Neural network and principal component analyses of highly variable myocardial mechanical waveforms derived from echocardiographic ultrasound images

McMahon EM; J Korinek; Honghai Zhang; M Sonka; A Manduca; M Belohlavek

doi:10.1109/IJCNN.2005.1556406

Back

Conference proceeding

Neural network and principal component analyses of highly variable myocardial mechanical waveforms derived from echocardiographic ultrasound images

McMahon EM, J Korinek, Honghai Zhang, M Sonka, A Manduca and M Belohlavek

Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005, Vol.5, pp.3017-3022 vol. 5

2005

DOI: 10.1109/IJCNN.2005.1556406

View Online

Abstract

We introduce a new type of data for classification of regional segments of myocardium. We have analyzed strain measurements taken throughout the cardiac cycle from the echocardiograms of pigs. Classifications by both principal component analysis (PCA) and by neural network (NN) are combined for a data mining operation. Differences in strain waveforms between normal and diseased myocardium may further elucidate the corresponding changes in physiology. Altered functioning of the heart muscle is reflected by strain, and objective computer analysis should aid in the diagnosis of ischemia. We hypothesize that the entire strain waveform over one heart cycle can be classified to functionally determine whether or not a myocardial region is perfused.

Capacitive sensors

Data mining

Heart

Image segmentation

Myocardium

Neural networks

Physiology

Principal component analysis

Strain measurement

Ultrasonic imaging

Details

Title: Subtitle: Neural network and principal component analyses of highly variable myocardial mechanical waveforms derived from echocardiographic ultrasound images
Creators: McMahon EM - Dept. of Internal Medicine, Mayo Clinic Coll. of Medicine, Rochester, MN, USA
J Korinek - Mayo Clinic
Honghai Zhang - University of Iowa
M Sonka - University of Iowa
A Manduca - Physiology & Biomedical Engineering
M Belohlavek - Cardiovascular Diseases
Resource Type: Conference proceeding
Publication Details: Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005, Vol.5, pp.3017-3022 vol. 5
DOI: 10.1109/IJCNN.2005.1556406
ISSN: 2161-4393
eISSN: 2161-4407
Publisher: IEEE
Language: English
Date published: 2005
Academic Unit: Roy J. Carver Department of Biomedical Engineering; Electrical and Computer Engineering; Radiation Oncology; The Iowa Institute for Biomedical Imaging; Fraternal Order of Eagles Diabetes Research Center; Injury Prevention Research Center; Ophthalmology and Visual Sciences
Record Identifier: 9984186601502771

Metrics

23 Record Views