Format

Send to

Choose Destination
See comment in PubMed Commons below
Comput Med Imaging Graph. 2014 Apr;38(3):190-201. doi: 10.1016/j.compmedimag.2013.12.011. Epub 2014 Jan 2.

Fast, accurate, and fully automatic segmentation of the right ventricle in short-axis cardiac MRI.

Author information

1
EECS Department, College of Engineering, University of Toledo, 2801 W. Bancroft Street, Toledo, OH 43606, United States. Electronic address: jordan.ringenberg@utoledo.edu.
2
Department of Engineering, Norfolk State University, 700 Park Avenue, Norfolk, VA 23504, United States.
3
EECS Department, College of Engineering, University of Toledo, 2801 W. Bancroft Street, Toledo, OH 43606, United States.
4
Center for Arrhythmia Research, Department of Internal Medicine, University of Michigan, 1500 E. Medical Center Drive, Ann Arbor, MI 48109, United States.
5
Interprofessional Immersive Simulation Center, University of Toledo, 3000 Arlington Avenue, Toledo, OH 43614, United States.

Abstract

This paper presents a fully automatic method to segment the right ventricle (RV) from short-axis cardiac MRI. A combination of a novel window-constrained accumulator thresholding technique, binary difference of Gaussian (DoG) filters, optimal thresholding, and morphology are utilized to drive the segmentation. A priori segmentation window constraints are incorporated to guide and refine the process, as well as to ensure appropriate area confinement of the segmentation. Training and testing were performed using a combined 48 patient datasets supplied by the organizers of the MICCAI 2012 right ventricle segmentation challenge, allowing for unbiased evaluations and benchmark comparisons. Marked improvements in speed and accuracy over the top existing methods are demonstrated.

KEYWORDS:

A priori constraints; Binary difference of Gaussians filter; Cardiac MRI; Optimal thresholding; Ventricular segmentation

[Indexed for MEDLINE]
PubMed Commons home

PubMed Commons

0 comments
How to join PubMed Commons

    Supplemental Content

    Full text links

    Icon for Elsevier Science
    Loading ...
    Support Center