Related Experiment Video
Updated: Jun 18, 2025
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
SARC-UNet: A coronary artery segmentation method based on spatial attention and residual convolution
Fangxun Bao1, Yongqi Zhao1, Xinyue Zhang1
1School of Mathematics, Shandong University, Jinan, Shandong, 250100, China.
Insights
This study introduces SARC-UNet, a novel deep learning model for enhanced coronary artery segmentation in medical images. The method improves accuracy, particularly for small vessels and connectivity, outperforming existing techniques.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Computer Vision
Background:
- Coronary artery segmentation is crucial but challenging due to image quality issues like low light and contrast.
- Existing methods struggle with noise, vascular breakages, and loss of small vessels in coronary angiography.
Purpose of the Study:
- To develop an advanced automatic segmentation network for coronary arteries in angiography images.
- To address limitations of current methods by improving accuracy, vessel connectivity, and small vessel detection.
Main Methods:
- A UNet-based segmentation network (SARC-UNet) incorporating residual convolution and spatial attention was developed.
- Low-light image enhancement (LIME) was applied to improve image clarity and contrast.
- Residual convolution fusion modules (RCFM1, RCFM2) and a location-enhanced spatial attention (LESA) mechanism were integrated.
Main Results:
- The SARC-UNet method demonstrated strong performance across general segmentation metrics.
- The approach significantly improved connectivity indicators compared to existing methods.
- Experimental results showed effective blood vessel segmentation with high accuracy.
Conclusions:
- The proposed SARC-UNet method surpasses state-of-the-art approaches for coronary artery segmentation.
- The model excels particularly in segmenting small blood vessels and maintaining vessel connectivity.
- This work offers a robust solution for improving diagnostic accuracy in cardiovascular imaging.
Background And Objective:
Coronary artery segmentation is a pivotal field that has received increasing attention in recent years. However, this task remains challenging because of the inhomogeneous distributions of the contrast agent and dim light, resulting in noise, vascular breakages and small vessel losses in the obtained segmentation results.
Methods:
To acquire better automatic blood vessel segmentation results for coronary angiography images, a UNet-based segmentation network (SARC-UNet) is constructed for coronary artery segmentation; this approach is based on residual convolution and spatial attention. First, we use the low-light image enhancement (LIME) approach to increase the contrast and clarity levels of coronary angiography images. Then, we design two residual convolution fusion modules (RCFM1 and RCFM2) that can successfully fuse the local and global information of coronary images while also capturing the characteristics of finer-grained blood vessels, hence preventing the loss of tiny blood vessels in the segmentation findings. Finally, using a cascaded waterfall structure, we create a new location-enhanced spatial attention (LESA) mechanism that can efficiently improve the long-distance dependencies between coronary vascular pixel features, eradicating vascular ruptures and noise in the segmentation results.
Results:
This article subjectively and objectively evaluates the experimental results. This method has performed well on five general indicators. Furthermore, it outperforms the connectivity indicators proposed in this article. This method can effectively segment blood vessels and obtain higher accuracy results.
Conclusions:
Numerous experiments have shown that the suggested method outperforms the state-of-the-art approaches, particularly in terms of vessel connectivity and small blood vessel segmentation.
