Format

Send to

Choose Destination
J Acoust Soc Am. 2019 May;145(5):EL423. doi: 10.1121/1.5103191.

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

Author information

1
Gordon Center for Medical Imaging, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts 02114, USA.
2
Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, Maryland 21218, USA.
3
Department of Pain and Neural Sciences, University of Maryland Dental School, Baltimore, Maryland 21201, USA.
4
Department of Communication Sciences and Disorders, MGH Institute of Health Professions, Boston, Massachusetts 02129, USA.
5
Department of Speech, Language and Swallowing Disorders, Massachusetts General Hospital, Boston, Massachusetts 02114, USA.
6
Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts 02114, USAjwoo@mgh.harvard.edu, fxing1@mgh.harvard.edu, prince@jhu.edu, mstone@umaryland.edu, jgreen2@mghihp.edu, tgoldsmith@partners.org, reese@nmr.mgh.harvard.edu, van@nmr.mgh.harvard.edu, elfakhri.georges@mgh.harvard.edu.

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.

Supplemental Content

Full text links

Icon for American Institute of Physics Icon for PubMed Central
Loading ...
Support Center