Structure-aware learnable multi-scale attention for retinal vessel analysis
- 1Department of Computer Science and Engineering, National Institute of Technology Calicut
- 2Advanced Computing Technology Group, Tata Elxsi Ltd.
- 3Giridhar Eye Hospital
Abstract
Accurate retinal vessel segmentation is critical for automated screening and monitoring of ocular and systemic diseases; however, existing deep segmentation models often struggle to preserve thin, low-contrast vessels. We propose a Learnable Multi-Scale Vesselness Attention (LMSA) module, a lightweight and architecture-agnostic component that introduces explicit vessel-aware priors into deep feature learning by adaptively selecting scale-space vesselness responses under a second-order structural prior and refining them through directional coherence modulation. LMSA aggregates multi-scale vesselness responses into a structurally aware representation and transforms them into a spatial attention mask that selectively enhances curvilinear vascular structures while suppressing background noise. Using U-Net as a reference backbone, an LMSA-enhanced network is constructed with an integrated multi-task learning (MTL) design that jointly supervises vessel segmentation, boundary delineation, and centerline extraction, thereby enforcing structural consistency. The generality of the framework is further demonstrated by integrating LMSA and MTL into multiple CNN segmentation architectures. Extensive experiments on three public benchmarks indicate that the proposed U-Net+LMSA+MTL model outperforms state-of-the-art baselines, achieving Dice scores of 85.39%, 85.00%, and 85.47%, with corresponding accuracies of 97.37%, 97.87%, and 97.90% on DRIVE, STARE, and CHASE_DB1, respectively. On a clinically acquired in-house dataset, the model maintains strong performance with a Dice score of 82.77% and an accuracy of 95.88%, supporting its potential for real-world clinical deployment. Collectively, these results demonstrate that the proposed framework effectively embeds vessel prominence and structural priors into deep networks, enabling more reliable, structurally consistent, and clinically meaningful retinal vessel analysis.
Related
- Structure-preserving lightweight skin lesion segmentation with dual-resolution attention and boundary-aware fusion
- Evaluating the real-world accessibility of open-source deep learning models for retinal vessel segmentation in optical coherence tomography angiography
- Retinal vessel segmentation using Kolmogorov-Arnold networks and test-time adaptation
- Associations between corneal biomechanical parameters and retinal superficial vessel density in young adults with varying myopia severity: a cross-sectional study.
- Feature-aware attention convolutional neural network for efficient pulmonary fibrosis classification from chest CT images with FPGA deployment
BibTeX
@article{johny2026structureaware,
title = {{Structure-aware learnable multi-scale attention for retinal vessel analysis}},
author = {Dinoy Johny and V. Chandan and Shubham Loni and A. Devika Gireesh and Vasarla Saimahesh and Kalpana George and Manju Anup and S. S. Anup and P. B. Jayaraj},
journal = {Scientific Reports},
year = {2026},
month = jul,
doi = {10.1038/s41598-026-62880-x},
url = {https://doi.org/10.1038/s41598-026-62880-x},
note = {CC BY},
}
RIS
TY - JOUR
TI - Structure-aware learnable multi-scale attention for retinal vessel analysis
AU - Dinoy Johny
AU - V. Chandan
AU - Shubham Loni
AU - A. Devika Gireesh
AU - Vasarla Saimahesh
AU - Kalpana George
AU - Manju Anup
AU - S. S. Anup
AU - P. B. Jayaraj
PY - 2026
DA - 2026/07/01
JO - Scientific Reports
DO - 10.1038/s41598-026-62880-x
UR - https://doi.org/10.1038/s41598-026-62880-x
AB - Accurate retinal vessel segmentation is critical for automated screening and monitoring of ocular and systemic diseases; however, existing deep segmentation models often struggle to preserve thin, low-contrast vessels. We propose a Learnable Multi-Scale Vesselness Attention (LMSA) module, a lightweight and architecture-agnostic component that introduces explicit vessel-aware priors into deep feature learning by adaptively selecting scale-space vesselness responses under a second-order structural prior and refining them through directional coherence modulation. LMSA aggregates multi-scale vesselness responses into a structurally aware representation and transforms them into a spatial attention mask that selectively enhances curvilinear vascular structures while suppressing background noise. Using U-Net as a reference backbone, an LMSA-enhanced network is constructed with an integrated multi-task learning (MTL) design that jointly supervises vessel segmentation, boundary delineation, and centerline extraction, thereby enforcing structural consistency. The generality of the framework is further demonstrated by integrating LMSA and MTL into multiple CNN segmentation architectures. Extensive experiments on three public benchmarks indicate that the proposed U-Net+LMSA+MTL model outperforms state-of-the-art baselines, achieving Dice scores of 85.39%, 85.00%, and 85.47%, with corresponding accuracies of 97.37%, 97.87%, and 97.90% on DRIVE, STARE, and CHASE_DB1, respectively. On a clinically acquired in-house dataset, the model maintains strong performance with a Dice score of 82.77% and an accuracy of 95.88%, supporting its potential for real-world clinical deployment. Collectively, these results demonstrate that the proposed framework effectively embeds vessel prominence and structural priors into deep networks, enabling more reliable, structurally consistent, and clinically meaningful retinal vessel analysis.
SN - 2045-2322
ER -