Related Experiment Video
Updated: Sep 26, 2025
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
Recursive Centerline- and Direction-Aware Joint Learning Network with Ensemble Strategy for Vessel Segmentation in
Tao Han1, Danni Ai1, Yining Wang2
1Laboratory of Beijing Engineering Research Center of Mixed Reality and Advanced Display, School of Optics and Photonics, Beijing Institute of Technology, Beijing, 100081, China.
Insights
This study introduces a novel recursive joint learning network for improved automatic vessel segmentation in X-ray angiography (XRA) images. The method enhances segmentation accuracy and completeness, crucial for cardiovascular disease diagnosis.
Area of Science:
- Medical Imaging
- Cardiovascular Disease Research
- Artificial Intelligence in Healthcare
Background:
- Automatic vessel segmentation from X-ray angiography (XRA) images is critical for diagnosing and treating cardiovascular diseases.
- Existing methods struggle with poor image quality and complexity, often yielding incomplete or broken vessel segmentation results due to a lack of geometric feature consideration.
Purpose of the Study:
- To develop an improved method for automatic vessel segmentation in XRA images that enhances both completeness and accuracy.
- To address the limitations of existing pixel-wise segmentation approaches by incorporating geometric vessel features.
Main Methods:
- A recursive joint learning network is proposed, integrating centerline- and direction-aware auxiliary tasks with primary segmentation.
- A recursive learning strategy iteratively refines segmentation by feeding previous results back into the network.
- A complementary-task ensemble strategy with majority voting fuses outputs from multiple tasks to enhance vessel connectivity.
Main Results:
- The proposed method demonstrates superior performance in qualitative and quantitative experiments on coronary artery and aorta XRA images.
- Achieved high F1 scores: 85.61% for coronary artery, 89.02% for aortic arch, 88.22% for thoracic aorta, and 83.12% for abdominal aorta.
Conclusions:
- The developed recursive joint learning network significantly improves vessel segmentation completeness and accuracy compared to state-of-the-art methods.
- The integration of geometric features and recursive learning offers a promising advancement for cardiovascular imaging analysis.
Background And Objective:
Automatic vessel segmentation from X-ray angiography images is an important research topic for the diagnosis and treatment of cardiovascular disease. The main challenge is how to extract continuous and completed vessel structures from XRA images with poor quality and high complexity. Most existing methods predominantly focus on pixel-wise segmentation and overlook the geometric features, resulting in breaking and absence in segmentation results. To improve the completeness and accuracy of vessel segmentation, we propose a recursive joint learning network embedded with geometric features.
Methods:
The network joins the centerline- and direction-aware auxiliary tasks with the primary task of segmentation, which guides the network to explore the geometric features of vessel connectivity. Moreover, the recursive learning strategy is designed by passing the previous segmentation result into the same network iteratively to improve segmentation. To further enhance connectivity, we present a complementary-task ensemble strategy by fusing the outputs of the three tasks for the final segmentation result with majority voting.
Results:
To validate the effectiveness of our method, we conduct qualitative and quantitative experiments on the XRA images of the coronary artery and aorta including aortic arch, thoracic aorta, and abdominal aorta. Our method achieves F1 scores of 85.61±3.48% for the coronary artery, 89.02±2.89% for the aortic arch, 88.22±3.33% for the thoracic aorta, and 83.12±4.61% for the abdominal aorta.
Conclusions:
Compared with six state-of-the-art methods, our method shows the most complete and accurate vessel segmentation results.
Related Concept Videos
01:19Imaging Studies VII: Vascular Imaging
01:20Anatomy of Blood Vessels
Arteries
Arteries circulate oxygenated blood from the heart, except the pulmonary artery, which transports deoxygenated blood to the lungs. Large arteries, such as the aorta,...
01:20Imaging Studies for Cardiovascular System III: X-Ray
Definition and Purpose
An X-ray, or radiograph, is a non-invasive method that uses ionizing radiation to take images of internal structures. It is mainly used in cardiac imaging to examine the heart, lungs, and major blood vessels, aiming to identify abnormalities in the heart's size, shape, and position, such as heart failure, congenital defects, and vascular...
01:28Imaging Studies for Cardiovascular System V: CT