Inverse biomechanical modeling of the tongue via machine learning and synthetic training data

Aniket A. Tolpadi, Maureen L. Stone, Aaron Carass, Jerry Ladd Prince, Arnold Gomez

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

Abstract

The tongue's deformation during speech can be measured using tagged magnetic resonance imaging, but there is no current method to directly measure the pattern of muscles that activate to produce a given motion. In this paper, the activation pattern of the tongue's muscles is estimated by solving an inverse problem using a random forest. Examples describing different activation patterns and the resulting deformations are generated using a finite-element model of the tongue. These examples form training data for a random forest comprising 30 decision trees to estimate contractions in 262 contractile elements. The method was evaluated on data from tagged magnetic resonance data from actual speech and on simulated data mimicking flaps that might have resulted from glossectomy surgery. The estimation accuracy was modest (5.6% error), but it surpassed a semimanual approach (8.1% error). The results suggest that a machine learning approach to contraction pattern estimation in the tongue is feasible, even in the presence of flaps.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2018
Subtitle of host publicationImage-Guided Procedures, Robotic Interventions, and Modeling
EditorsBaowei Fei, Robert J. Webster
PublisherSPIE
Volume10576
ISBN (Electronic)9781510616417
DOIs
StatePublished - Jan 1 2018
EventMedical Imaging 2018: Image-Guided Procedures, Robotic Interventions, and Modeling - Houston, United States
Duration: Feb 12 2018Feb 15 2018

Other

OtherMedical Imaging 2018: Image-Guided Procedures, Robotic Interventions, and Modeling
CountryUnited States
CityHouston
Period2/12/182/15/18

Fingerprint

Flaps
machine learning
tongue
Magnetic resonance
Tongue
Muscle
Learning systems
education
Chemical activation
Decision trees
muscles
Inverse problems
Surgery
contraction
magnetic resonance
Glossectomy
activation
Imaging techniques
Muscles
Decision Trees

Keywords

  • Biomechanics
  • Machine-Learning
  • Model Inversion
  • Random Forest

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Atomic and Molecular Physics, and Optics
  • Radiology Nuclear Medicine and imaging

Cite this

Tolpadi, A. A., Stone, M. L., Carass, A., Prince, J. L., & Gomez, A. (2018). Inverse biomechanical modeling of the tongue via machine learning and synthetic training data. In B. Fei, & R. J. Webster (Eds.), Medical Imaging 2018: Image-Guided Procedures, Robotic Interventions, and Modeling (Vol. 10576). [1057606] SPIE. https://doi.org/10.1117/12.2296927

Inverse biomechanical modeling of the tongue via machine learning and synthetic training data. / Tolpadi, Aniket A.; Stone, Maureen L.; Carass, Aaron; Prince, Jerry Ladd; Gomez, Arnold.

Medical Imaging 2018: Image-Guided Procedures, Robotic Interventions, and Modeling. ed. / Baowei Fei; Robert J. Webster. Vol. 10576 SPIE, 2018. 1057606.

