Artificial neural network prediction of ischemic tissue fate in acute stroke imaging

Shiliang Huang, Qiang Shen, Timothy Q. Duong

Research output: Contribution to journalArticle

30 Citations (Scopus)

Abstract

Multimodal magnetic resonance imaging of acute stroke provides predictive value that can be used to guide stroke therapy. A flexible artificial neural network (ANN) algorithm was developed and applied to predict ischemic tissue fate on three stroke groups: 30-, 60-minute, and permanent middle cerebral artery occlusion in rats. Cerebral blood flow (CBF), apparent diffusion coefficient (ADC), and spin-spin relaxation time constant (T2) were acquired during the acute phase up to 3 hours and again at 24 hours followed by histology. Infarct was predicted on a pixel-by-pixel basis using only acute (30-minute) stroke data. In addition, neighboring pixel information and infarction incidence were also incorporated into the ANN model to improve prediction accuracy. Receiver-operating characteristic analysis was used to quantify prediction accuracy. The major findings were the following: (1) CBF alone poorly predicted the final infarct across three experimental groups; (2) ADC alone adequately predicted the infarct; (3) CBFADC improved the prediction accuracy; (4) inclusion of neighboring pixel information and infarction incidence further improved the prediction accuracy; and (5) prediction was more accurate for permanent occlusion, followed by 60- and 30-minute occlusion. The ANN predictive model could thus provide a flexible and objective framework for clinicians to evaluate stroke treatment options on an individual patient basis.

Original languageEnglish (US)
Pages (from-to)1661-1670
Number of pages10
JournalJournal of Cerebral Blood Flow and Metabolism
Volume30
Issue number9
DOIs
StatePublished - Sep 2010

Fingerprint

Stroke
Cerebrovascular Circulation
Neural Networks (Computer)
Infarction
Middle Cerebral Artery Infarction
Incidence
ROC Curve
Histology
Magnetic Resonance Imaging
Therapeutics

Keywords

  • ANN
  • DWI
  • ischemic penumbra
  • perfusiondiffusion mismatch
  • predictive model
  • PWI

ASJC Scopus subject areas

  • Cardiology and Cardiovascular Medicine
  • Clinical Neurology
  • Neurology
  • Medicine(all)

Cite this

Artificial neural network prediction of ischemic tissue fate in acute stroke imaging. / Huang, Shiliang; Shen, Qiang; Duong, Timothy Q.

In: Journal of Cerebral Blood Flow and Metabolism, Vol. 30, No. 9, 09.2010, p. 1661-1670.

Research output: Contribution to journalArticle

Huang, Shiliang ; Shen, Qiang ; Duong, Timothy Q. / Artificial neural network prediction of ischemic tissue fate in acute stroke imaging. In: Journal of Cerebral Blood Flow and Metabolism. 2010 ; Vol. 30, No. 9. pp. 1661-1670.
@article{1d230a37efc144819a9d031e77d46b7b,
title = "Artificial neural network prediction of ischemic tissue fate in acute stroke imaging",
abstract = "Multimodal magnetic resonance imaging of acute stroke provides predictive value that can be used to guide stroke therapy. A flexible artificial neural network (ANN) algorithm was developed and applied to predict ischemic tissue fate on three stroke groups: 30-, 60-minute, and permanent middle cerebral artery occlusion in rats. Cerebral blood flow (CBF), apparent diffusion coefficient (ADC), and spin-spin relaxation time constant (T2) were acquired during the acute phase up to 3 hours and again at 24 hours followed by histology. Infarct was predicted on a pixel-by-pixel basis using only acute (30-minute) stroke data. In addition, neighboring pixel information and infarction incidence were also incorporated into the ANN model to improve prediction accuracy. Receiver-operating characteristic analysis was used to quantify prediction accuracy. The major findings were the following: (1) CBF alone poorly predicted the final infarct across three experimental groups; (2) ADC alone adequately predicted the infarct; (3) CBFADC improved the prediction accuracy; (4) inclusion of neighboring pixel information and infarction incidence further improved the prediction accuracy; and (5) prediction was more accurate for permanent occlusion, followed by 60- and 30-minute occlusion. The ANN predictive model could thus provide a flexible and objective framework for clinicians to evaluate stroke treatment options on an individual patient basis.",
keywords = "ANN, DWI, ischemic penumbra, perfusiondiffusion mismatch, predictive model, PWI",
author = "Shiliang Huang and Qiang Shen and Duong, {Timothy Q.}",
year = "2010",
month = "9",
doi = "10.1038/jcbfm.2010.56",
language = "English (US)",
volume = "30",
pages = "1661--1670",
journal = "Journal of Cerebral Blood Flow and Metabolism",
issn = "0271-678X",
publisher = "Nature Publishing Group",
number = "9",

