3D carotid artery segmentation using shape-constrained active contours. (February 2023)

• Record Type: Journal Article
• Authors: Huang, Xianjue; Wang, Jun; Li, Zhiyong
• Is Part Of: Computers in biology and medicine. Volume 153(2023)
• Publication Date: 2023-02
• Subjects: Magnetic resonance imaging -- Active contours -- Carotid artery segmentation -- Deep learning -- Level set method -- Vessel segmentation; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2022.106530
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Reconstruction of the carotid artery is demanded in the detection and characterization of atherosclerosis. This study proposes a shape-constrained active contour model for segmenting the carotid artery from MR images, which embeds the output of the deep learning network into the active contour. First the centerline of the carotid artery is localized and then modified active contour initialized from the centerline is used to extract the vessel lumen, finally the probability atlas generated by the deep learning network in polar representation domain is integrated into the active contour as a prior information to detect the outer wall. The results showed that the proposed active contour model was efficient and comparable to manual segmentation. Highlights: A shape-constrained active contour model (SACM) is proposed for segmenting the carotid artery from MR images. The shape-constraint maps generated by 2.5D CNN are integrated into SACM as prior information to detect the vessel wall. The effectiveness of the proposed method is demonstrated by clinical data (25 patients, 4500 images). The proposed method is shown to be feasible after being compared against manual delineations.