Related Experiment Video
Updated: Mar 6, 2026
Two-Dimensional X-Ray Angiography to Examine Fine Vascular Structure Using a Silicone Rubber Injection Compound
Published on: January 7, 2019
Vessel extraction in X-ray angiograms using deep learning
Insights
This study introduces a deep learning method using convolutional neural networks (CNN) to improve coronary artery disease (CAD) diagnosis by enhancing vessel detection in X-ray angiograms, leading to superior vessel segmentation performance.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Cardiology
Background:
- Coronary artery disease (CAD) is a leading global cause of death.
- X-ray angiography is the standard for CAD diagnosis but yields low-quality, noisy images.
- Accurate vessel enhancement and segmentation are crucial for CAD diagnosis.
Purpose of the Study:
- To propose a deep learning approach for precise vessel region detection in angiograms.
- To enhance the diagnostic accuracy of coronary artery disease (CAD).
Main Methods:
- Utilized a deep convolutional neural network (CNN) for image analysis.
- Preprocessed angiograms to improve contrast.
- Trained the CNN on 1,040,000 pixel patches to differentiate vessel and background regions.
Main Results:
- The proposed deep learning method demonstrated superior performance in extracting vessel regions.
- Achieved enhanced vessel segmentation in low-quality angiographic images.
Conclusions:
- Deep learning, specifically CNNs, offers a powerful tool for improving vessel detection in coronary angiography.
- This approach holds significant potential for enhancing the diagnosis of coronary artery disease (CAD).
Abstract:
Coronary artery disease (CAD) is the most common type of heart disease which is the leading cause of death all over the world. X-ray angiography is currently the gold standard imaging technique for CAD diagnosis. These images usually suffer from low quality and presence of noise. Therefore, vessel enhancement and vessel segmentation play important roles in CAD diagnosis. In this paper a deep learning approach using convolutional neural networks (CNN) is proposed for detecting vessel regions in angiography images. Initially, an input angiogram is preprocessed to enhance its contrast. Afterward, the image is evaluated using patches of pixels and the network determines the vessel and background regions. A set of 1,040,000 patches is used in order to train the deep CNN. Experimental results on angiography images of a dataset show that our proposed method has a superior performance in extraction of vessel regions.
Related Concept Videos
01:19Imaging Studies VII: Vascular Imaging
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...