Differentiating post-cancer from healthy tongue muscle coordination patterns during speech using deep learning

Jonghye Woo, Fangxu Xing, Jerry Ladd Prince, Maureen Stone, Jordan R. Green, Tessa Goldsmith, Timothy G. Reese, Van J. Wedeen, Georges El Fakhri

Research output: Contribution to journalArticle

Abstract

The ability to differentiate post-cancer from healthy tongue muscle coordination patterns is necessary for the advancement of speech motor control theories and for the development of therapeutic and rehabilitative strategies. A deep learning approach is presented to classify two groups using muscle coordination patterns from magnetic resonance imaging (MRI). The proposed method uses tagged-MRI to track the tongue's internal tissue points and atlas-driven non-negative matrix factorization to reduce the dimensionality of the deformation fields. A convolutional neural network is applied to the classification task yielding an accuracy of 96.90%, offering the potential to the development of therapeutic or rehabilitative strategies in speech-related disorders.

Original languageEnglish (US)
Pages (from-to)EL423-EL429
JournalJournal of the Acoustical Society of America
Volume145
Issue number5
DOIs
StatePublished - May 1 2019

Fingerprint

tongue
muscles
learning
magnetic resonance
cancer
control theory
factorization
disorders
matrices
Tongue
Therapeutics
Cancer
Magnetic Resonance Imaging
Atlas
Speech Motor Control
Neural Networks
Control Theory

ASJC Scopus subject areas

  • Arts and Humanities (miscellaneous)
  • Acoustics and Ultrasonics

Cite this

Differentiating post-cancer from healthy tongue muscle coordination patterns during speech using deep learning. / Woo, Jonghye; Xing, Fangxu; Prince, Jerry Ladd; Stone, Maureen; Green, Jordan R.; Goldsmith, Tessa; Reese, Timothy G.; Wedeen, Van J.; El Fakhri, Georges.

In: Journal of the Acoustical Society of America, Vol. 145, No. 5, 01.05.2019, p. EL423-EL429.

Research output: Contribution to journalArticle

Woo, J, Xing, F, Prince, JL, Stone, M, Green, JR, Goldsmith, T, Reese, TG, Wedeen, VJ & El Fakhri, G 2019, 'Differentiating post-cancer from healthy tongue muscle coordination patterns during speech using deep learning', Journal of the Acoustical Society of America, vol. 145, no. 5, pp. EL423-EL429. https://doi.org/10.1121/1.5103191
Woo, Jonghye ; Xing, Fangxu ; Prince, Jerry Ladd ; Stone, Maureen ; Green, Jordan R. ; Goldsmith, Tessa ; Reese, Timothy G. ; Wedeen, Van J. ; El Fakhri, Georges. / Differentiating post-cancer from healthy tongue muscle coordination patterns during speech using deep learning. In: Journal of the Acoustical Society of America. 2019 ; Vol. 145, No. 5. pp. EL423-EL429.
@article{0882f0b817db4507a53c989140984332,
title = "Differentiating post-cancer from healthy tongue muscle coordination patterns during speech using deep learning",
abstract = "The ability to differentiate post-cancer from healthy tongue muscle coordination patterns is necessary for the advancement of speech motor control theories and for the development of therapeutic and rehabilitative strategies. A deep learning approach is presented to classify two groups using muscle coordination patterns from magnetic resonance imaging (MRI). The proposed method uses tagged-MRI to track the tongue's internal tissue points and atlas-driven non-negative matrix factorization to reduce the dimensionality of the deformation fields. A convolutional neural network is applied to the classification task yielding an accuracy of 96.90{\%}, offering the potential to the development of therapeutic or rehabilitative strategies in speech-related disorders.",
author = "Jonghye Woo and Fangxu Xing and Prince, {Jerry Ladd} and Maureen Stone and Green, {Jordan R.} and Tessa Goldsmith and Reese, {Timothy G.} and Wedeen, {Van J.} and {El Fakhri}, Georges",
year = "2019",
month = "5",
day = "1",
doi = "10.1121/1.5103191",
language = "English (US)",
volume = "145",
pages = "EL423--EL429",
journal = "Journal of the Acoustical Society of America",
issn = "0001-4966",
publisher = "Acoustical Society of America",
number = "5",

}

TY - JOUR

T1 - Differentiating post-cancer from healthy tongue muscle coordination patterns during speech using deep learning

AU - Woo, Jonghye

AU - Xing, Fangxu

AU - Prince, Jerry Ladd

AU - Stone, Maureen

AU - Green, Jordan R.

AU - Goldsmith, Tessa

AU - Reese, Timothy G.

AU - Wedeen, Van J.

AU - El Fakhri, Georges

PY - 2019/5/1

Y1 - 2019/5/1

N2 - The ability to differentiate post-cancer from healthy tongue muscle coordination patterns is necessary for the advancement of speech motor control theories and for the development of therapeutic and rehabilitative strategies. A deep learning approach is presented to classify two groups using muscle coordination patterns from magnetic resonance imaging (MRI). The proposed method uses tagged-MRI to track the tongue's internal tissue points and atlas-driven non-negative matrix factorization to reduce the dimensionality of the deformation fields. A convolutional neural network is applied to the classification task yielding an accuracy of 96.90%, offering the potential to the development of therapeutic or rehabilitative strategies in speech-related disorders.

AB - The ability to differentiate post-cancer from healthy tongue muscle coordination patterns is necessary for the advancement of speech motor control theories and for the development of therapeutic and rehabilitative strategies. A deep learning approach is presented to classify two groups using muscle coordination patterns from magnetic resonance imaging (MRI). The proposed method uses tagged-MRI to track the tongue's internal tissue points and atlas-driven non-negative matrix factorization to reduce the dimensionality of the deformation fields. A convolutional neural network is applied to the classification task yielding an accuracy of 96.90%, offering the potential to the development of therapeutic or rehabilitative strategies in speech-related disorders.

UR - http://www.scopus.com/inward/record.url?scp=85066103401&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066103401&partnerID=8YFLogxK

U2 - 10.1121/1.5103191

DO - 10.1121/1.5103191

M3 - Article

C2 - 31153323

AN - SCOPUS:85066103401

VL - 145

SP - EL423-EL429

JO - Journal of the Acoustical Society of America

JF - Journal of the Acoustical Society of America

SN - 0001-4966

IS - 5

ER -