3D segmentation of the tongue in MRI: a minimally interactive model-based approach
Bibliographic record
Abstract
Static magnetic resonance imaging partially resolves soft tissue details of the oropharynx, which are crucial in swallowing and speech studies. However, delineation of tongue tissue remains a challenge due to the lack of definitive boundary features. In this article, we propose a minimally interactive inter-subject mesh-to-image registration scheme to tackle 3D segmentation of the human tongue from MRI volumes. A tongue surface-mesh is first initialised using an exemplar expert-delineated template, which is then refined based on local intensity similarities between the source and target volumes. A shape-matching technique [Gilles B, Pai D. 2008. Fast musculoskeletal registration based on shape matching. Paper presented at: MICCAI 2008. Proceedings of the 11th International Conference on Medical Image Computing and Computer Assisted Intervention; New York, NY, USA] is applied for regularising the deformation. We enable effective minimal user interaction by incorporating additional boundary labels in areas where automatic segmentation is deemed inadequate. We validate our method on 18 normal subjects using expert manual delineation as the ground truth. Results indicate an average segmentation accuracy of overlap of 90.4 ± 0.4% and distance of 2 ± 0.2 mm, achieved within an expert interaction time of 2 ± 1 min per volume.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.002 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.003 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".