A deep joint sparse non-negative matrix factorization framework for identifying the common and subject-specific functional units of tongue motion during speech

• Published in: Medical image analysis Vol. 72; p. 102131
• Main Authors: Woo, Jonghye, Xing, Fangxu, Prince, Jerry L., Stone, Maureen, Gomez, Arnold D., Reese, Timothy G., Wedeen, Van J., El Fakhri, Georges
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.08.2021; Elsevier BV
• Subjects: Algorithms; Artificial neural networks; Clustering; Coordination; Coordination compounds; Deep learning; Deep non-negative matrix factorization; Factorization; Functional units; Humans; In vivo methods and tests; Joints (anatomy); Machine learning; Magnetic Resonance Imaging; Muscles; Neural networks; Neural Networks, Computer; Speech; Structure-function relationships; Tagged-MRI; Tongue; Tongue - diagnostic imaging; Tongue motion; Weighting; Tagged-MRI; Functional units; Deep non-negative matrix factorization; Tongue motion

•We presented a method to identify both common and subject-specific functional units within a material coordinate system from MRI.•We proposed to convert non-negative matrix factorization with sparse and manifold regularizations into modular structures.•We provided validation to demonstrate superior...