Projet de fin d'étude : Collection and preparation of a dataset for classification diabetic retinopathy stages using deep learning

Etudiant : CHELLAK EL MEHDI

Filière : Master Informatique Décisionnelle et Vision Intelligente (MIDVI)

Encadrant : Pr. TAIRI HAMID

Annèe : 2022

Résumé : Imagine being able to detect blindness before it happens. Millions of people suffer from diabetic retinopathy, the leading cause of blindness among working-age adults. Approximately four hundred and twenty million of people worldwide have been diagnosed with diabetes mellitus. Diabetic mellitus is a which cause of Diabetic retinopathy is a major cause of visual impairment and blindness in France. It is the leading cause of blindness The prevalence of diabetic retinopathy increases with the duration of diabetes and the importance of chronic hyperglycemia. (Diabetes, 2021) As a result, it's critical to seek early detection of diabetic retinopathy lesions, as blindness can be avoided if therapy is started early. To do so, the diabetic must have frequent ophthalmologic surveillance throughout his or her life, and laser treatment must be performed before diabetic retinopathy has resulted in irreversible vision loss. Manual diagnostic procedures, on the other hand, may not be able to keep up with the growing global prevalence of diabetes and its accompanying retinal problems. For these reasons, collaboration between diabetologists, data scientists, and general practitioners is critical in order to create a solution that can lead to automating diabetic retinopathy diagnostic processes, with the ultimate goal of reducing the number of patients worldwide.