ELEMENT: Multi-Modal Retinal Vessel Segmentation Based on a Coupled Region Growing and Machine Learning Approach

TL;DR

ELEMENT is a multi-modal retinal vessel segmentation framework that combines region growing and machine learning, achieving higher accuracy than existing methods across various ocular imaging modalities.

Contribution

The paper introduces a novel multi-modal segmentation approach that integrates feature extraction, region growing, and connectivity-based classification, improving speed and accuracy.

Findings

Achieved 97.40% accuracy on DRIVE dataset, outperforming 25 of 26 state-of-the-art methods.

Outperformed all compared methods on STARE, CHASE-DB, VAMPIRE FA, IOSTAR SLO, and RC-SLO datasets.

Enhanced segmentation consistency and throughput compared to manual and existing automated approaches.

Abstract

Vascular structures in the retina contain important information for the detection and analysis of ocular diseases, including age-related macular degeneration, diabetic retinopathy and glaucoma. Commonly used modalities in diagnosis of these diseases are fundus photography, scanning laser ophthalmoscope (SLO) and fluorescein angiography (FA). Typically, retinal vessel segmentation is carried out either manually or interactively, which makes it time consuming and prone to human errors. In this research, we propose a new multi-modal framework for vessel segmentation called ELEMENT (vEsseL sEgmentation using Machine lEarning and coNnecTivity). This framework consists of feature extraction and pixel-based classification using region growing and machine learning. The proposed features capture complementary evidence based on grey level and vessel connectivity properties. The latter information is seamlessly propagated through the pixels at the classification phase. ELEMENT reduces inconsistencies and speeds up the segmentation throughput. We analyze and compare the performance of the proposed approach against state-of-the-art vessel segmentation algorithms in three major groups of experiments, for each of the ocular modalities. Our method produced higher overall performance, with an overall accuracy of 97.40%, compared to 25 of the 26 state-of-the-art approaches, including six works based on deep learning, evaluated on the widely known DRIVE fundus image dataset. In the case of the STARE, CHASE-DB, VAMPIRE FA, IOSTAR SLO and RC-SLO datasets, the proposed framework outperformed all of the state-of-the-art methods with accuracies of 98.27%, 97.78%, 98.34%, 98.04% and 98.35%, respectively.