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

Tolpadi, AA, Stone, ML, Carass, A, Prince, JL & Gomez, A 2018, Inverse biomechanical modeling of the tongue via machine learning and synthetic training data. in B Fei & RJ Webster (eds), Medical Imaging 2018: Image-Guided Procedures, Robotic Interventions, and Modeling. vol. 10576, 1057606, SPIE, Medical Imaging 2018: Image-Guided Procedures, Robotic Interventions, and Modeling, Houston, United States, 2/12/18. https://doi.org/10.1117/12.2296927
Tolpadi AA, Stone ML, Carass A, Prince JL, Gomez A. Inverse biomechanical modeling of the tongue via machine learning and synthetic training data. In Fei B, Webster RJ, editors, Medical Imaging 2018: Image-Guided Procedures, Robotic Interventions, and Modeling. Vol. 10576. SPIE. 2018. 1057606 https://doi.org/10.1117/12.2296927
Tolpadi, Aniket A. ; Stone, Maureen L. ; Carass, Aaron ; Prince, Jerry Ladd ; Gomez, Arnold. / Inverse biomechanical modeling of the tongue via machine learning and synthetic training data. Medical Imaging 2018: Image-Guided Procedures, Robotic Interventions, and Modeling. editor / Baowei Fei ; Robert J. Webster. Vol. 10576 SPIE, 2018.
@inproceedings{ce4ab68e843e44899d57e809ec45dca4,
title = "Inverse biomechanical modeling of the tongue via machine learning and synthetic training data",
abstract = "The tongue's deformation during speech can be measured using tagged magnetic resonance imaging, but there is no current method to directly measure the pattern of muscles that activate to produce a given motion. In this paper, the activation pattern of the tongue's muscles is estimated by solving an inverse problem using a random forest. Examples describing different activation patterns and the resulting deformations are generated using a finite-element model of the tongue. These examples form training data for a random forest comprising 30 decision trees to estimate contractions in 262 contractile elements. The method was evaluated on data from tagged magnetic resonance data from actual speech and on simulated data mimicking flaps that might have resulted from glossectomy surgery. The estimation accuracy was modest (5.6{\%} error), but it surpassed a semimanual approach (8.1{\%} error). The results suggest that a machine learning approach to contraction pattern estimation in the tongue is feasible, even in the presence of flaps.",
keywords = "Biomechanics, Machine-Learning, Model Inversion, Random Forest",
author = "Tolpadi, {Aniket A.} and Stone, {Maureen L.} and Aaron Carass and Prince, {Jerry Ladd} and Arnold Gomez",
year = "2018",
month = "1",
day = "1",
doi = "10.1117/12.2296927",
language = "English (US)",
volume = "10576",
editor = "Baowei Fei and Webster, {Robert J.}",
booktitle = "Medical Imaging 2018",
publisher = "SPIE",

}

TY - GEN

T1 - Inverse biomechanical modeling of the tongue via machine learning and synthetic training data

AU - Tolpadi, Aniket A.

AU - Stone, Maureen L.

AU - Carass, Aaron

AU - Prince, Jerry Ladd

AU - Gomez, Arnold

PY - 2018/1/1

Y1 - 2018/1/1

N2 - The tongue's deformation during speech can be measured using tagged magnetic resonance imaging, but there is no current method to directly measure the pattern of muscles that activate to produce a given motion. In this paper, the activation pattern of the tongue's muscles is estimated by solving an inverse problem using a random forest. Examples describing different activation patterns and the resulting deformations are generated using a finite-element model of the tongue. These examples form training data for a random forest comprising 30 decision trees to estimate contractions in 262 contractile elements. The method was evaluated on data from tagged magnetic resonance data from actual speech and on simulated data mimicking flaps that might have resulted from glossectomy surgery. The estimation accuracy was modest (5.6% error), but it surpassed a semimanual approach (8.1% error). The results suggest that a machine learning approach to contraction pattern estimation in the tongue is feasible, even in the presence of flaps.

AB - The tongue's deformation during speech can be measured using tagged magnetic resonance imaging, but there is no current method to directly measure the pattern of muscles that activate to produce a given motion. In this paper, the activation pattern of the tongue's muscles is estimated by solving an inverse problem using a random forest. Examples describing different activation patterns and the resulting deformations are generated using a finite-element model of the tongue. These examples form training data for a random forest comprising 30 decision trees to estimate contractions in 262 contractile elements. The method was evaluated on data from tagged magnetic resonance data from actual speech and on simulated data mimicking flaps that might have resulted from glossectomy surgery. The estimation accuracy was modest (5.6% error), but it surpassed a semimanual approach (8.1% error). The results suggest that a machine learning approach to contraction pattern estimation in the tongue is feasible, even in the presence of flaps.

KW - Biomechanics

KW - Machine-Learning

KW - Model Inversion

KW - Random Forest

UR - http://www.scopus.com/inward/record.url?scp=85050671881&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050671881&partnerID=8YFLogxK

U2 - 10.1117/12.2296927

DO - 10.1117/12.2296927

M3 - Conference contribution

C2 - 29997406

AN - SCOPUS:85050671881

VL - 10576

BT - Medical Imaging 2018

A2 - Fei, Baowei

A2 - Webster, Robert J.

PB - SPIE

ER -