Computer-aided diagnosis via model-based shape analysis: automated classification of wall motion abnormalities in echocardiograms

Johan G Bosch; Francisca Nijland; Steven C Mitchell; Boudewijn P F Lelieveldt; Otto Kamp; Johan H C Reiber; Milan Sonka

doi:10.1016/j.acra.2004.11.025

Back

Computer-aided diagnosis via model-based shape analysis: automated classification of wall motion abnormalities in echocardiograms

Journal article

Open access

Peer reviewed

Computer-aided diagnosis via model-based shape analysis: automated classification of wall motion abnormalities in echocardiograms

Johan G Bosch, Francisca Nijland, Steven C Mitchell, Boudewijn P F Lelieveldt, Otto Kamp, Johan H C Reiber and Milan Sonka

Academic radiology, Vol.12(3), pp.358-367

03/2005

DOI: 10.1016/j.acra.2004.11.025

PMID: 15766696

Files and links (1)

url

https://research.vumc.nl/en/publications/d7c14d04-dcc9-4f28-8a27-a3c840a969a5View

Open Access

Abstract

Shape analysis of endocardial contour sequences from echocardiograms can provide classification of wall motion abnormalities (WMA). We previously reported on active appearance motion models (AAMM) for automated detection of endocardial contours in sequences of echocardiograms. The shape analysis of AAMM renders eigenvariations of shape/motion, including typical normal and pathologic endocardial contraction patterns. A set of stress echocardiograms (single-beat four-chamber and two-chamber sequences with expert-verified endocardial contours) of 129 infarct patients was split randomly into training (n = 65) and testing (n = 64) sets. AAMMs were generated from the training set and AAMM shape coefficients (ASCs) were extracted for all sequences and statistically related to regional/global visual wall motion scoring (VWMS) and volumetric parameters. Linear regression showed clear correlations between ASCs and VWMS. Discriminant analysis showed good prediction by ASCs of both segmental (74% correctness) and global WMA (90% correctness). Volumetric parameters correlated poorly to regional VWMS. 1) ASCs show promising accuracy for automated WMA classification. 2) VWMS and endocardial border motion are closely related; with accurate automated border detection, automated WMA classification should be feasible. 3) ASC shape analysis allows contour set evaluation by direct comparison to clinical parameters.

Diagnosis, Computer-Assisted

Humans

Myocardial Contraction - physiology

Cardiac Volume - physiology

Linear Models

Echocardiography, Stress

Myocardial Infarction - diagnostic imaging

Image Processing, Computer-Assisted - methods

Ventricular Dysfunction, Left - diagnostic imaging

Ventricular Dysfunction, Left - physiopathology

Discriminant Analysis

Myocardial Infarction - physiopathology

Neural Networks (Computer)

Details

Title: Subtitle: Computer-aided diagnosis via model-based shape analysis: automated classification of wall motion abnormalities in echocardiograms
Creators: Johan G Bosch - Leiden University Medical Center, Leiden, The Netherlands
Francisca Nijland
Steven C Mitchell
Boudewijn P F Lelieveldt
Otto Kamp
Johan H C Reiber
Milan Sonka
Resource Type: Journal article
Publication Details: Academic radiology, Vol.12(3), pp.358-367
DOI: 10.1016/j.acra.2004.11.025
PMID: 15766696
NLM abbreviation: Acad Radiol
ISSN: 1076-6332
eISSN: 1878-4046
Publisher: United States
Grant note: R01 HL071809 / NHLBI NIH HHS
Language: English
Date published: 03/2005
Academic Unit: Roy J. Carver Department of Biomedical Engineering; Electrical and Computer Engineering; Radiation Oncology; Injury Prevention Research Center; Ophthalmology and Visual Sciences
Record Identifier: 9984047996202771

Metrics

22 Record Views

25 Times Cited - Web of Science