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

Aniket A. Tolpadi; Maureen L. Stone; Aaron Carass; Jerry L. Prince; Arnold D. Gomez

doi:10.1117/12.2296927

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

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

Research output: Chapter in Book/Report/Conference proceeding › Conference 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 language	English (US)
Title of host publication	Medical Imaging 2018
Subtitle of host publication	Image-Guided Procedures, Robotic Interventions, and Modeling
Editors	Baowei Fei, Robert J. Webster
Publisher	SPIE
ISBN (Electronic)	9781510616417
DOIs	https://doi.org/10.1117/12.2296927
State	Published - 2018
Externally published	Yes
Event	Medical Imaging 2018: Image-Guided Procedures, Robotic Interventions, and Modeling - Houston, United States Duration: Feb 12 2018 → Feb 15 2018

Publication series

Name	Progress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume	10576
ISSN (Print)	1605-7422

Other

Other	Medical Imaging 2018: Image-Guided Procedures, Robotic Interventions, and Modeling
Country/Territory	United States
City	Houston
Period	2/12/18 → 2/15/18

Keywords

Biomechanics
Machine-Learning
Model Inversion
Random Forest

ASJC Scopus subject areas

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

Access to Document

10.1117/12.2296927

Cite this

Tolpadi, A. A., Stone, M. L., Carass, A., Prince, J. L., & Gomez, A. D. (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 Article 1057606 (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 10576). 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 et al.
Medical Imaging 2018: Image-Guided Procedures, Robotic Interventions, and Modeling. ed. / Baowei Fei; Robert J. Webster. SPIE, 2018. 1057606 (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 10576).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Tolpadi, AA, Stone, ML, Carass, A, Prince, JL & Gomez, AD 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., 1057606, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 10576, 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 AD. 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. SPIE. 2018. 1057606. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE). doi: 10.1117/12.2296927

@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 L.} and Gomez, {Arnold D.}",

note = "Funding Information: The authors would like to thank Jonghye Woo and Fanxu Xing at Harvard Medical School for their help with tagged imaging analysis. This study was funded by grants R01DC014717 and 2R01NS055951 from the National Institutes of Health in the United States. Publisher Copyright: {\textcopyright} 2018 SPIE.; Medical Imaging 2018: Image-Guided Procedures, Robotic Interventions, and Modeling ; Conference date: 12-02-2018 Through 15-02-2018",

year = "2018",

doi = "10.1117/12.2296927",

language = "English (US)",

series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

publisher = "SPIE",

editor = "Baowei Fei and Webster, {Robert J.}",

booktitle = "Medical Imaging 2018",

}

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 L.

AU - Gomez, Arnold D.

N1 - Funding Information: The authors would like to thank Jonghye Woo and Fanxu Xing at Harvard Medical School for their help with tagged imaging analysis. This study was funded by grants R01DC014717 and 2R01NS055951 from the National Institutes of Health in the United States. Publisher Copyright: © 2018 SPIE.

PY - 2018

Y1 - 2018

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

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

BT - Medical Imaging 2018

A2 - Fei, Baowei

A2 - Webster, Robert J.

PB - SPIE

T2 - Medical Imaging 2018: Image-Guided Procedures, Robotic Interventions, and Modeling

Y2 - 12 February 2018 through 15 February 2018

ER -

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

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this