Convolutional Neural Networks for Diabetic Retinopathy

TLDR

Diagnosis of diabetic retinopathy from color fundus images is laborious and requires experienced clinicians to detect numerous small features within a complex grading system. This study proposes a convolutional neural network to diagnose diabetic retinopathy from digital fundus images and accurately classify its severity. The authors built a CNN with data augmentation that automatically detects microaneurysms, exudates, and hemorrhages, and trained it on a GPU using the publicly available Kaggle dataset. On 80,000 training images, the CNN achieved 95 % sensitivity and 75 % accuracy on a 5,000‑image validation set.

Abstract

The diagnosis of diabetic retinopathy (DR) through colour fundus images requires experienced clinicians to identify the presence and significance of many small features which, along with a complex grading system, makes this a difficult and time consuming task. In this paper, we propose a CNN approach to diagnosing DR from digital fundus images and accurately classifying its severity. We develop a network with CNN architecture and data augmentation which can identify the intricate features involved in the classification task such as micro-aneurysms, exudate and haemorrhages on the retina and consequently provide a diagnosis automatically and without user input. We train this network using a high-end graphics processor unit (GPU) on the publicly available Kaggle dataset and demonstrate impressive results, particularly for a high-level classification task. On the data set of 80,000 images used our proposed CNN achieves a sensitivity of 95% and an accuracy of 75% on 5,000 validation images.