Intensity-based 3D/2D registration for percutaneous intervention of major aorto-pulmonary collateral arteries
Bibliographic record
Abstract
Percutaneous cardiac interventions rely mainly on the experience of the cardiologist to safely navigate inside soft tissues vessels under X-ray angiography guidance. Additional navigation guidance tool might contribute to improve reliability and safety of percutaneous procedures. This study focus on major aorta-pulmonary collateral arteries (MAPCAs) which are pediatric structures. We present a fully automatic intensity-based 3D/2D registration method that accurately maps pre-operatively acquired 3D tomographic vascular data of a newborn patient over intra-operatively acquired angiograms. The tomographic dataset 3D pose is evaluated by comparing the angiograms with simulated X-ray projections, computed from the pre-operative dataset with a proposed splatting-based projection technique. The rigid 3D pose is updated via a transformation matrix usually defined in respect of the C-Arm acquisition system reference frame, but it can also be defined in respect of the projection plane local reference frame. The optimization of the transformation is driven by two algorithms. First the hill climbing local search and secondly a proposed variant, the dense hill climbing. The latter makes the search space denser by considering the combinations of the registration parameters instead of neighboring solutions only. Although this study focused on the registration of pediatric structures, the same procedure could be applied for any cardiovascular structures involving CT-scan and X-ray angiography. Our preliminary results are promising that an accurate (3D TRE 0.265 ± 0.647mm) and robust (99% success rate) bi-planes registration of the aorta and MAPCAs from a initial displacement up to 20mm and 20° can be obtained within a reasonable amount of time (13.7 seconds).
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 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".