Related Experiment Video
Updated: Feb 14, 2026
Author Spotlight: Advancements in X-ray CT Tool Chain for Tree Core Analysis
Published on: September 22, 2023
Automated coronary artery tree segmentation in X-ray angiography using improved Hessian based enhancement and
Tao Wan1, Xiaoqing Shang1, Weilin Yang2
1Medical Image Analysis Lab, School of Biomedical Science and Medical Engineering, Beihang University, Beijing 100191, China.
Insights
This study introduces an automated method for coronary artery segmentation from angiography images, achieving 93% accuracy. This technique aids in the early detection of coronary artery disease, outperforming existing segmentation approaches.
Area of Science:
- Medical Imaging
- Computer-Aided Diagnosis
- Cardiology
Background:
- Coronary artery segmentation is crucial for detecting heart disease.
- Manual segmentation is time-consuming and challenging for radiologists.
- Automated methods are needed to improve efficiency and accuracy.
Purpose of the Study:
- To develop and validate a novel computerized method for automatic coronary artery segmentation.
- To enhance the detection of complex and thin vessel structures.
- To assist cardiothoracic radiologists in diagnosing coronary artery disease.
Main Methods:
- A combination of multiscale-based adaptive Hessian enhancement and statistical region merging was employed.
- The method was validated on coronary angiography images from 100 patients.
- Performance was assessed using qualitative and quantitative evaluations.
Main Results:
- The automated method achieved 93% accuracy in identifying coronary artery trees.
- It outperformed existing methods in mean absolute difference and dice similarity coefficient.
- The technique effectively delineated complex and thin vessel structures.
Conclusions:
- The developed automated segmentation method shows potential for computer-aided diagnosis systems.
- It offers a reliable tool for the early detection of coronary artery disease.
- The method's performance is comparable to manual segmentation by human observers.
Background And Objective:
Coronary artery segmentation is a fundamental step for a computer-aided diagnosis system to be developed to assist cardiothoracic radiologists in detecting coronary artery diseases. Manual delineation of the vasculature becomes tedious or even impossible with a large number of images acquired in the daily life clinic. A new computerized image-based segmentation method is presented for automatically extracting coronary arteries from angiography images.
Methods:
A combination of a multiscale-based adaptive Hessian-based enhancement method and a statistical region merging technique provides a simple and effective way to improve the complex vessel structures as well as thin vessel delineation which often missed by other segmentation methods. The methodology was validated on 100 patients who underwent diagnostic coronary angiography. The segmentation performance was assessed via both qualitative and quantitative evaluations.
Results:
Quantitative evaluation shows that our method is able to identify coronary artery trees with an accuracy of 93% and outperforms other segmentation methods in terms of two widely used segmentation metrics of mean absolute difference and dice similarity coefficient.
Conclusions:
The comparison to the manual segmentations from three human observers suggests that the presented automated segmentation method is potential to be used in an image-based computerized analysis system for early detection of coronary artery disease.
More Related Videos
Related Concept Videos
01:30Coronary Artery Disease I: Introduction
01:26Coronary Artery Disease II: Pathophysiology
01:27Coronary Artery Disease V: Interprofessional Care
02:40The Tree of Life - Bacteria, Archaea, Eukaryotes
01:30Coronary Artery Disease III: Clinical Manifestations
01:26Coronary Artery Disease IV: Preventive Measures