Optimized Vessel Segmentation: A Structure-Agnostic Approach With Small Vessel Enhancement and Morphological Correction.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 41032568.
- Also identified by DOI 10.1109/TIP.2025.3607583.
- No licence information is recorded for this record.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
Abstract
Accurate segmentation of blood vessels is essential for various clinical assessments and postoperative analyses. However, the inherent challenges of vascular imaging-such as sparsity, fine granularity, low contrast, data distribution variability, and the critical need for preserving topological integrity-make generalized vessel segmentation particularly complex. While specialized segmentation methods have been developed for specific anatomical regions, their over-reliance on tailored models hinders broader applicability and generalization. General-purpose segmentation models introduced in medical imaging often fail to address critical vascular characteristics, including the connectivity of segmentation results. In this study, we propose OVS-Net, an optimized vessel segmentation framework designed to generalize across diverse vessel structures and imaging modalities. It introduces a dual-branch architecture design for improving small vessel segmentation and a morphology-aware correction module to preserve vascular topology and connectivity. We compiled a comprehensive multi-modality dataset from 17 datasets to train and benchmark the proposed OVS-Net against 6 SAM-based methods and 17 expert models under various conditions. The results demonstrate that our approach achieves superior segmentation accuracy, generalization, and a 34.6% improvement in connectivity, underscoring its potential for clinical applications. The code and dataset information are available at https://github.com/Hk416mod2/OVS-Net.
Medical subject headings
- Image Processing, Computer-Assisted
- Blood Vessels