Systematic Development of AI-Enabled Diagnostic Systems for Glaucoma and Diabetic Retinopathy

With the rapid advancements in artificial intelligence, particularly in machine learning and deep learning, automated disease diagnosis is becoming increasingly feasible. Generating larger databases is crucial for training and validating the performance of models for chronic diseases such as glaucoma and diabetic retinopathy, which progress slowly and unnoticed. Automated procedures for retinal vessel segmentation and optic cup/disk localization are preferred for large-scale screening of the public, contributing to the early detection and treatment of eye diseases, preventing blindness, and improving public health. This paper focuses on the challenges involved in segmenting the retinal vessels from fundus images and presents a modified ColonSegNet model for retinal vessel segmentation that includes efficient methods for locating the true vessels and applies data augmentation to overcome the issue of fewer graded images. The paper uses the optimal values for the contrast enhancement of retinal fundus images using intelligent evolution algorithms. The central vessel reflex, bifurcation, crossover, thin vessels, and lesion presence are highlighted as significant challenges in retinal vessel segmentation. The proposed method achieves high sensitivity, specificity, and accuracy, {0.839, 0.979, 0.966}, {0.865, 0.979, 0.971}, and {0.867, 0.981, 0.972}, segmenting retinal vessels on DRIVE, CHASE_DB, and STARE. The work is crucial in developing automated systems for the early detection and treatment of eye diseases, thereby improving public health.