LVS-Net: A Lightweight Vessels Segmentation Network for Retinal Image Analysis

TL;DR

LVS-Net is a lightweight, efficient retinal vessel segmentation model that uses multi-scale features and attention mechanisms, achieving high accuracy with fewer parameters for early disease detection.

Contribution

The paper introduces a novel lightweight encoder-decoder architecture with multi-scale convolutional blocks and attention modules, reducing computational costs while improving segmentation performance.

Findings

Achieves dice scores of 86.44%, 84.22%, and 87.88% on DRIVE, CHASE_DB, and STARE datasets.

Uses only 0.71 million parameters and 29.60 GFLOPs, enabling faster processing.

Outperforms existing models in retinal vessel segmentation accuracy.

Abstract

The analysis of retinal images for the diagnosis of various diseases is one of the emerging areas of research. Recently, the research direction has been inclined towards investigating several changes in retinal blood vessels in subjects with many neurological disorders, including dementia. This research focuses on detecting diseases early by improving the performance of models for segmentation of retinal vessels with fewer parameters, which reduces computational costs and supports faster processing. This paper presents a novel lightweight encoder-decoder model that segments retinal vessels to improve the efficiency of disease detection. It incorporates multi-scale convolutional blocks in the encoder to accurately identify vessels of various sizes and thicknesses. The bottleneck of the model integrates the Focal Modulation Attention and Spatial Feature Refinement Blocks to refine and enhance essential features for efficient segmentation. The decoder upsamples features and integrates them with the corresponding feature in the encoder using skip connections and the spatial feature refinement block at every upsampling stage to enhance feature representation at various scales. The estimated computation complexity of our proposed model is around 29.60 GFLOP with 0.71 million parameters and 2.74 MB of memory size, and it is evaluated using public datasets, that is, DRIVE, CHASE\_DB, and STARE. It outperforms existing models with dice scores of 86.44\%, 84.22\%, and 87.88\%, respectively.