MIAL

Analysis of Tongue Dynamics from US

PhD Student: Lisa Tang
Principal Investigator: Ghassan Hamarneh

We are developing techniques for analyzing the movement of the human tongue as captured in 2D dynamic ultrasound.

Please visit the new project webpage:

TongueTrack.cs.sfu.ca

This project is in collaboration with Prof. Tim BressmannSpeech-Language Pathology, Faculty of Medicine, University of Toronto. 


 


Archived Material:


 A. Segmentation

Lisa Tang and Ghassan Hamarneh. Graph-based tracking of the tongue contour in ultrasound sequences with adaptive temporal regularization, In Mathematical Methods for Biomedical Image Analysis (MMBIA) in conjunction with the IEEE Conference on Computer Vision and Pattern Recognition (IEEE CVPR), pages 154-161, 2010.    Poster ]

 
** Software available. To download this software, first request a password (check Tongue Tracking), then download the Tongue Tracking software. New: Code package and Usage Guide  have been updated!  
  
Features:
  • Capable of automatic segmentation of over 500 frames in <4 minutes 
  • Method was validated on a set of 63 clinical data sequences
  • Experimental results demonstrate that our method can robustly segment US sequences containing over 500 frames with mean accuracy of 3 mm, using default parameters

B. Analysis

Lisa Tang, Ghassan Hamarneh, and Tim Bressmann. Automatic Approach to Tongue Motion Analysis in Ultrasound Images. In Medical Image Computing and Computer-Assisted Intervention Workshop on Machine Learning in Medical Imaging (MICCAI MLMI), pages 1-8, 2011.   Poster ] 

Site by Faculty of Applied Science web team, Simon Fraser University