A Trio-Method for Retinal Vessel Segmentation using Image Processing

TL;DR

This paper introduces a triple preprocessing approach combined with two U-Net architectures for improved retinal vessel segmentation, demonstrating enhanced performance on the DRIVE database for potential real-time medical imaging applications.

Contribution

It proposes a novel triple preprocessing pipeline and compares two U-Net models, advancing retinal vessel segmentation techniques with detailed performance analysis.

Findings

Preprocessing significantly improved segmentation accuracy.

U-Net architectures outperformed traditional methods.

Enhanced real-time image processing potential.

Abstract

Inner Retinal neurons are a most essential part of the retina and they are supplied with blood via retinal vessels. This paper primarily focuses on the segmentation of retinal vessels using a triple preprocessing approach. DRIVE database was taken into consideration and preprocessed by Gabor Filtering, Gaussian Blur, and Edge Detection by Sobel and Pruning. Segmentation was driven out by 2 proposed U-Net architectures. Both the architectures were compared in terms of all the standard performance metrics. Preprocessing generated varied interesting results which impacted the results shown by the UNet architectures for segmentation. This real-time deployment can help in the efficient pre-processing of images with better segmentation and detection.