

This paper applies active learning to improve deep learning-based classification of retinal diseases from OCTA images, significantly enhancing model performance despite limited labeled data.

Contribution

It introduces an active learning approach for OCTA image classification, outperforming traditional data balancing methods and addressing data scarcity in medical imaging.

Findings

Active learning improves F1 scores by up to 49%.

Active subset selection outperforms class weighting, undersampling, and oversampling.

Deep learning models benefit from targeted data labeling in OCTA analysis.

Abstract

Eye diseases are common in older Americans and can lead to decreased vision and blindness. Recent advancements in imaging technologies allow clinicians to capture high-quality images of the retinal blood vessels via Optical Coherence Tomography Angiography (OCTA), which contain vital information for diagnosing these diseases and expediting preventative measures. OCTA provides detailed vascular imaging as compared to the solely structural information obtained by common OCT imaging. Although there have been considerable studies on OCT imaging, there have been limited to no studies exploring the role of artificial intelligence (AI) and machine learning (ML) approaches for predictive modeling with OCTA images. In this paper, we explore the use of deep learning to identify eye disease in OCTA images. However, due to the lack of labeled data, the straightforward application of deep learning doesn't necessarily yield good generalization. To this end, we utilize active learning to select the most valuable subset of data to train our model. We demonstrate that active learning subset selection greatly outperforms other strategies, such as inverse frequency class weighting, random undersampling, and oversampling, by up to 49% in F1 evaluation.