Poster — Thur Eve — 35: Characterization of performance of two deformable registration software
Bibliographic record
Abstract
PURPOSE: To evaluate the performance of two deformable registration softwares (a commercial and an open source software) using cone-beam computed tomography (CBCT) images. METHODS: We used a set of 34 lung patients with generally large tumors each having between 1 and 20 CBCT scans. A radiation oncologist resident contoured GTVs on each CBCTs using planning CT contours as reference. Deformable registrations were performed on CT scans to adapt it to the first CBCT of each patient independently with both software. Then each CBCT was registered to the next CBCT. Contour structures have been deformed in the process for the commercial software and for the open source software contours have been drawn manually on deformed images. RESULTS: Mean remaining volume (±SD) for manual GTV contours was 59 ± 32 %. GTVs obtained with the open source software were closer to the manual GTV in size than the commercial software. Mean relative errors on volume were 45 ± 60 % for the commercial system (33 patients) and 9 ± 2 % for the open source software (6 patients). Relative errors for the commercial software increased exponentially with the volume reduction but were constant over all CBCT for the open source software. Mean Jaccard and Dice's index were 0.57 and 0.71 for the commercial software (24 patients) and 0.80 and 0.88 for the open source software (6 patients). CONCLUSION: Open source software shown tendency to give better results than commercial software but was slower than the commercial software.
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 | 0.003 | 0.017 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.004 | 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".