Related Experiment Video
Updated: May 21, 2026
Analyzing Neural Activity and Connectivity Using Intracranial EEG Data with SPM Software
Published on: October 30, 2018
Wavelet-enhanced spatiotemporal connectivity-preserving network for intracranial artery segmentation in DSA sequences
Yingchao He1,2, Mingfeng Lv3, Yi Yang3
1Department of Neurology, Fuzhou University Affiliated Provincial Hospital, Fuzhou, 350000, Fujian, China.
Insights
A new AI model, WESCP-Net, precisely segments intracranial arteries from Digital Subtraction Angiography. It improves accuracy and connectivity for diagnosing cerebrovascular diseases and guiding surgery.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Biomedical Engineering
Background:
- Accurate intracranial artery segmentation is vital for cerebrovascular disease diagnosis and treatment.
- Traditional methods face challenges with spatiotemporal dependencies, leading to vessel discontinuity and loss of fine details.
Purpose of the Study:
- To introduce the Wavelet-Enhanced Spatiotemporal Connectivity-Preserving Network (WESCP-Net) for improved intracranial artery segmentation.
- To address limitations in capturing dynamic vascular information and preserving fine vessel structures.
Main Methods:
- Developed WESCP-Net, integrating physical priors and frequency-domain feature extraction.
- Employed a Physically-Guided Spatiotemporal Enhancement module using hemodynamic flow variance.
- Incorporated a Wavelet-Integrated Encoder and Topology-Aware Reconstruction module for detail preservation.
Main Results:
- WESCP-Net achieved state-of-the-art performance on the DIAS dataset.
- Achieved a Dice Similarity Coefficient of 0.7982 and Intersection over Union of 0.6422.
- Demonstrated improved vascular terminal continuity with a clDice metric of 0.7135.
Conclusions:
- WESCP-Net offers a robust framework for precise cerebrovascular segmentation.
- The model enhances surgical navigation and quantitative diagnosis of cerebrovascular diseases.
- The approach effectively preserves vessel connectivity and high-frequency details.
Abstract:
Accurate intracranial artery segmentation from Digital Subtraction Angiography is critical for the diagnosis and interventional treatment of cerebrovascular diseases. However, traditional methods struggle to capture dynamic spatiotemporal dependencies, often leading to vascular discontinuity and the loss of fine distal vessels due to background interference and resolution loss. In this study, we propose the Wavelet-Enhanced Spatiotemporal Connectivity-Preserving Network (WESCP-Net), a novel framework designed to synergize physical priors with frequency-domain feature extraction. Specifically, we introduce a Physically-Guided Spatiotemporal Enhancement module that explicitly exploits hemodynamic flow variance to differentiate active vascular signals from static artifacts. To address the loss of high-frequency spatial details in standard downsampling, we incorporate a Wavelet-Integrated Encoder and a Topology-Aware Reconstruction module, which utilize discrete wavelet transforms to preserve sharp vessel boundaries and restore structural connectivity. Experimental results on the DIAS dataset demonstrate that WESCP-Net achieves state-of-the-art performance, yielding a Dice Similarity Coefficient of 0.7982 and an Intersection over Union score of 0.6422. Notably, its connectivity-preserving mechanism achieves a clDice metric of 0.7135, improving the continuity of vascular terminals. WESCP-Net provides a robust technological paradigm for precise cerebrovascular segmentation, facilitating reliable surgical navigation and quantitative diagnosis.
