Related Experiment Video
Updated: May 22, 2025
Author Spotlight: Advancing Cardiovascular Imaging - Introducing the Spatially Weighted Calcium Score for Early Disease Detection
Published on: September 22, 2023
HWA-ResMamba: automatic segmentation of coronary arteries based on residual Mamba with high-order wavelet-enhanced
Jinzhong Yang1,2, Peng Hong2,3, Lu Wang4
1College of Medicine and Biological Information Engineering, Northeastern University, Shenyang 110169, People's Republic of China.
Insights
This study introduces HWA-ResMamba, a novel deep learning model for accurate coronary artery segmentation, improving diagnosis of coronary artery disease by enhancing feature extraction and long-range dependency modeling.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Cardiovascular Disease Research
Background:
- Automatic segmentation of coronary arteries is vital for diagnosing coronary artery disease (CAD).
- Challenges include fuzzy boundaries, fine branches, and individual variations, hindering accurate segmentation.
- Existing methods struggle with the complexity of coronary artery structures.
Purpose of the Study:
- To develop an advanced deep learning model, HWA-ResMamba, for precise coronary artery segmentation.
- To address the limitations of current methods in capturing subtle details and long-range dependencies.
- To improve the accuracy and reliability of automated coronary artery segmentation for clinical applications.
Main Methods:
- Proposed HWA-ResMamba architecture incorporating high-order wavelet-enhanced convolution (HWCB), residual Mamba (ResMamba), and attention feature aggregation (AFA) modules.
- HWCB captures low-frequency image information for boundary detail.
- ResMamba establishes long-range dependencies, while AFA refines feature aggregation for small branches.
Main Results:
- HWA-ResMamba demonstrated superior performance on three datasets compared to state-of-the-art methods.
- Achieved Dice scores of 0.8857 and Hausdorff Distance of 1.9028 on a self-built dataset, outperforming nnUnet.
- Secured Dice scores of 0.8371 and 0.7861 on public datasets, also surpassing nnUnet.
Conclusions:
- The HWA-ResMamba model offers significant improvements in coronary artery segmentation accuracy.
- The method effectively handles complex anatomical variations and fine structures.
- This contributes to enhanced diagnosis and assessment of coronary artery disease.
Abstract:
Objective.Automatic segmentation of coronary arteries is a crucial prerequisite in assisting in the diagnosis of coronary artery disease. However, due to the fuzzy boundaries, small-slender branches, and significant individual variations, automatic segmentation of coronary arteries is extremely challenging.Approach.This study proposes a residual Mamba with high-order wavelet-enhanced convolution and attention feature aggregation (HWA-ResMamba) for coronary arteries segmentation. The network consists of three core modules: high-order wavelet-enhanced convolution block (HWCB), residual Mamba (ResMamba), and attention feature aggregation (AFA) module. Firstly, the HWCB captures low-frequency information of the image in the shallow layers of the network, allowing for detailed exploration of subtle changes in the boundaries of coronary arteries. Secondly, the ResMamba module establishes long-range dependencies between features in the deep layers of the encoder and at the beginning of the decoder, improving the continuity of the segmentation process. Finally, the AFA module in the decoder reduces semantic differences between the encoder and decoder, which can capture small-slender coronary artery branches and further improve segmentation accuracy.Main results.Experiments on three coronary artery segmentation datasets have shown that the HWA-ResMamba outperforms other state-of-the-art methods in performance and generalization. Specifically, in the self-built dataset, HWA-ResMamba obtained Dice of 0.8857 and Hausdorff Distance (HD) of 1.9028, outperforming nnUnet by 0.0521, and 0.5489, respectively. HWA-ResMamba obtained Dice of 0.8371, and 0.7861 in the two public datasets, outperforming nnUnet by 0.0255, and 0.0107, respectively.Significance.Our method can accurately segment coronary arteries and can contribute to improved diagnosis and assessment of CAD.
