Automated left ventricular segmentation in cardiac MRI

Amol Pednekar; Uday Kurkure; Raja Muthupillai; Scott Flamm; Ioannis A. Kakadiaris

doi:10.1109/TBME.2006.873684

Automated left ventricular segmentation in cardiac MRI

Amol Pednekar, Uday Kurkure, Raja Muthupillai, Scott Flamm, Ioannis A. Kakadiaris

Research output: Contribution to journal › Article › peer-review

120 Scopus citations

Abstract

We present an automated left ventricular (LV) myocardial boundary extraction method. Automatic localization of the LV is achieved using a motion map and an expectation maximization algorithm. The myocardial region is then segmented using an intensity-based fuzzy affinity map and the myocardial contours are extracted by cost minimization through a dynamic programming approach. The results from the automated algorithm compared against the experienced radiologists using Bland and Altman analysis were found to have consistent mean bias of 7% and limits of agreement comparable to the inter-observer variability inherent in the manual method.

Original language	English (US)
Article number	1643412
Pages (from-to)	1425-1428
Number of pages	4
Journal	IEEE Transactions on Biomedical Engineering
Volume	53
Issue number	7
DOIs	https://doi.org/10.1109/TBME.2006.873684
State	Published - Jul 2006

Keywords

Ejection fraction
Fuzzy connectedness
Image segmentation
Left ventricle

ASJC Scopus subject areas

Biomedical Engineering

Access to Document

10.1109/TBME.2006.873684

Cite this

@article{d7ababe7bbc848a48226eec9d2a965f9,

title = "Automated left ventricular segmentation in cardiac MRI",

abstract = "We present an automated left ventricular (LV) myocardial boundary extraction method. Automatic localization of the LV is achieved using a motion map and an expectation maximization algorithm. The myocardial region is then segmented using an intensity-based fuzzy affinity map and the myocardial contours are extracted by cost minimization through a dynamic programming approach. The results from the automated algorithm compared against the experienced radiologists using Bland and Altman analysis were found to have consistent mean bias of 7% and limits of agreement comparable to the inter-observer variability inherent in the manual method.",

keywords = "Ejection fraction, Fuzzy connectedness, Image segmentation, Left ventricle",

author = "Amol Pednekar and Uday Kurkure and Raja Muthupillai and Scott Flamm and Kakadiaris, {Ioannis A.}",

year = "2006",

month = jul,

doi = "10.1109/TBME.2006.873684",

language = "English (US)",

volume = "53",

pages = "1425--1428",

journal = "IEEE Transactions on Biomedical Engineering",

issn = "0018-9294",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "7",

}

TY - JOUR

T1 - Automated left ventricular segmentation in cardiac MRI

AU - Pednekar, Amol

AU - Kurkure, Uday

AU - Muthupillai, Raja

AU - Flamm, Scott

AU - Kakadiaris, Ioannis A.

PY - 2006/7

Y1 - 2006/7

N2 - We present an automated left ventricular (LV) myocardial boundary extraction method. Automatic localization of the LV is achieved using a motion map and an expectation maximization algorithm. The myocardial region is then segmented using an intensity-based fuzzy affinity map and the myocardial contours are extracted by cost minimization through a dynamic programming approach. The results from the automated algorithm compared against the experienced radiologists using Bland and Altman analysis were found to have consistent mean bias of 7% and limits of agreement comparable to the inter-observer variability inherent in the manual method.

AB - We present an automated left ventricular (LV) myocardial boundary extraction method. Automatic localization of the LV is achieved using a motion map and an expectation maximization algorithm. The myocardial region is then segmented using an intensity-based fuzzy affinity map and the myocardial contours are extracted by cost minimization through a dynamic programming approach. The results from the automated algorithm compared against the experienced radiologists using Bland and Altman analysis were found to have consistent mean bias of 7% and limits of agreement comparable to the inter-observer variability inherent in the manual method.

KW - Ejection fraction

KW - Fuzzy connectedness

KW - Image segmentation

KW - Left ventricle

UR - http://www.scopus.com/inward/record.url?scp=33746849826&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33746849826&partnerID=8YFLogxK

U2 - 10.1109/TBME.2006.873684

DO - 10.1109/TBME.2006.873684

M3 - Article

C2 - 16830947

AN - SCOPUS:33746849826

SN - 0018-9294

VL - 53

SP - 1425

EP - 1428

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

IS - 7

M1 - 1643412

ER -

Automated left ventricular segmentation in cardiac MRI

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this