Adaptive Class Learning to Screen Diabetic Disorders in Fundus Images of Eye
This work addresses early detection of diabetic disorders and glaucoma in eye images, which is crucial for preventing visual impairment, but it is incremental as it builds on existing classification methods with a new training strategy.
The paper tackles the problem of classifying retinal fundus images into multiple disease categories with limited labeled data by introducing the CELD framework, achieving an overall accuracy of 91% on public datasets.
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.