Ultrasound Probe Pose Classification for Task Recognition in Central Venous Catheterization
Bibliographic record
Abstract
Central Line Tutor is a system that facilitates real-time feedback during training for central venous catheterization. One limitation of Central Line Tutor is its reliance on expensive, cumbersome electromagnetic tracking to facilitate various training aids, including ultrasound task identification and segmentation of neck vasculature. The purpose of this study is to validate deep learning methods for vessel segmentation and ultrasound pose classification in order to mitigate the system's reliance on electromagnetic tracking. A large dataset of segmented and classified ultrasound images was generated from participant data captured using Central Line Tutor. A U-Net architecture was used to perform vessel segmentation, while a shallow Convolutional Neural Network (CNN) architecture was designed to classify the pose of the ultrasound probe. A second classifier architecture was also tested that used the U-Net output as the CNN input. The mean testing set Intersect over Union score for U-Net cross-validation was 0.746 ± 0.052. The mean test set classification accuracy for the CNN was 92.0% ± 3.0, while the U-Net + CNN achieved 92.7% ± 2.1%. This study highlights the potential for deep learning on ultrasound images to replace the current electromagnetic tracking-based methods for vessel segmentation and ultrasound pose classification, and represents an important step towards removing the electromagnetic tracker altogether. Removing the need for an external tracking system would significantly reduce the cost of Central Line Tutor and make it far more accessible to the medical trainees that would benefit from it most.
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 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.002 |
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".