Semi-automatic segmentation for 3D motion analysis of the tongue with dynamic MRI

• Published in: Computerized medical imaging and graphics Vol. 38; no. 8; pp. 714 - 724
• Main Authors: Lee, Junghoon, Woo, Jonghye, Xing, Fangxu, Murano, Emi Z., Stone, Maureen, Prince, Jerry L.
• Format: Journal Article
• Language: English
• Published: New York, NY Elsevier Ltd 01.12.2014; Elsevier
• Subjects: Algorithms; Applied sciences; Artificial intelligence; Biological and medical sciences; Computer science; control theory; systems; Data processing. List processing. Character string processing; Deformable registration; Deformation; Dynamic MRI; Dynamics; Exact sciences and technology; Frames; Humans; Image Interpretation, Computer-Assisted - methods; Imaging, Three-Dimensional - methods; Internal Medicine; Investigative techniques, diagnostic techniques (general aspects); Magnetic Resonance Imaging - methods; Medical sciences; Memory organisation. Data processing; Motion; Movement - physiology; Other; Otorhinolaryngology. Stomatology. Orbit; Pattern Recognition, Automated - methods; Pattern recognition. Digital image processing. Computational geometry; Radiodiagnosis. Nmr imagery. Nmr spectrometry; Random walker; Reproducibility of Results; Segmentation; Sensitivity and Specificity; Software; Speech; Speech - physiology; Subtraction Technique; Super-resolution reconstruction; Three dimensional; Tongue; Tongue - anatomy & histology; Tongue - physiology; Two dimensional; User-Computer Interface; Motion; Super-resolution reconstruction; Tongue; Segmentation; Dynamic MRI; Random walker; Deformable registration; Image registration; Computer vision; High resolution; Target tracking; Statistical analysis; Motion estimation; Similarity; Random walk; Variability; Nuclear magnetic resonance imaging; Tissue; Image segmentation; Tridimensional image; Automatic analysis; Mechanical deformation

•We proposed a segmentation method for dynamic MRI-based tongue motion analysis.•Proposed method requires a small amount of user-interactions.•Proposed method significantly reduces the segmentation time.•Proposed method produces more consistent segmentation than manual segmentation. Dynamic MRI has...