Multiple two-dimensional active shape model framework for right ventricular segmentation

Hossam El-Rewaidy; Ahmed S Fahmy; Ayman M Khalifa; El-Sayed H Ibrahim

doi:10.1016/j.mri.2021.10.029

Multiple two-dimensional active shape model framework for right ventricular segmentation

Magn Reson Imaging. 2022 Jan:85:177-185. doi: 10.1016/j.mri.2021.10.029. Epub 2021 Oct 20.

Authors

Hossam El-Rewaidy¹, Ahmed S Fahmy², Ayman M Khalifa³, El-Sayed H Ibrahim⁴

Affiliations

¹ Department of Medicine, Beth Israel Deaconess Medical Center and Harvard Medical School, 25 Shattuck St, Boston, MA 02115, USA; Department of Systems and Biomedical Engineering, Cairo University, Cairo University Rd, Giza, Egypt. Electronic address: helrewai@bidmc.harvard.edu.
² Department of Medicine, Beth Israel Deaconess Medical Center and Harvard Medical School, 25 Shattuck St, Boston, MA 02115, USA; Department of Systems and Biomedical Engineering, Cairo University, Cairo University Rd, Giza, Egypt. Electronic address: asfahmy@bidmc.harvard.edu.
³ Department of Biomedical Engineering, Helwan University, Mostafa Fahmy Street, Helwan, Egypt. Electronic address: ayman_khalifa@h-eng.helwan.edu.eg.
⁴ Department of Radiology, Medical College of Wisconsin, 8701 W Watertown Plank Rd, Milwaukee, WI 53226, USA. Electronic address: eibrahim@mcw.edu.

PMID: 34687848
DOI: 10.1016/j.mri.2021.10.029

Abstract

Segmentation of the right ventricle (RV) in MRI short axis images is very challenging due to its complex shape and various appearance among the different subjects and cross-sections. Active shape models (ASM) have shown potential for segmenting the complex structures, including the RV, through two formulations: two- and three-dimensional modeling with a reported trade-off between accuracy and complexity of each formulation. In this work, we propose a new framework for modeling the RV surface using multiple 2D contours, where information from multiple cross-sectional images are incorporated into the same model. The proposed method was tested using cardiac MRI images from 56 human subjects. Compared to a golden reference of manually delineated RV contours, the proposed method resulted in significantly lower error than (almost one half) that of the conventional 2D ASM especially at the apical slices. The mean absolute distance of the proposed method was 2.9 ± 2 mm while the conventional 2D ASM resulted in an error of 6.6 ± 4.5 mm. In addition, the computation time of the proposed method was 5 s compared to 4 ± 1 min previously reported for the 3D ASM formulation.

Keywords: Active shape model; MRI; Multiple-ASM; Right ventricle segmentation.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Algorithms
Heart / diagnostic imaging
Heart Ventricles* / diagnostic imaging
Humans
Imaging, Three-Dimensional* / methods
Magnetic Resonance Imaging / methods