Optic disc and cup segmentation using Vision Mamba UNet with enhanced edge-guided attention in fundus images
- 1School of Medicine and Health, Guangzhou Xinhua University, Guangzhou, 510520 China
Abstract
Background: Glaucoma is an irreversible blinding disease for which early detection is essential. Precise segmentation of the optic disc (OD) and optic cup (OC) enables accurate cup-to-disc ratio (CDR) calculation, which serves as an important reference for glaucoma evaluation. However, the ambiguous boundaries between these structures make manual segmentation time-consuming and highly subjective.
Methods: This study proposes a hybrid framework for OD and OC segmentation in fundus images. The framework first adopts YOLOv10 to achieve coarse localization and extraction of the OD region, followed by fine-grained segmentation using the proposed EEGA-VMUNet network. Based on a Vision Mamba-UNet backbone, we design an enhanced edge-guided attention (EEGA) module to adaptively integrate multi-scale contextual information. This module strengthens the representation of edges and fine structural features. A multi-scale loss function is also used to improve robustness to scale variations.
Results: Experiments on four benchmark datasets demonstrate that EEGA-VMUNet achieves competitive segmentation performance. On the same-domain test sets, OD Dice coefficients range from 95.20% to 97.65% and OC Dice coefficients range from 87.51% to 89.95%. Zero-shot cross-domain experiments achieve an OD Dice of 95.18% and an OC Dice of 85.13%.
Conclusion: The proposed model achieves competitive performance in both OD and OC segmentation tasks. Bland-Altman analysis suggests that the derived vertical cup-to-disc ratio (VCDR) holds potential as a diagnostic aid for glaucoma screening, although its precision may require further improvement for longitudinal monitoring.
Supplementary Information: The online version contains supplementary material available at https://doi.org/10.1186/s12886-026-05371-x.
Related
- Hybrid feature pyramid attention and capsule network (FpaNet+CapsNet) for enhanced spatial and contextual feature extraction for improved brain tumor segmentation
- A segmentation-guided CNN–Vision transformer feature fusion framework for multi-class breast ultrasound image classification
- An attention-guided dense convolutional network for automated diabetic foot ulcer segmentation
- UGB-SegNet: Uncertainty-Guided Multi-Scale Attention and Boundary-Aware Learning for Breast Ultrasound Lesion Segmentation
- Automatic segmentation of liver tumors based on attention-guided 3D U-Net using LiTS dataset revision
BibTeX
@article{cai2026optic,
title = {{Optic disc and cup segmentation using Vision Mamba UNet with enhanced edge-guided attention in fundus images}},
author = {Lili Cai and Keke Hou and Zhong Mo},
journal = {BMC Ophthalmology},
year = {2026},
month = oct,
doi = {10.1186/s12886-026-05371-x},
url = {https://doi.org/10.1186/s12886-026-05371-x},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Optic disc and cup segmentation using Vision Mamba UNet with enhanced edge-guided attention in fundus images
AU - Lili Cai
AU - Keke Hou
AU - Zhong Mo
PY - 2026
DA - 2026/10/23
JO - BMC Ophthalmology
DO - 10.1186/s12886-026-05371-x
UR - https://doi.org/10.1186/s12886-026-05371-x
AB - Background: Glaucoma is an irreversible blinding disease for which early detection is essential. Precise segmentation of the optic disc (OD) and optic cup (OC) enables accurate cup-to-disc ratio (CDR) calculation, which serves as an important reference for glaucoma evaluation. However, the ambiguous boundaries between these structures make manual segmentation time-consuming and highly subjective. Methods: This study proposes a hybrid framework for OD and OC segmentation in fundus images. The framework first adopts YOLOv10 to achieve coarse localization and extraction of the OD region, followed by fine-grained segmentation using the proposed EEGA-VMUNet network. Based on a Vision Mamba-UNet backbone, we design an enhanced edge-guided attention (EEGA) module to adaptively integrate multi-scale contextual information. This module strengthens the representation of edges and fine structural features. A multi-scale loss function is also used to improve robustness to scale variations. Results: Experiments on four benchmark datasets demonstrate that EEGA-VMUNet achieves competitive segmentation performance. On the same-domain test sets, OD Dice coefficients range from 95.20% to 97.65% and OC Dice coefficients range from 87.51% to 89.95%. Zero-shot cross-domain experiments achieve an OD Dice of 95.18% and an OC Dice of 85.13%. Conclusion: The proposed model achieves competitive performance in both OD and OC segmentation tasks. Bland-Altman analysis suggests that the derived vertical cup-to-disc ratio (VCDR) holds potential as a diagnostic aid for glaucoma screening, although its precision may require further improvement for longitudinal monitoring. Supplementary Information: The online version contains supplementary material available at https://doi.org/10.1186/s12886-026-05371-x.
SN - 1471-2415
ER -