Enhancing Choroidal Nevus Position Identification through CNN-Based Segmentation of Eye Fundus Images

Diagnosing choroidal nevus in color fundus images is challenging for clinicians not regularly practicing it. Machine learning (ML) has proven effective in detecting and analyzing such abnormalities with high accuracy and efficiencyThis research is part of a larger project to develop a decision support system for choroidal nevus diagnosis, focusing on creating a segmentation algorithm to identify key areas in color fundus images. The study evaluates and compares the efficacy of various convolutional neural network (CNN) segmentation models, a crucial step for improved image analysis accuracyFundus images from the Alberta Ocular Brachytherapy Program, including healthy and choroidal nevus-affected eyes, were used. An ocular oncologist provided a ground truth mask dataset for training the models. Preprocessing improved image features, and multiple CNN models segmented the images to detect lesions. Model performance was compared to find the most accurate and efficient approach, with external validation using a separate test set and ophthalmology expertsFour CNN models – U-net, Residual U-net, Attention U-net, and a voting-based Ensemble – were developed for segmentation. Their effectiveness was measured by accuracy metrics, achieving Dice Coefficient scores of 85.02%, 85.66%, 86.89%, and 87.7% respectively.