Title: Automated hard exudate segmentation using neural encoders and attention mechanisms for diabetic retinopathy diagnosis

Authors: Pratiksha Gawas; Sowmya Kamath S.

Addresses: Department of Information Technology, National Institute of Technology Karnataka, Surathkal, Mangalore 575025, India ' Department of Information Technology, National Institute of Technology Karnataka, Surathkal, Mangalore 575025, India

Abstract: Diabetic retinopathy (DR) is a complication caused by increased blood glucose levels, which causes retinal damage in diabetic patients' eyes. If not discovered and treated early, it can lead to vision loss. Hard exudates (HE) are one of its characteristic signs. Identification of HE is a paramount step in early diagnosis of DR. In this work, the suitability of U-Net-based deep CNN with different encoder configurations and attention gates (AG) is experimented, for HE segmentation. The proposed models were benchmarked on the standard IDRiD dataset. To overcome the challenges related to the limited dataset, data augmentation techniques were also applied to generate image patches and used for model training. Extensive experiments on the dataset revealed that U-Net with AG achieved an accuracy of 98.8%. The U-Net with ResNet50 as the encoder backbone achieved an accuracy of 98.64%. The findings show that the presented models are effective and suitable for early-stage clinical diagnosis.

Keywords: hard exudate; hard exudate segmentation; neural encoders; attention mechanism; diabetic retinopathy; diabetic retinopathy prediction; medical informatics; deep learning.

DOI: 10.1504/IJBET.2023.133723

International Journal of Biomedical Engineering and Technology, 2023 Vol.43 No.1, pp.60 - 75

Received: 23 Mar 2022
Accepted: 08 Oct 2022
Published online: 02 Oct 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article