Integrated 3D anatomical model for automatic myocardial segmentation in cardiac CT imagery

• Type of Material: Article
• Authors: N. Dahiya, Georgia Institute of Technology; A. Yezzi, Georgia Institute of Technology; Marina Piccinelli, Emory University; Ernesto Garcia, Emory University
• Language: English
• Date: 2019-11-02
• Publisher: Taylor & Francis
• Publication Version: Author Accepted Manuscript (After Peer Review)
• Copyright Statement: © 2019 Informa UK Limited, trading as Taylor & Francis Group.
• Final Published Version (URL): http://dx.doi.org/10.1080/21681163.2019.1583607
• Title of Journal or Parent Work: Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization
• Volume: 7
• Issue: 5-6
• Start Page: 690
• End Page: 706
• Grant/Funding Information: This work was funded in part by a seed grant from the Coulter Foundation (Cou 2017), National Science Foundation (NSF) grant number CCF-1526848, National Institutes of Health (NIH) grant number R01 HL143350, and Army Research Office grant number ARO W911NF-18-1-0281.
• Keywords: myocardial segmentation; Biomedical Engineering; shape analysis; active contours; principal component analysis; 3D modeling; cardiac tomographic angiography (CTA)
• Research Categories: Engineering, Biomedical; Computer Science; Applied Mechanics

Abstract

Segmentation of epicardial and endocardial boundaries is a critical step in diagnosing cardiovascular function in heart patients. The manual tracing of organ contours in computed tomography angiography (CTA) slices is subjective, time-consuming and impractical in clinical setting. We propose a novel multidimensional automatic edge detection algorithm based on shape priors and principal component analysis (PCA). We have developed a highly customised parametric model for implicit representations of segmenting curves (3D) for left ventricle (LV), right ventricle (RV) and epicardium (Epi) used simultaneously to achieve myocardial segmentation. We have combined these representations in a region-based image modelling framework with high-level constraints enabling the modelling of complex cardiac anatomical structures to automatically guide the segmentation of endo/epicardial boundaries. Test results on 30 short-axis CTA datasets show robust segmentation with error (mean ± std mm) of (1.46 ± 0.41), (2.06 ± 0.65) and (2.88 ± 0.59) for LV, RV and Epi, respectively.