2021
A deep joint sparse non-negative matrix factorization framework for identifying the common and subject-specific functional units of tongue motion during speech
Woo J, Xing F, Prince J, Stone M, Gomez A, Reese T, Wedeen V, El Fakhri G. A deep joint sparse non-negative matrix factorization framework for identifying the common and subject-specific functional units of tongue motion during speech. Medical Image Analysis 2021, 72: 102131. PMID: 34174748, PMCID: PMC8316408, DOI: 10.1016/j.media.2021.102131.Peer-Reviewed Original ResearchConceptsNon-negative matrix factorizationSparse Non-negative Matrix FactorizationIterative shrinkage-thresholding algorithmNon-negative matrix factorization frameworkDeep neural networksMatrix factorization frameworkDeep learning frameworkTongue motionIdentified functional unitsGraph regularizationClustering performanceWeight mapLearning frameworkSpectral clusteringNeural networkMatrix factorizationModular architectureIncreased interpretabilityMotion dataFactorization frameworkConvoluted natureComparison methodTagged magnetic resonance imagingMuscle coordination patternsSpeech
2020
Identifying the common and subject-specific functional units of speech movements via a joint sparse non-negative matrix factorization framework
Woo J, Xing F, Prince J, Stone M, Reese T, Wedeen V, El Fakhri G. Identifying the common and subject-specific functional units of speech movements via a joint sparse non-negative matrix factorization framework. 2020, 63. DOI: 10.1117/12.2548991.Peer-Reviewed Original ResearchIdentifying the Common and Subject-specific Functional Units of Speech Movements via a Joint Sparse Non-negative Matrix Factorization Framework.
Woo J, Xing F, Prince J, Stone M, Reese T, Wedeen V, El Fakhri G. Identifying the Common and Subject-specific Functional Units of Speech Movements via a Joint Sparse Non-negative Matrix Factorization Framework. Proceedings Of SPIE--the International Society For Optical Engineering 2020, 11313 PMID: 32454553, PMCID: PMC7243345.Peer-Reviewed Original Research
2018
A Sparse Non-Negative Matrix Factorization Framework for Identifying Functional Units of Tongue Behavior From MRI
Woo J, Prince J, Stone M, Xing F, Gomez A, Green J, Hartnick C, Brady T, Reese T, Wedeen V, Fakhri G. A Sparse Non-Negative Matrix Factorization Framework for Identifying Functional Units of Tongue Behavior From MRI. IEEE Transactions On Medical Imaging 2018, 38: 730-740. PMID: 30235120, PMCID: PMC6422735, DOI: 10.1109/tmi.2018.2870939.Peer-Reviewed Original ResearchConceptsNon-negative matrix factorization frameworkProbabilistic graphical model frameworkMatrix factorization frameworkGraphical model frameworkWeight mapSpectral clusteringSynthetic dataMuscle coordination patternsMatrix factorizationMotion dataMotion patternsTongue motionFactorization frameworkTwo-dimensional imagesMuscle groupsLocal regionsLocal muscle groupLocal structural elementsTagged-MRIImagesFunctional muscle groups