Automatic segmentation of echocardiographic sequences by active appearance motion models

Johan G BOSCH; Steven C MITCHELL; Boudewijn P. F LELIEVELDT; Francisca NIJLAND; Otto KAMP; Milan SONKA; Johan H. C. SR REIBER

doi:10.1109/TMI.2002.806427

Back

Automatic segmentation of echocardiographic sequences by active appearance motion models

Journal article

Peer reviewed

Automatic segmentation of echocardiographic sequences by active appearance motion models

Johan G BOSCH, Steven C MITCHELL, Boudewijn P. F LELIEVELDT, Francisca NIJLAND, Otto KAMP, Milan SONKA and Johan H. C. SR REIBER

IEEE transactions on medical imaging, Vol.21(11), pp.1374-1383

2002

DOI: 10.1109/TMI.2002.806427

PMID: 12575874

View Online

Abstract

A novel extension of active appearance models (AAMs) for automated border detection in echocardiographic image sequences is reported. The active appearance motion model (AAMM) technique allows fully automated robust and time-continuous delineation of left ventricular (LV) endocardial contours over the full heart cycle with good results. Nonlinear intensity normalization was developed and employed to accommodate ultrasound-specific intensity distributions. The method was trained and tested on 16-frame phase-normalized transthoracic four-chamber sequences of 129 unselected infarct patients, split randomly into a training set (n=65) and a test set (n=64). Borders were compared to expert drawn endocardial contours. On the test set, fully automated AAMM performed well in 97% of the cases (average distance between manual and automatic landmark points was 3.3 mm, comparable to human interobserver variabilities). The ultrasound-specific intensity normalization proved to be of great value for good results in echocardiograms. The AAMM was significantly more accurate than an equivalent set of two-dimensional AAMs.

Cardiovascular System

Ultrasonic investigative techniques

Biological and medical sciences

Investigative techniques, diagnostic techniques (general aspects)

Medical sciences

Details

Title: Subtitle: Automatic segmentation of echocardiographic sequences by active appearance motion models
Creators: Johan G BOSCH - Division of Image Processing (LKEB), Department of Radiology, Leiden University Medical Center, P.O. Box 9600, 2300 RC Leiden, Netherlands
Steven C MITCHELL - Department of Electrical and Computer Engineering, University of Iowa, Iowa City, IA 52242, United States
Boudewijn P. F LELIEVELDT - Division of Image Processing, Department of Radiology, Leiden University Medical Center, 2300 RC Leiden, Netherlands
Francisca NIJLAND - Department of Cardiology, Vrije Universiteit Medical Center, 1081 HV Amsterdam, Netherlands
Otto KAMP - Department of Cardiology, Vrije Universiteit Medical Center, 1081 HV Amsterdam, Netherlands
Milan SONKA - Department of Electrical and Computer Engineering, University of Iowa, Iowa City, IA 52242, United States
Johan H. C. SR REIBER - Division of Image Processing, Department of Radiology, Leiden University Medical Center, 2300 RC Leiden, Netherlands
Resource Type: Journal article
Publication Details: IEEE transactions on medical imaging, Vol.21(11), pp.1374-1383
DOI: 10.1109/TMI.2002.806427
PMID: 12575874
NLM abbreviation: IEEE Trans Med Imaging
ISSN: 0278-0062
eISSN: 1558-254X
Publisher: Institute of Electrical and Electronics Engineers; New York, NY
Language: English
Date published: 2002
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: 9984046904702771

Metrics

25 Record Views

227 Times Cited - Web of Science

See more details