Identification of Diabetic Related Eye Diseases Using Deep Learning

Visual disability seems to be increasing and widespread worldwide. Current diagnostics require manual expertise for diagnosis. The advancement of Artificial Intelligence research for medical applications has been in focus in recent years. Fundus images and oct images are valuable sources of information to help ophthalmologists diagnose vision disorders or eye diseases. Early detection can improve the chances of recovery and prevent blindness. The application of an intelligent computer-based approach to classifying different eye disorders is extremely beneficial for both diagnosis and prevention. The proposed expert system for diagnosing diabetic macular edema, diabetic retinopathy, cataracts, and glaucoma diseases is discussed in this research study. It is based on deep learning image processing techniques. For the detection of eye diseases, software used retinal and OTC images. This study presents Yolo, UNET, customized CNN, and Auto ML model-based system for detecting eye diseases. For the tasks of disease identification and grading, the suggested methods each obtained more than 87% accuracy. The primary objective of this study is to achieve automated identification of eye disease images. This is accomplished through the implementation of a deep learning model alongside advanced image processing techniques, enabling the automatic classification of eyes into either a healthy or diseased category.