Study on Limited Data Problem - Semantic Segmentation of Retinal Fundus Images

Abstract

Medical images captured through various imaging modalities are key to the diagnosis and treatment of diseases, and these images serve as a major input to AI driven models but due to the scarcity of medical experts and their quality research time, the quantum of data required for AI models is limited. Moreover, medical image analysis is a laborious and error prone task. Early detection of retinal diseases by means of AI based semantic segmentation model has been boon to the diagnostic system. However, performing semantic segmentation with limited data of retinal fundus image is quite challenging. The present study is primarily focused on investigation of effectiveness of data augmentation with gamma corrected images to alleviate the problem of limited annotated data in deep learning models. The most widely accepted U-Net model in medical domain for image segmentation is trained employing retinal fundus image dataset augmented with gamma corrected images on all image channels and then tested against major publicly available datasets. The proposed method has outperformed other complex contemporary methods in terms of sensitivity and has also shown better generalizability across datasets from different institutions.