Share Email Print

Proceedings Paper

Interactive segmentation of tongue contours in ultrasound video sequences using quality maps
Author(s): Sarah Ghrenassia; Lucie Ménard; Catherine Laporte
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Ultrasound (US) imaging is an effective and non invasive way of studying the tongue motions involved in normal and pathological speech, and the results of US studies are of interest for the development of new strategies in speech therapy. State-of-the-art tongue shape analysis techniques based on US images depend on semi-automated tongue segmentation and tracking techniques. Recent work has mostly focused on improving the accuracy of the tracking techniques themselves. However, occasional errors remain inevitable, regardless of the technique used, and the tongue tracking process must thus be supervised by a speech scientist who will correct these errors manually or semi-automatically. This paper proposes an interactive framework to facilitate this process. In this framework, the user is guided towards potentially problematic portions of the US image sequence by a segmentation quality map that is based on the normalized energy of an active contour model and automatically produced during tracking. When a problematic segmentation is identified, corrections to the segmented contour can be made on one image and propagated both forward and backward in the problematic subsequence, thereby improving the user experience. The interactive tools were tested in combination with two different tracking algorithms. Preliminary results illustrate the potential of the proposed framework, suggesting that the proposed framework generally improves user interaction time, with little change in segmentation repeatability.

Paper Details

Date Published: 21 March 2014
PDF: 7 pages
Proc. SPIE 9034, Medical Imaging 2014: Image Processing, 903440 (21 March 2014); doi: 10.1117/12.2042883
Show Author Affiliations
Sarah Ghrenassia, Ecole de Technologie Supérieure (Canada)
Lucie Ménard, Univ. du Québec à Montréal (Canada)
Catherine Laporte, Ecole de Technologie Supérieure (Canada)

Published in SPIE Proceedings Vol. 9034:
Medical Imaging 2014: Image Processing
Sebastien Ourselin; Martin A. Styner, Editor(s)

© SPIE. Terms of Use
Back to Top