Software for interactive segmentation of the carotid artery from 3D black blood magnetic resonance images

• Published in: Computer methods and programs in biomedicine Vol. 75; no. 1; pp. 31 - 43
• Main Authors: Jin, Yuan, Ladak, Hanif M.
• Format: Journal Article
• Language: English
• Published: Ireland Elsevier Ireland Ltd 01.07.2004
• Subjects: Algorithms; Carotid Arteries - anatomy & histology; Deformable models; Diagnosis, Computer-Assisted; Humans; Initialization; Magnetic Resonance Imaging - methods; Medical imaging; Medical Informatics; Segmentation; Software; Deformable models; Initialization; Medical imaging; Segmentation
• ISSN: 0169-2607; 1872-7565
• DOI: 10.1016/j.cmpb.2003.10.003

A semiautomatic algorithm for segmenting organ surfaces from 3D medical images is presented in this work. The algorithm is based on a deformable model, and allows the user to initialize the model by combining and molding primitive shapes such as cylinders and spheres to form an initial approximate model of the organ surface. The initial model is automatically deformed to better fit organ boundaries. The algorithm was applied to segment the carotid bifurcation from 3D black blood magnetic resonance (MR) images of 5 subjects. The algorithm-segmented surfaces were compared to surfaces segmented manually by an experienced user. On average, approximately 3 min were required to segment an image using the algorithm, whereas 1 h was required for manual segmentation. The average distance between corresponding points on the manually and algorithm-segmented surfaces was 0.37 mm, whereas the average maximum distance was 2.03 mm. Moreover, algorithm-segmented surfaces exhibited less intra-operator variability than those segmented manually.