Augmented Reality System for Ultrasound Guidance of Transcatheter Aortic Valve Implantation
Bibliographic record
Abstract
OBJECTIVE: Transcatheter aortic valve implantation (TAVI) relies on fluoroscopy and nephrotoxic contrast medium for valve deployment. We propose an alternative guidance system using augmented reality (AR) and transesophageal echocardiography (TEE) to guide TAVI deployment. The goals of this study were to determine how consistently the aortic valve annulus is defined from TEE using different aortic valve landmarks and to compare AR guidance with fluoroscopic guidance of TAVI deployment in an aortic root model. METHODS: Magnetic tracking sensors were integrated into the TAVI catheter and TEE probe, allowing these tools to be displayed in an AR environment. Variability in identifying aortic valve commissures and cuspal nadirs was assessed using TEE aortic root images. To compare AR guidance of TAVI deployment with fluoroscopic guidance, a TAVI stent was deployed 10 times in the aortic root model using each of the two guidance systems. RESULTS: Commissures and nadirs were both investigated as features for defining the valve annulus in the AR guidance system. The commissures were identified more consistently than the nadirs, with intraobserver variability of 2.2 and 3.8 mm, respectively, and interobserver variability of 3.3 and 4.7 mm, respectively. The precision of TAVI deployment using fluoroscopic guidance was 3.4 mm, whereas the precision of AR guidance was 2.9 mm, and its overall accuracy was 3.4 mm. This indicates that both have similar performance. CONCLUSIONS: Aortic valve commissures can be identified more reliably than cuspal nadirs from TEE. The AR guidance system achieved similar deployment accuracy to that of fluoroscopy while eliminating the use and consequences of nephrotoxic contrast and radiation.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| 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) | 0.005 | 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".