Deep Learner System Based on Focal Color Retinal Fundus Images to Assist in Diagnosis

Abstract

Retinal diseases are a serious and widespread ophthalmic disease that seriously affects patients’ vision and quality of life. With the aging of the population and the change in lifestyle, the incidence rate of retinal diseases has increased year by year. However, traditional diagnostic methods often require experienced doctors to analyze and judge fundus images, which carries the risk of subjectivity and misdiagnosis. This paper will analyze an intelligent medical system based on focal retinal image-aided diagnosis and use a convolutional neural network (CNN) to recognize, classify, and detect hard exudates (HEs) in fundus images (FIs). The research results indicate that under the same other conditions, the accuracy, recall, and precision of the system in diagnosing five types of patients with pathological changes under color retinal FIs range from 86.4% to 98.6%. Under conventional retinopathy FIs, the accuracy, recall, and accuracy of the system in diagnosing five types of patients ranged from 70.1% to 85%. The results show that the application of focus color retinal FIs in the intelligent medical system has high accuracy and reliability for the early detection and diagnosis of diabetic retinopathy and has important clinical applications.