Best practices for tracing the palate in ultrasound images

Ultrasound (US) imaging is a powerful tool for visualizing the vocal tract and tongue motion during speech articulation. A key aspect of analyzing tongue motion is accurately tracing the palate's contour in US images, as it provides a fixed anatomical reference for measuring tongue position and deformation. However, accurately tracing the palate in US images remains challenging due to limited visibility caused by the air gap between the palate and the tongue. To address this limitation, we evaluate the reproducibility of manual palate tracing using methods that rely on varying levels of assistance from image-enhancement algorithms. One of these methods is the cumulative echo skeleton (CES), which enhances video frames to stack and reconstruct palate echoes. These methods are tested across different swallowing tasks. Results indicate that CES-based methods enhance rater agreement, primarily due to the cumulation of echoes. Among the tasks, dry swallow consistently yields higher agreement across methods. Additionally, the CES-based automatic method was benchmarked against manual annotations, showing promising accuracy in dry swallow with a mean sum of distances of 2.63 mm. These findings emphasize the important role of method and task selection in enhancing reproducibility and highlight the potential of automated approaches for palate tracing in US imaging.Clinical relevance - In Speech-Language Pathology (SLP), the application of real-time US imaging can be used in diagnostics and treatment of Speech Sound Disorders (SSD). Furthermore, it facilitates observations of oral movements like swallowing and mastication. The incorporation of a static image of the palate - an anatomical structure that is both familiar and tangible within the oral cavity - provides a valuable reference point for interpreting the dynamic movements of the tongue. This visual aid enhances the understanding of real-time ultrasound images, benefiting both the clinician and the client.