Show simple item record

dc.contributor.authorWoo, Jonghye
dc.contributor.authorXing, Fangxu
dc.contributor.authorPrince, Jerry L
dc.contributor.authorStone, Maureen
dc.contributor.authorGomez, Arnold D
dc.contributor.authorReese, Timothy G
dc.contributor.authorWedeen, Van J
dc.contributor.authorEl Fakhri, Georges
dc.date.accessioned2021-06-29T12:23:11Z
dc.date.available2021-06-29T12:23:11Z
dc.date.issued2021-06-12
dc.identifier.urihttp://hdl.handle.net/10713/16106
dc.description.abstractIntelligible speech is produced by creating varying internal local muscle groupings—i.e., functional units—that are generated in a systematic and coordinated manner. There are two major challenges in characterizing and analyzing functional units. First, due to the complex and convoluted nature of tongue structure and function, it is of great importance to develop a method that can accurately decode complex muscle coordination patterns during speech. Second, it is challenging to keep identified functional units across subjects comparable due to their substantial variability. In this work, to address these challenges, we develop a new deep learning framework to identify common and subject-specific functional units of tongue motion during speech. Our framework hinges on joint deep graph-regularized sparse non-negative matrix factorization (NMF) using motion quantities derived from displacements by tagged Magnetic Resonance Imaging. More specifically, we transform NMF with sparse and graph regularizations into modular architectures akin to deep neural networks by means of unfolding the Iterative Shrinkage-Thresholding Algorithm to learn interpretable building blocks and associated weighting map. We then apply spectral clustering to common and subject-specific weighting maps from which we jointly determine the common and subject-specific functional units. Experiments carried out with simulated datasets show that the proposed method achieved on par or better clustering performance over the comparison methods. Experiments carried out with in vivo tongue motion data show that the proposed method can determine the common and subject-specific functional units with increased interpretability and decreased size variability. © 2021en_US
dc.description.sponsorshipThis work is partially supported by NIH R01DC014717, R01DC018511, R01CA133015, R21DC016047, R00DC012575, P41EB022544 and NSF 1504804 PoLS .en_US
dc.description.urihttps://doi.org/10.1016/j.media.2021.102131en_US
dc.description.urihttps://arxiv.org/pdf/2007.04865.pdf
dc.language.isoenen_US
dc.publisherElsevier B.V.en_US
dc.relation.ispartofMedical Image Analysisen_US
dc.rightsCopyright © 2021. Published by Elsevier B.V.en_US
dc.subjectDeep non-negative matrix factorizationen_US
dc.subjectFunctional unitsen_US
dc.subjectTagged-MRIen_US
dc.subjectTongue motionen_US
dc.titleA deep joint sparse non-negative matrix factorization framework for identifying the common and subject-specific functional units of tongue motion during speechen_US
dc.typeArticleen_US
dc.identifier.doi10.1016/j.media.2021.102131
dc.identifier.pmid34174748
dc.source.volume72
dc.source.beginpage102131
dc.source.endpage
dc.source.countryNetherlands


Files in this item

Thumbnail
Name:
Publisher version

This item appears in the following Collection(s)

Show simple item record