Abstract 13989: Automated VT Localization System Based on Patient-Specific Integration of Two-Dimensional (2D) Intracardiac Echocardiography (ICE) and 3DElectroanatomic (EA) Mapping
Bibliographic record
Abstract
Introduction: We have previously developed an intraprocedural automated localization system to identify VT-exit sites projected onto a patient-specific CT geometry using 12-lead ECGs. However, the accuracy of the system depends on a registered reconstruction of the cardiac surface. Objective: To assess the feasibility of using a registered integration of 2D ICE and 3D EA mapping to perform intraprocedural localization, while avoiding errors being introduced by registration of the CT geometry and EA map. Methods: Four patients with 7 VTs (5 LV VTs, 2 RV VTs) were enrolled. A 3D patient-specific shell of both ventricles that combines ICE and EA map was reconstructed during the ablation procedure. It was imported into the automated localization system post-procedure for offline analysis. The system was used to estimate the location of VT-exit sites on the reconstructed 3D geometry. Localization accuracy was quantified for the VT-exit sites by comparing the distance of the calculated site to the site of successful ablation or that of best pacing site match. Results: Five reentrant VT-exit sites were identified using activation and entrainment mapping, supplemented by pace-mapping at the scar margin; two focal VTs were identified by pace mapping. The proposed system achieved mean localization accuracy of 6.4 mm for 7 VTs. Conclusions: ICE and EA mapping can be successfully integrated for intraprocedural automated localization of ventricular activation in both ventricular chambers and may avoid registration errors of CT geometry integration.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.006 | 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".