Joint-octamamba:an octa joint segmentation network based on feature enhanced mamba
This work addresses retinal disease diagnosis by improving segmentation accuracy for clinicians, but it appears incremental as it builds on existing Mamba and joint segmentation methods.
The paper tackles the problem of insufficient accuracy in 2D-based retinal vessel segmentation from OCTA images and performance imbalance in joint segmentation tasks, proposing Joint-OCTAMamba, which outperforms existing models on the OCTA-500 dataset.
OCTA is a crucial non-invasive imaging technique for diagnosing and monitoring retinal diseases like diabetic retinopathy, age-related macular degeneration, and glaucoma. Current 2D-based methods for retinal vessel (RV) segmentation offer insufficient accuracy. To address this, we propose RVMamba, a novel architecture integrating multiple feature extraction modules with the Mamba state-space model. Moreover, existing joint segmentation models for OCTA data exhibit performance imbalance between different tasks. To simultaneously improve the segmentation of the foveal avascular zone (FAZ) and mitigate this imbalance, we introduce FAZMamba and a unified Joint-OCTAMamba framework. Experimental results on the OCTA-500 dataset demonstrate that Joint-OCTAMamba outperforms existing models across evaluation metrics.The code is available at https://github.com/lc-sfis/Joint-OCTAMamba.