Diabetic Retinopathy Grading System Based on Transfer Learning

TL;DR

This paper introduces a transfer learning-based deep learning system using a customized EfficientNet model for automatic diabetic retinopathy grading, achieving high accuracy and robustness on the IDRiD dataset.

Contribution

It presents a novel multi-label classification system with a customized EfficientNet model for DR grading, leveraging transfer learning for small datasets.

Findings

Achieved 86% accuracy in DR grading

Attained 78.45 Dice similarity coefficient

Demonstrated robustness and reliability of the system

Abstract

Much effort is being made by the researchers in order to detect and diagnose diabetic retinopathy (DR) accurately automatically. The disease is very dangerous as it can cause blindness suddenly if it is not continuously screened. Therefore, many computers aided diagnosis (CAD) systems have been developed to diagnose the various DR grades. Recently, many CAD systems based on deep learning (DL) methods have been adopted to get deep learning merits in diagnosing the pathological abnormalities of DR disease. In this paper, we present a full based-DL CAD system depending on multi-label classification. In the proposed DL CAD system, we present a customized efficientNet model in order to diagnose the early and advanced grades of the DR disease. Learning transfer is very useful in training small datasets. We utilized IDRiD dataset. It is a multi-label dataset. The experiments manifest that the proposed DL CAD system is robust, reliable, and deigns promising results in detecting and grading DR. The proposed system achieved accuracy (ACC) equals 86%, and the Dice similarity coefficient (DSC) equals 78.45.