}

TY - JOUR

T1 - Artificial neural network prediction of ischemic tissue fate in acute stroke imaging

AU - Huang, Shiliang

AU - Shen, Qiang

AU - Duong, Timothy Q.

PY - 2010/9

Y1 - 2010/9

N2 - Multimodal magnetic resonance imaging of acute stroke provides predictive value that can be used to guide stroke therapy. A flexible artificial neural network (ANN) algorithm was developed and applied to predict ischemic tissue fate on three stroke groups: 30-, 60-minute, and permanent middle cerebral artery occlusion in rats. Cerebral blood flow (CBF), apparent diffusion coefficient (ADC), and spin-spin relaxation time constant (T2) were acquired during the acute phase up to 3 hours and again at 24 hours followed by histology. Infarct was predicted on a pixel-by-pixel basis using only acute (30-minute) stroke data. In addition, neighboring pixel information and infarction incidence were also incorporated into the ANN model to improve prediction accuracy. Receiver-operating characteristic analysis was used to quantify prediction accuracy. The major findings were the following: (1) CBF alone poorly predicted the final infarct across three experimental groups; (2) ADC alone adequately predicted the infarct; (3) CBFADC improved the prediction accuracy; (4) inclusion of neighboring pixel information and infarction incidence further improved the prediction accuracy; and (5) prediction was more accurate for permanent occlusion, followed by 60- and 30-minute occlusion. The ANN predictive model could thus provide a flexible and objective framework for clinicians to evaluate stroke treatment options on an individual patient basis.

AB - Multimodal magnetic resonance imaging of acute stroke provides predictive value that can be used to guide stroke therapy. A flexible artificial neural network (ANN) algorithm was developed and applied to predict ischemic tissue fate on three stroke groups: 30-, 60-minute, and permanent middle cerebral artery occlusion in rats. Cerebral blood flow (CBF), apparent diffusion coefficient (ADC), and spin-spin relaxation time constant (T2) were acquired during the acute phase up to 3 hours and again at 24 hours followed by histology. Infarct was predicted on a pixel-by-pixel basis using only acute (30-minute) stroke data. In addition, neighboring pixel information and infarction incidence were also incorporated into the ANN model to improve prediction accuracy. Receiver-operating characteristic analysis was used to quantify prediction accuracy. The major findings were the following: (1) CBF alone poorly predicted the final infarct across three experimental groups; (2) ADC alone adequately predicted the infarct; (3) CBFADC improved the prediction accuracy; (4) inclusion of neighboring pixel information and infarction incidence further improved the prediction accuracy; and (5) prediction was more accurate for permanent occlusion, followed by 60- and 30-minute occlusion. The ANN predictive model could thus provide a flexible and objective framework for clinicians to evaluate stroke treatment options on an individual patient basis.

KW - ANN

KW - DWI

KW - ischemic penumbra

KW - perfusiondiffusion mismatch

KW - predictive model

KW - PWI

UR - http://www.scopus.com/inward/record.url?scp=77956266570&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77956266570&partnerID=8YFLogxK

U2 - 10.1038/jcbfm.2010.56

DO - 10.1038/jcbfm.2010.56

M3 - Article

C2 - 20424631

AN - SCOPUS:77956266570

VL - 30

SP - 1661

EP - 1670

JO - Journal of Cerebral Blood Flow and Metabolism

JF - Journal of Cerebral Blood Flow and Metabolism

SN - 0271-678X

IS - 9

ER -