Deep semi-supervised and self-supervised learning for diabetic retinopathy detection

Abstract

Diabetic retinopathy (DR) is one of the leading causes of blindness in the working-age population of developed countries, caused by a side effect of diabetes that reduces the blood supply to the retina. Deep neural networks have been widely used in automated systems for DR classification on eye fundus images. However, these models need a large number of annotated images. In the medical domain, annotations from experts are costly, tedious, and time-consuming; as a result, a limited number of annotated images are available. This paper presents a semi-supervised method that leverages unlabeled images and labeled ones to train a model that detects diabetic retinopathy. The proposed method uses unsupervised pretraining via self-supervised learning followed by supervised fine-tuning with a small set of labeled images and knowledge distillation to increase the performance in a classification task. This method was evaluated on the EyePACS test and Messidor-2 dataset achieving 0.94 and 0.89 AUC respectively using only 2% of EyePACS train labeled images.

Diabetes management in the era of artificial intelligence

“…AI-based DHTs in diabetes care could help develop better preventive strategies for high-risk populations, manage patients unable to attend in-person appointments, provide real-time health, encourage self-management, and save time and money by minimising travel to in-person appointments [8]. ML [9] is a subfield of AI, based on statistical methods that can automatically learn and enhance its performance, such as accuracy, via supervised or unsupervised methods. Thanks to its exceptional feature extraction and pattern recognition capabilities, which use multiple processing layers (artificial neurons) to learn representations of data with different levels of abstraction so that it associates the input with a diagnostic output, DL [10], which employs advanced machine learning techniques, has achieved significant success in computer vision and natural language processing tasks.…”