Related Experiment Video
Updated: Sep 3, 2025
Identifying Coronary Artery Calcification on Non-gated Computed Tomography Scans
Published on: August 28, 2018
Development of an approach to extracting coronary arteries and detecting stenosis in invasive coronary angiograms
Chen Zhao1, Haipeng Tang2, Daniel McGonigle2
1Michigan Technological University, Department of Applied Computing, Houghton, Michigan, United States.
Insights
This study introduces a novel AI method for precise coronary artery segmentation and stenosis detection in invasive coronary angiograms, aiming to improve diagnosis for coronary artery disease (CAD). The approach shows promise for enhancing clinical decision-making in CAD management.
Area of Science:
- Medical Imaging
- Artificial Intelligence in Cardiology
- Cardiovascular Disease Research
Background:
- Stable coronary artery disease (CAD) management often involves revascularization, but its benefits over medical therapy regarding mortality and myocardial infarction are not consistently proven.
- Accurate segmentation of coronary arteries and quantification of stenosis from invasive coronary angiograms (ICA) are crucial for effective diagnosis and treatment planning.
Purpose of the Study:
- To develop an automated method for accurate coronary artery segmentation using a multi-input and multiscale (MIMS) U-Net.
- To create a subsequent algorithm for detecting and quantifying arterial stenosis from segmented coronary vessels.
Main Methods:
- A two-stage recurrent training strategy was employed for the MIMS U-Net to segment coronary arteries from ICAs.
- Stage I involved coarse segmentation and probability map generation; Stage II refined segmentation using the original image, probability map, and edge-enhanced image.
- An arterial stenosis detection algorithm was developed post-segmentation to calculate vessel centerlines and diameters.
Main Results:
- The MIMS U-Net achieved an average Dice similarity coefficient of 0.8329, sensitivity of 0.8281, and specificity of 0.9979 for vessel segmentation.
- The stenosis detection algorithm demonstrated a true positive rate of 0.6668 and a positive predictive value of 0.7043.
- The methods were validated on a dataset of 294 ICAs from 73 patients.
Conclusions:
- The proposed automated approach for coronary artery segmentation and stenosis detection shows significant potential for clinical application.
- This technology could aid physicians in making more informed diagnostic and therapeutic decisions for patients with coronary artery disease.
Abstract:
Purpose: In stable coronary artery disease (CAD), reduction in mortality and/or myocardial infarction with revascularization over medical therapy has not been reliably achieved. Coronary arteries are usually extracted to perform stenosis detection. As such, developing accurate segmentation of vascular structures and quantification of coronary arterial stenosis in invasive coronary angiograms (ICA) is necessary. Approach: A multi-input and multiscale (MIMS) U-Net with a two-stage recurrent training strategy was proposed for the automatic vessel segmentation. The proposed model generated a refined prediction map with the following two training stages: (i) stage I coarsely segmented the major coronary arteries from preprocessed single-channel ICAs and generated the probability map of arteries; and (ii) during the stage II, a three-channel image consisting of the original preprocessed image, a generated probability map, and an edge-enhanced image generated from the preprocessed image was fed to the proposed MIMS U-Net to produce the final segmentation result. After segmentation, an arterial stenosis detection algorithm was developed to extract vascular centerlines and calculate arterial diameters to evaluate stenotic level. Results: Experimental results demonstrated that the proposed method achieved an average Dice similarity coefficient of 0.8329, an average sensitivity of 0.8281, and an average specificity of 0.9979 in our dataset with 294 ICAs obtained from 73 patients. Moreover, our stenosis detection algorithm achieved a true positive rate of 0.6668 and a positive predictive value of 0.7043. Conclusions: Our proposed approach has great promise for clinical use and could help physicians improve diagnosis and therapeutic decisions for CAD.
More Related Videos
10:28Interventional Diagnostic Procedure: A Practical Guide for the Assessment of Coronary Vascular Function
Published on: March 15, 2022
13:07Optical Coherence Tomography Based Biomechanical Fluid-Structure Interaction Analysis of Coronary Atherosclerosis Progression
Published on: January 15, 2022
Related Concept Videos
01:30Acute Coronary Syndrome III: Diagnostic Studies
01:25Imaging Studies for Cardiovascular System VI: Calcium -Scoring CT
01:27Coronary Artery Disease V: Interprofessional Care
01:28Imaging Studies for Cardiovascular System V: CT
01:28Cardiac Catheterization I: Pre-Procedure Overview