DS-AdaptNet: An Efficient Retinal Vessel Segmentation Framework With Adaptive Enhancement and Depthwise Separable Convolutions

• Published in: IEEE access Vol. 13; pp. 122207 - 122223
• Main Authors: Chen, Shuting, Hong, Chengxi, Jia, Hong
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2025; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accuracy; adaptive data augmentation; adaptive thresholding; Anatomical structure; Artificial neural networks; Blood vessels; Computational efficiency; Computer architecture; Constraints; Deep learning; depth-separable convolutions; Diagnostic systems; Efficiency; efficient neural networks; Fine structure; Image segmentation; Medical image segmentation; Medical imaging; morphology-aware processing; Optimization; Parameters; Real time; real-time medical analysis; resource-constrained computing; retinal vessel segmentation; Retinal vessels; Technological innovation; topology preservation; Training
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2025.3585611

Medical image segmentation plays a crucial role in diagnosis and treatment planning, yet faces persistent challenges including limited annotated data, boundary ambiguity, and high computational demands that hinder clinical deployment. This paper presents DS-AdaptNet, an efficient segmentation framework that addresses these challenges through two synergistic technical innovations. First, we introduce a Multi-Dimensional Morphological Perturbation Augmentation Technique (MD-PAT) that generates anatomically plausible variations through topologically-constrained deformation fields, significantly enhancing training data diversity while preserving critical structural properties. Second, we develop a Context-Aware Adaptive Threshold Optimization (CA-ATO) algorithm that dynamically determines optimal thresholds by integrating multi-scale contextual information and uncertainty estimates, substantially improving boundary delineation accuracy and fine structure preservation. These techniques are integrated with an Efficient Depthwise Convolutional Neural Network (ED-CNN) architecture that employs depth-separable convolutions, dramatically reducing computational complexity while maintaining high segmentation accuracy. Our comprehensive experiments on three benchmark retinal vessel segmentation datasets demonstrate that the proposed DS-AdaptNet achieves state-of-the-art performance while maintaining exceptional efficiency. Notably, our method attains a Dice coefficient of 0.8328 on DRIVE, 0.8110 on CHASE_DB1, and 0.8515 on STARE, consistently outperforming existing approaches. Most importantly, DS-AdaptNet achieves these results with only 1.57M parameters and 44.08 GFLOPs-a 94.9% reduction in parameters and 77.2% reduction in computational operations compared to standard U-Net. These efficiency gains enable real-time retinal vessel analysis on standard hardware without specialized acceleration, making DS-AdaptNet particularly suitable for resource-constrained clinical environments and telemedicine applications. The proposed framework establishes a foundation for developing practical computer-aided diagnostic systems that balance accuracy, efficiency, and clinical utility.