Poster — Thur Eve — 45: Three‐Dimensional US Probe Localization by Single Perspective Pose Estimation
Bibliographic record
Abstract
Purpose: Intra‐operative fluoroscopy and transesophageal (TEE) ultrasound are imaging modalities commonly used in many cardiac procedures, including trans‐catheter aortic valve replacement. Fluoroscopy‐to‐ultrasound registration would enhance conventional image guidance by providing a common frame of reference in which both modalities can be viewed. An important component of this registration is 3D localization of the TEE probe with respect to the fluoroscopic image. Traditional approaches to this problem employed magnetic tracking systems, however these systems are hindered by metallic distortions and restrictive patient access within the operating room. Methods: Two 2D‐to‐3D registration techniques, a point‐based and intensity‐based technique, were implemented. These registration techniques determine the 3D pose of the TEE probe directly from single‐perspective fluoroscopy images, which facilitates the localization of both the probe and fluoroscopic image in a common frame of reference. In vitro experiments were performed to assess the accuracy of each registration technique. Measured displacements were compared against mechanical translation/rotation tables, utilized to provide a gold standard. Results: Maximum root‐mean‐square displacement and rotation errors were found to be 0.58mm, 0.32° and 2.29mm, 3.76° for point‐based and intensity‐based tracking techniques, respectively. The accuracy of the point‐based registration technique is significantly higher than the intensity‐based technique, but requires the use of a rigid tracking attachment. Conclusion: Localization of the TEE from single‐perspective fluoroscopy images provides an accurate means of intra‐operative fluoroscopy‐to‐ultrasound registration, and does not significantly interrupt the regular workflow within the operating room.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.014 | 0.007 |
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".