Related Experiment Video
Updated: May 12, 2026
A Methodological Approach to Non-invasive Assessments of Vascular Function and Morphology
Published on: February 7, 2015
Ultrasound common carotid artery segmentation based on active shape model
Xin Yang1, Jiaoying Jin, Mengling Xu
1State Key Laboratory for Multispectral Information Processing Technologies, Institute for Pattern Recognition and Artificial Intelligence (IPRAI), Huazhong University of Science and Technology (HUST), Wuhan, Hubei 430074, China.
A new Active Shape Model (ASM) method accurately segments carotid arteries in 3D ultrasound images, aiding in the evaluation of carotid atherosclerosis and stroke risk. This automated approach significantly reduces segmentation time compared to manual methods.
Area of Science:
- Medical Imaging
- Biomedical Engineering
- Cardiovascular Research
Background:
- Carotid atherosclerosis is a primary cause of stroke, necessitating advanced diagnostic tools.
- Accurate segmentation of the common carotid artery (CCA) is crucial for evaluating atherosclerotic disease.
Purpose of the Study:
- To develop and evaluate an Active Shape Model (ASM) based segmentation method for CCA.
- To enable computer-aided evaluation and diagnosis of carotid atherosclerosis using 3D ultrasound (3D US) images.
Main Methods:
- The proposed method segments media-adventitia-boundary (MAB) and lumen-intima-boundary (LIB) on 3D US transverse slices.
- The dataset included 68 3D US volumes from patients with significant carotid stenosis, treated with atorvastatin or placebo.
- Manual expert outlines served as the ground truth for performance evaluation.
Main Results:
- The ASM method achieved high accuracy with Dice Similarity Coefficient (DSC) of 94.4% for MAB and 92.8% for LIB.
- Mean absolute distances (MAD) were 0.26 mm (MAB) and 0.33 mm (LIB), with maximum distances (MAXD) of 0.75 mm and 0.84 mm, respectively.
- Automated segmentation time was 4.3 minutes, significantly faster than manual segmentation (11.7 minutes).
Conclusions:
- The developed ASM segmentation method demonstrates high accuracy and efficiency for CCA analysis in 3D US.
- This automated approach facilitates clinical translation for monitoring atherosclerotic disease progression and regression.
- The method holds potential for improving stroke prevention strategies through enhanced diagnostic capabilities.
