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

Eileen M. McMahon, Josef Korinek, Honghai Zhang, Milan Sonka, Armando Manduca, Marek Belohlavek

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

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. Classification 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.

Original languageEnglish (US)
Title of host publicationProceedings of the International Joint Conference on Neural Networks
Pages3017-3022
Number of pages6
Volume5
DOIs
StatePublished - 2005
EventInternational Joint Conference on Neural Networks, IJCNN 2005 - Montreal, QC, Canada
Duration: Jul 31 2005Aug 4 2005

Other

OtherInternational Joint Conference on Neural Networks, IJCNN 2005
CountryCanada
CityMontreal, QC
Period7/31/058/4/05

Fingerprint

Ultrasonics
Neural networks
Mechanical properties
Strain measurement
Physiology
Principal component analysis
Data mining
Muscle

ASJC Scopus subject areas

  • Software

Cite this

McMahon, E. M., Korinek, J., Zhang, H., Sonka, M., Manduca, A., & Belohlavek, M. (2005). Neural network and principal component analyses of highly variable myocardial mechanical waveforms derived from echocardiographic ultrasound images. In Proceedings of the International Joint Conference on Neural Networks (Vol. 5, pp. 3017-3022). [1556406] https://doi.org/10.1109/IJCNN.2005.1556406

Neural network and principal component analyses of highly variable myocardial mechanical waveforms derived from echocardiographic ultrasound images. / McMahon, Eileen M.; Korinek, Josef; Zhang, Honghai; Sonka, Milan; Manduca, Armando; Belohlavek, Marek.

Proceedings of the International Joint Conference on Neural Networks. Vol. 5 2005. p. 3017-3022 1556406.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

McMahon, EM, Korinek, J, Zhang, H, Sonka, M, Manduca, A & Belohlavek, M 2005, Neural network and principal component analyses of highly variable myocardial mechanical waveforms derived from echocardiographic ultrasound images. in Proceedings of the International Joint Conference on Neural Networks. vol. 5, 1556406, pp. 3017-3022, International Joint Conference on Neural Networks, IJCNN 2005, Montreal, QC, Canada, 7/31/05. https://doi.org/10.1109/IJCNN.2005.1556406
McMahon EM, Korinek J, Zhang H, Sonka M, Manduca A, Belohlavek M. Neural network and principal component analyses of highly variable myocardial mechanical waveforms derived from echocardiographic ultrasound images. In Proceedings of the International Joint Conference on Neural Networks. Vol. 5. 2005. p. 3017-3022. 1556406 https://doi.org/10.1109/IJCNN.2005.1556406
McMahon, Eileen M. ; Korinek, Josef ; Zhang, Honghai ; Sonka, Milan ; Manduca, Armando ; Belohlavek, Marek. / Neural network and principal component analyses of highly variable myocardial mechanical waveforms derived from echocardiographic ultrasound images. Proceedings of the International Joint Conference on Neural Networks. Vol. 5 2005. pp. 3017-3022
@inproceedings{a9084664f3c24583ae3c20cbb2e30a4c,
title = "Neural network and principal component analyses of highly variable myocardial mechanical waveforms derived from echocardiographic ultrasound images",
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. Classification 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.",
author = "McMahon, {Eileen M.} and Josef Korinek and Honghai Zhang and Milan Sonka and Armando Manduca and Marek Belohlavek",
year = "2005",
doi = "10.1109/IJCNN.2005.1556406",
language = "English (US)",
isbn = "0780390482",
volume = "5",
pages = "3017--3022",
booktitle = "Proceedings of the International Joint Conference on Neural Networks",

}

TY - GEN

T1 - Neural network and principal component analyses of highly variable myocardial mechanical waveforms derived from echocardiographic ultrasound images

AU - McMahon, Eileen M.

AU - Korinek, Josef

AU - Zhang, Honghai

AU - Sonka, Milan

AU - Manduca, Armando

AU - Belohlavek, Marek

PY - 2005

Y1 - 2005

N2 - 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. Classification 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.

AB - 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. Classification 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.

UR - http://www.scopus.com/inward/record.url?scp=33750110684&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33750110684&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2005.1556406

DO - 10.1109/IJCNN.2005.1556406

M3 - Conference contribution

SN - 0780390482

SN - 9780780390485

VL - 5

SP - 3017

EP - 3022

BT - Proceedings of the International Joint Conference on Neural Networks

ER -