Improving ultrasound post estimation accuracy by training on co-registered EMA data
Files
Date
2024-06-28
Citation
Balch-Tomes, J., Wrench, A.A., Scobbie, J.M., Macmartin, C. and Turk, A. (2024) in Ultrafest XI: extended abstracts. University of Aizu, pp. 91–95. Available at: https://zenodo.org/doi/10.5281/zenodo.12578650.
Abstract
This study aims to assess how accurately DeepLabCut [1], when applied to ultrasound tongue images, can estimate Electromagnetic Articulography (EMA) sensor positions. EMA provides objective measures of anterior tongue, jaw, and lip kinematics. DeepLabCut pose estimation is a powerful method of extracting keypoint positions from midsagittal ultrasound images of the tongue. It has an advantage over EMA in that it can be applied to the whole of the tongue from tip to root as well as the jaw and the hyoid. After correction for probe translation standard error in the estimation of keypoint positions compared to the corresponding EMA sensor positions was 1.2-1.5mm along the tongue contour and 0.5-0.9mm perpendicular to the tongue contour.