Adaptive Class Learning to Screen Diabetic Disorders in Fundus Images of Eye

TL;DR

This paper presents CELD, a novel adaptive learning framework that improves diabetic disorder screening in fundus images with limited data, achieving 91% accuracy by gradually expanding classification capabilities.

Contribution

Introduces CELD, a new adaptive training framework that enhances classification of retinal images into multiple eye disease categories with limited labeled data.

Findings

Achieved 91% accuracy on public datasets.

Effectively classified Healthy, DR, and Glaucoma images.

Utilized perturbation methods to interpret model decisions.

Abstract

The prevalence of ocular illnesses is growing globally, presenting a substantial public health challenge. Early detection and timely intervention are crucial for averting visual impairment and enhancing patient prognosis. This research introduces a new framework called Class Extension with Limited Data (CELD) to train a classifier to categorize retinal fundus images. The classifier is initially trained to identify relevant features concerning Healthy and Diabetic Retinopathy (DR) classes and later fine-tuned to adapt to the task of classifying the input images into three classes: Healthy, DR, and Glaucoma. This strategy allows the model to gradually enhance its classification capabilities, which is beneficial in situations where there are only a limited number of labeled datasets available. Perturbation methods are also used to identify the input image characteristics responsible for influencing the models decision-making process. We achieve an overall accuracy of 91% on publicly available datasets.