Best practices for tracing the palate in ultrasound images
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.025 | 0.121 |
| Meta-epidemiology (narrow) | 0.002 | 0.002 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.011 | 0.005 |
| Science and technology studies | 0.002 | 0.002 |
| Scholarly communication | 0.006 | 0.004 |
| Open science | 0.005 | 0.005 |
| Research integrity | 0.004 | 0.003 |
| Insufficient payload (model declined to judge) | 0.011 | 0.018 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".