Segmentation of the right ventricle in four chamber cine cardiac MR images using polar dynamic programming

Jose A. Rosado-Toro, Aiden Abidov, Maria I Altbach, Isabel B. Oliva, Jeffrey J Rodriguez, Ryan J. Avery

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The four chamber plane is currently underutilized in the right ventricular segmentation community. Four chamber information can be useful to determine ventricular short axis stacks and provide a rough estimate of the right ventricle in short axis stacks. In this study, we develop and test a semi-automated technique for segmenting the right ventricle in four chamber cine cardiac magnetic resonance images. The three techniques that use minimum cost path algorithms were used. The algorithms are: Dijkstra's shortest path algorithm (Dijkstra), an A* algorithm that uses length, curvature and torsion into an active contour model (ALCT), and a variation of polar dynamic programming (PDP). The techniques are evaluated against the expert traces using 175 cardiac images from 7 patients. The evaluation first looks at mutual overlap metrics and then focuses on clinical measures such as fractional area change (FAC). The mean mutual overlap between the physician's traces ranged from 0.85 to 0.88. Using as reference physician 1's landmarks and traces (i.e., comparing the traces from physician 1 to the semi-automated segmentation using physician 1's landmarks), the PDP algorithm has a mean mutual overlap of 0.8970 compared to 0.8912 for ALCT and 0.8879 for Dijkstra. The mean mutual overlap between the BP regions generated by physician 1 and physician 2 landmarks are 0.9674, 0.9605 and 0.9531 for PDP, ALCT and Dijkstra, respectively. The FAC correlation coefficient between the physician's traces ranged from 0.73 to 0.93.

Original languageEnglish (US)
JournalComputerized Medical Imaging and Graphics
DOIs
StateAccepted/In press - 2017

Fingerprint

Dynamic programming
Heart Ventricles
Physicians
Magnetic resonance
Torsional stress
Magnetic Resonance Spectroscopy
Costs and Cost Analysis
Costs

Keywords

  • Four chamber right ventricle segmentation
  • Polar dynamic programming
  • Polar variance

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

@article{e2f0953ecc514402bab1812cdd150ece,
title = "Segmentation of the right ventricle in four chamber cine cardiac MR images using polar dynamic programming",
abstract = "The four chamber plane is currently underutilized in the right ventricular segmentation community. Four chamber information can be useful to determine ventricular short axis stacks and provide a rough estimate of the right ventricle in short axis stacks. In this study, we develop and test a semi-automated technique for segmenting the right ventricle in four chamber cine cardiac magnetic resonance images. The three techniques that use minimum cost path algorithms were used. The algorithms are: Dijkstra's shortest path algorithm (Dijkstra), an A* algorithm that uses length, curvature and torsion into an active contour model (ALCT), and a variation of polar dynamic programming (PDP). The techniques are evaluated against the expert traces using 175 cardiac images from 7 patients. The evaluation first looks at mutual overlap metrics and then focuses on clinical measures such as fractional area change (FAC). The mean mutual overlap between the physician's traces ranged from 0.85 to 0.88. Using as reference physician 1's landmarks and traces (i.e., comparing the traces from physician 1 to the semi-automated segmentation using physician 1's landmarks), the PDP algorithm has a mean mutual overlap of 0.8970 compared to 0.8912 for ALCT and 0.8879 for Dijkstra. The mean mutual overlap between the BP regions generated by physician 1 and physician 2 landmarks are 0.9674, 0.9605 and 0.9531 for PDP, ALCT and Dijkstra, respectively. The FAC correlation coefficient between the physician's traces ranged from 0.73 to 0.93.",
keywords = "Four chamber right ventricle segmentation, Polar dynamic programming, Polar variance",
author = "Rosado-Toro, {Jose A.} and Aiden Abidov and Altbach, {Maria I} and Oliva, {Isabel B.} and Rodriguez, {Jeffrey J} and Avery, {Ryan J.}",
year = "2017",
doi = "10.1016/j.compmedimag.2017.08.002",
language = "English (US)",
journal = "Computerized Medical Imaging and Graphics",
issn = "0895-6111",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Segmentation of the right ventricle in four chamber cine cardiac MR images using polar dynamic programming

AU - Rosado-Toro, Jose A.

