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

Jordan Ringenberg, Makarand Deo, Vijay Devabhaktuni, Omer Berenfeld, Pamela Boyers, Jeffrey Gold

Research output: Contribution to journalArticle

31 Citations (Scopus)

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.

Original languageEnglish (US)
Pages (from-to)190-201
Number of pages12
JournalComputerized Medical Imaging and Graphics
Volume38
Issue number3
DOIs
StatePublished - Apr 1 2014

Fingerprint

Magnetic resonance imaging
Heart Ventricles
Benchmarking
Testing
Datasets

Keywords

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

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Computer Vision and Pattern Recognition
  • Health Informatics
  • Computer Graphics and Computer-Aided Design

Cite this

Fast, accurate, and fully automatic segmentation of the right ventricle in short-axis cardiac MRI. / Ringenberg, Jordan; Deo, Makarand; Devabhaktuni, Vijay; Berenfeld, Omer; Boyers, Pamela; Gold, Jeffrey.

In: Computerized Medical Imaging and Graphics, Vol. 38, No. 3, 01.04.2014, p. 190-201.

Research output: Contribution to journalArticle

Ringenberg, Jordan ; Deo, Makarand ; Devabhaktuni, Vijay ; Berenfeld, Omer ; Boyers, Pamela ; Gold, Jeffrey. / Fast, accurate, and fully automatic segmentation of the right ventricle in short-axis cardiac MRI. In: Computerized Medical Imaging and Graphics. 2014 ; Vol. 38, No. 3. pp. 190-201.
@article{e9c9a5e51f8d4eda80de06dbe537cc34,
title = "Fast, accurate, and fully automatic segmentation of the right ventricle in short-axis cardiac MRI",
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",
author = "Jordan Ringenberg and Makarand Deo and Vijay Devabhaktuni and Omer Berenfeld and Pamela Boyers and Jeffrey Gold",
year = "2014",
month = "4",
day = "1",
doi = "10.1016/j.compmedimag.2013.12.011",
language = "English (US)",
volume = "38",
pages = "190--201",
journal = "Computerized Medical Imaging and Graphics",
issn = "0895-6111",
publisher = "Elsevier Limited",
number = "3",

}

TY - JOUR

T1 - Fast, accurate, and fully automatic segmentation of the right ventricle in short-axis cardiac MRI

AU - Ringenberg, Jordan

AU - Deo, Makarand

AU - Devabhaktuni, Vijay

AU - Berenfeld, Omer

AU - Boyers, Pamela

AU - Gold, Jeffrey

PY - 2014/4/1

Y1 - 2014/4/1

N2 - 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.

AB - 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.

KW - A priori constraints

KW - Binary difference of Gaussians filter

KW - Cardiac MRI

KW - Optimal thresholding

KW - Ventricular segmentation

UR - http://www.scopus.com/inward/record.url?scp=84893929553&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893929553&partnerID=8YFLogxK

U2 - 10.1016/j.compmedimag.2013.12.011

DO - 10.1016/j.compmedimag.2013.12.011

M3 - Article

C2 - 24456907

AN - SCOPUS:84893929553

VL - 38

SP - 190

EP - 201

JO - Computerized Medical Imaging and Graphics

JF - Computerized Medical Imaging and Graphics

SN - 0895-6111

IS - 3

ER -