Wall Motion Classification of Stress Echocardiography Based on Combined Rest-and-Stress Data

Authors:
Sarina Mansor;Nicholas P. Hughes;J. Alison Noble
Affiliations:
Biomedical Image Analysis (BioMedIA) Laboratory, Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, United Kingdom;Biomedical Image Analysis (BioMedIA) Laboratory, Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, United Kingdom;Biomedical Image Analysis (BioMedIA) Laboratory, Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, United Kingdom
Venue:
MICCAI '08 Proceedings of the 11th International Conference on Medical Image Computing and Computer-Assisted Intervention, Part II
Year:
2008

Citing 5
Cited 0

2-D Shape Classification Using Hidden Markov Model

IEEE Transactions on Pattern Analysis and Machine Intelligence
Automated heart wall motion abnormality detection from ultrasound images using Bayesian networks

IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Local wall-motion classification in echocardiograms using shape models and orthomax rotations

FIMH'07 Proceedings of the 4th international conference on Functional imaging and modeling of the heart
Automatic prediction of myocardial contractility improvement in stress MRI using shape morphometrics with independent component analysis

IPMI'05 Proceedings of the 19th international conference on Information Processing in Medical Imaging
Cardiology meets image analysis: just an application or can image analysis usefully impact cardiology practice?

CVBIA'05 Proceedings of the First international conference on Computer Vision for Biomedical Image Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we represent a new framework that performs automated local wall motion analysis based on the combined information derived from a rest and stress sequence (a full stress echocardiography study). Since cardiac data inherits time-varying and sequential properties, we introduce a Hidden Markov Model (HMM) approach to classify stress echocardiography. A wall segment model is developed for a normal and an abnormal heart and experiments are performed on rest, stress and rest-and-stress sequences. In an assessment using n=44 datasets, combined rest-and-stress analysis shows an improvement in classification (84.17%) over individual rest (73.33%) and stress (68.33%).