AU - Abidov, Aiden

AU - Altbach, Maria I

AU - Oliva, Isabel B.

AU - Rodriguez, Jeffrey J

AU - Avery, Ryan J.

PY - 2017

Y1 - 2017

N2 - The four chamber plane is currently underutilized in the right ventricular segmentation community. Four chamber information can be useful to determine ventricular short axis stacks and provide a rough estimate of the right ventricle in short axis stacks. In this study, we develop and test a semi-automated technique for segmenting the right ventricle in four chamber cine cardiac magnetic resonance images. The three techniques that use minimum cost path algorithms were used. The algorithms are: Dijkstra's shortest path algorithm (Dijkstra), an A* algorithm that uses length, curvature and torsion into an active contour model (ALCT), and a variation of polar dynamic programming (PDP). The techniques are evaluated against the expert traces using 175 cardiac images from 7 patients. The evaluation first looks at mutual overlap metrics and then focuses on clinical measures such as fractional area change (FAC). The mean mutual overlap between the physician's traces ranged from 0.85 to 0.88. Using as reference physician 1's landmarks and traces (i.e., comparing the traces from physician 1 to the semi-automated segmentation using physician 1's landmarks), the PDP algorithm has a mean mutual overlap of 0.8970 compared to 0.8912 for ALCT and 0.8879 for Dijkstra. The mean mutual overlap between the BP regions generated by physician 1 and physician 2 landmarks are 0.9674, 0.9605 and 0.9531 for PDP, ALCT and Dijkstra, respectively. The FAC correlation coefficient between the physician's traces ranged from 0.73 to 0.93.

AB - The four chamber plane is currently underutilized in the right ventricular segmentation community. Four chamber information can be useful to determine ventricular short axis stacks and provide a rough estimate of the right ventricle in short axis stacks. In this study, we develop and test a semi-automated technique for segmenting the right ventricle in four chamber cine cardiac magnetic resonance images. The three techniques that use minimum cost path algorithms were used. The algorithms are: Dijkstra's shortest path algorithm (Dijkstra), an A* algorithm that uses length, curvature and torsion into an active contour model (ALCT), and a variation of polar dynamic programming (PDP). The techniques are evaluated against the expert traces using 175 cardiac images from 7 patients. The evaluation first looks at mutual overlap metrics and then focuses on clinical measures such as fractional area change (FAC). The mean mutual overlap between the physician's traces ranged from 0.85 to 0.88. Using as reference physician 1's landmarks and traces (i.e., comparing the traces from physician 1 to the semi-automated segmentation using physician 1's landmarks), the PDP algorithm has a mean mutual overlap of 0.8970 compared to 0.8912 for ALCT and 0.8879 for Dijkstra. The mean mutual overlap between the BP regions generated by physician 1 and physician 2 landmarks are 0.9674, 0.9605 and 0.9531 for PDP, ALCT and Dijkstra, respectively. The FAC correlation coefficient between the physician's traces ranged from 0.73 to 0.93.

KW - Four chamber right ventricle segmentation

KW - Polar dynamic programming

KW - Polar variance

UR - http://www.scopus.com/inward/record.url?scp=85028774700&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85028774700&partnerID=8YFLogxK

U2 - 10.1016/j.compmedimag.2017.08.002

DO - 10.1016/j.compmedimag.2017.08.002

M3 - Article

C2 - 28886885

AN - SCOPUS:85028774700

JO - Computerized Medical Imaging and Graphics

JF - Computerized Medical Imaging and Graphics

SN - 0895-6111

ER -