A framework for assessing and optimising data sufficiency in ultrasound tongue imaging

Tools

Al Ani, Saja and Cleland, Joanne and Zoha, Ahmed; (2026) A framework for assessing and optimising data sufficiency in ultrasound tongue imaging. In: Proceedings of the 19th International Joint Conference on Biomedical Engineering Systems and Technologies. SCITEPRESS, ESP, pp. 279-286. ISBN 9789897588020 (https://doi.org/10.5220/0014440800004070)

[thumbnail of Ani-etal-2026-A-framework-for-assessing-and-optimising-data-sufficiency-in-ultrasound-tongue-imaging]
Preview
 Text. Filename: Ani-etal-2026-A-framework-for-assessing-and-optimising-data-sufficiency-in-ultrasound-tongue-imaging.pdf
Final Published Version
License: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 logo
Download (659kB)| Preview

Abstract

Deep learning (DL) applied to ultrasound tongue imaging (UTI) for speech-disorder assessment is limited by the cost and scarcity of expert-annotated data. Each ultrasound frame requires labelling by trained speech and language therapists (SLTs), making large-scale dataset construction expensive and time-consuming. This paper presents a cost-aware framework that integrates statistical power-curve modelling with active learning (AL) to optimise dataset size and annotation efficiency. Power-curve analysis quantifies the relationship between dataset size and classification performance, identifying a point of diminishing returns beyond which additional annotation yields minimal improvement. Experiments on paediatric UTI data from 28 participants showed that performance stabilised when approximately 65–70% of the available training data were used, reaching an asymptotic accuracy of around 90%. Building on this, uncertainty-based AL further reduced annotation requirements by prioritising in (More)

ORCID iDs

Al Ani, Saja, Cleland, Joanne ORCID logoORCID: https://orcid.org/0000-0002-0660-1646 and Zoha, Ahmed;
CORE (COnnecting REpositories)