LFRA-Net: A Lightweight Focal and Region-Aware Attention Network for Retinal Vessel Segmentatio

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Mehmood, Mehwish, Iqbal, Shahzaib, Khan, Tariq Mahmood, Spence, Ivor, Fahim, Muhammad
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918141161897984
author Mehmood, Mehwish
Iqbal, Shahzaib
Khan, Tariq Mahmood
Spence, Ivor
Fahim, Muhammad
author_facet Mehmood, Mehwish
Iqbal, Shahzaib
Khan, Tariq Mahmood
Spence, Ivor
Fahim, Muhammad
contents Retinal vessel segmentation is critical for the early diagnosis of vision-threatening and systemic diseases, especially in real-world clinical settings with limited computational resources. Although significant improvements have been made in deep learning-based segmentation methods, current models still face challenges in extracting tiny vessels and suffer from high computational costs. In this study, we present LFRA-Net by incorporating focal modulation attention at the encoder-decoder bottleneck and region-aware attention in the selective skip connections. LFRA-Net is a lightweight network optimized for precise and effective retinal vascular segmentation. It enhances feature representation and regional focus by efficiently capturing local and global dependencies. LFRA-Net outperformed many state-of-the-art models while maintaining lightweight characteristics with only 0.17 million parameters, 0.66 MB memory size, and 10.50 GFLOPs. We validated it on three publicly available datasets: DRIVE, STARE, and CHASE\_DB. It performed better in terms of Dice score (84.28\%, 88.44\%, and 85.50\%) and Jaccard index (72.86\%, 79.31\%, and 74.70\%) on the DRIVE, STARE, and CHASE\_DB datasets, respectively. LFRA-Net provides an ideal ratio between segmentation accuracy and computational cost compared to existing deep learning methods, which makes it suitable for real-time clinical applications in areas with limited resources. The code can be found at https://github.com/Mehwish4593/LFRA-Net.
format Preprint
id arxiv_https___arxiv_org_abs_2509_11811
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LFRA-Net: A Lightweight Focal and Region-Aware Attention Network for Retinal Vessel Segmentatio
Mehmood, Mehwish
Iqbal, Shahzaib
Khan, Tariq Mahmood
Spence, Ivor
Fahim, Muhammad
Computer Vision and Pattern Recognition
Retinal vessel segmentation is critical for the early diagnosis of vision-threatening and systemic diseases, especially in real-world clinical settings with limited computational resources. Although significant improvements have been made in deep learning-based segmentation methods, current models still face challenges in extracting tiny vessels and suffer from high computational costs. In this study, we present LFRA-Net by incorporating focal modulation attention at the encoder-decoder bottleneck and region-aware attention in the selective skip connections. LFRA-Net is a lightweight network optimized for precise and effective retinal vascular segmentation. It enhances feature representation and regional focus by efficiently capturing local and global dependencies. LFRA-Net outperformed many state-of-the-art models while maintaining lightweight characteristics with only 0.17 million parameters, 0.66 MB memory size, and 10.50 GFLOPs. We validated it on three publicly available datasets: DRIVE, STARE, and CHASE\_DB. It performed better in terms of Dice score (84.28\%, 88.44\%, and 85.50\%) and Jaccard index (72.86\%, 79.31\%, and 74.70\%) on the DRIVE, STARE, and CHASE\_DB datasets, respectively. LFRA-Net provides an ideal ratio between segmentation accuracy and computational cost compared to existing deep learning methods, which makes it suitable for real-time clinical applications in areas with limited resources. The code can be found at https://github.com/Mehwish4593/LFRA-Net.
title LFRA-Net: A Lightweight Focal and Region-Aware Attention Network for Retinal Vessel Segmentatio
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.11811