Deep Semi-Supervised and Self-Supervised Learning for Diabetic Retinopathy Detection
This addresses the costly and time-consuming annotation process in medical imaging for diabetic retinopathy detection, offering a practical solution with incremental improvements in efficiency.
The paper tackles the problem of limited annotated medical images for diabetic retinopathy detection by proposing a semi-supervised method that uses self-supervised pretraining and knowledge distillation, achieving AUC scores of 0.94 on EyePACS and 0.89 on Messidor-2 with only 2% labeled data.
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 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.