Title: Retinal vascular segmentation using deep learning reinforced by discrete wavelet transform

Authors: Mohamed Elssaleh Bachiri

Addresses: Limose Laboratory, Department of Electrical Engineering, Faculty of Technology, University M'hamed Bougara – Boumerdes, 35000, Algeria

Abstract: The detection of blood vessels in the retina helps to identify various diseases such as diabetes and hypertension. Detection of vessels is a complex task facing specialists during the segmentation process especially children's blood vessels, which are thin. We proposed a deep learning model to do the semantic segmentation of blood vessels in general and the identification of vessels with very high accuracy, where we used short discrete wavelet transform to enhance the features extracted from the deep learning that we created to fit the waves. We applied different types of discrete waves with varying scaling within the model to accurately detect vessels. In addition, we used these waves on other models of DL used for vascular segmentation, where the yield improved significantly after these additions. The experiments on the Digital Retinal Images for Vessel Extraction (DRIVE) database were our model achieved the best results with test F1-score and accuracy of 0.9873, 0.9787, respectively.

Keywords: DWT2; deep learning; residual; retinal segmentation; U-net.

DOI: 10.1504/IJBET.2026.151415

International Journal of Biomedical Engineering and Technology, 2026 Vol.50 No.1, pp.32 - 54

Received: 21 Jan 2025
Accepted: 13 Sep 2025
Published online: 28 Jan 2026 *

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