A computer-based statistical pattern recognition for Doppler spectral waveforms of intracranial blood flow

Jianwei Miao, Paul J. Benkeser, Fenwick T Nichols

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

A computer-based statistical pattern recognition system has been developed for the analysis of transcranial Doppler (TCD) spectral waveforms of the intracranial middle cerebral artery with varying degrees of increased intracranial pressure. This system extracts multidimensional features from TCD waveforms and performs a cluster analysis of those features. The system can automatically recognize the pattern of spectral waveform and classify it as a normal, abnormal, or borderline subclass of TCD spectral waveform. An optimum decision function was generated based on the Bayes Gaussian classifier. The accuracy of the Bayes Gaussian model the spectral waveforms reaches 100% by estimating posterior probability and using the resubstituting method of estimating misclassification in the training TCD data.

Original languageEnglish (US)
Pages (from-to)53-63
Number of pages11
JournalComputers in Biology and Medicine
Volume26
Issue number1
DOIs
StatePublished - Jan 1 1996

Fingerprint

Automated Pattern Recognition
Pattern recognition systems
Middle Cerebral Artery
Intracranial Pressure
Cluster analysis
Pattern recognition
Cluster Analysis
Blood
Classifiers

Keywords

  • Bayes classifier
  • Blood flow
  • Canonical discriminant technique
  • Cluster analysis
  • Doppler waveforms
  • K means algorithm
  • Pattern recognition

ASJC Scopus subject areas

  • Computer Science Applications
  • Health Informatics

Cite this

A computer-based statistical pattern recognition for Doppler spectral waveforms of intracranial blood flow. / Miao, Jianwei; Benkeser, Paul J.; Nichols, Fenwick T.

In: Computers in Biology and Medicine, Vol. 26, No. 1, 01.01.1996, p. 53-63.

Research output: Contribution to journalArticle

@article{a045de87144f496692e029f662d7a79c,
title = "A computer-based statistical pattern recognition for Doppler spectral waveforms of intracranial blood flow",
abstract = "A computer-based statistical pattern recognition system has been developed for the analysis of transcranial Doppler (TCD) spectral waveforms of the intracranial middle cerebral artery with varying degrees of increased intracranial pressure. This system extracts multidimensional features from TCD waveforms and performs a cluster analysis of those features. The system can automatically recognize the pattern of spectral waveform and classify it as a normal, abnormal, or borderline subclass of TCD spectral waveform. An optimum decision function was generated based on the Bayes Gaussian classifier. The accuracy of the Bayes Gaussian model the spectral waveforms reaches 100{\%} by estimating posterior probability and using the resubstituting method of estimating misclassification in the training TCD data.",
keywords = "Bayes classifier, Blood flow, Canonical discriminant technique, Cluster analysis, Doppler waveforms, K means algorithm, Pattern recognition",
author = "Jianwei Miao and Benkeser, {Paul J.} and Nichols, {Fenwick T}",
year = "1996",
month = "1",
day = "1",
doi = "10.1016/0010-4825(95)00029-1",
language = "English (US)",
volume = "26",
pages = "53--63",
journal = "Computers in Biology and Medicine",
issn = "0010-4825",
publisher = "Elsevier Limited",
number = "1",

}

TY - JOUR

T1 - A computer-based statistical pattern recognition for Doppler spectral waveforms of intracranial blood flow

AU - Miao, Jianwei

AU - Benkeser, Paul J.

AU - Nichols, Fenwick T

PY - 1996/1/1

Y1 - 1996/1/1

N2 - A computer-based statistical pattern recognition system has been developed for the analysis of transcranial Doppler (TCD) spectral waveforms of the intracranial middle cerebral artery with varying degrees of increased intracranial pressure. This system extracts multidimensional features from TCD waveforms and performs a cluster analysis of those features. The system can automatically recognize the pattern of spectral waveform and classify it as a normal, abnormal, or borderline subclass of TCD spectral waveform. An optimum decision function was generated based on the Bayes Gaussian classifier. The accuracy of the Bayes Gaussian model the spectral waveforms reaches 100% by estimating posterior probability and using the resubstituting method of estimating misclassification in the training TCD data.

AB - A computer-based statistical pattern recognition system has been developed for the analysis of transcranial Doppler (TCD) spectral waveforms of the intracranial middle cerebral artery with varying degrees of increased intracranial pressure. This system extracts multidimensional features from TCD waveforms and performs a cluster analysis of those features. The system can automatically recognize the pattern of spectral waveform and classify it as a normal, abnormal, or borderline subclass of TCD spectral waveform. An optimum decision function was generated based on the Bayes Gaussian classifier. The accuracy of the Bayes Gaussian model the spectral waveforms reaches 100% by estimating posterior probability and using the resubstituting method of estimating misclassification in the training TCD data.

KW - Bayes classifier

KW - Blood flow

KW - Canonical discriminant technique

KW - Cluster analysis

KW - Doppler waveforms

KW - K means algorithm

KW - Pattern recognition

UR - http://www.scopus.com/inward/record.url?scp=0030043193&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030043193&partnerID=8YFLogxK

U2 - 10.1016/0010-4825(95)00029-1

DO - 10.1016/0010-4825(95)00029-1

M3 - Article

C2 - 8654053

AN - SCOPUS:0030043193

VL - 26

SP - 53

EP - 63

JO - Computers in Biology and Medicine

JF - Computers in Biology and Medicine

SN - 0010-4825

IS - 1

ER -