SU‐E‐J‐109: Registration/Segmentation for Adaptive Radiotherapy Using the Jensen Renyi Divergence
Bibliographic record
Abstract
Purpose: For the purposes of adaptive radiotherapy, the consolidation of offline and online imaging modalities requires costly registration, resegmentation and re‐optimization. The Jensen Renyi (JR) divergence is a non‐parametric generalized statistical measure that can be applied as an energy function for all three of these objectives. Further efficiency and accuracy can be attained by coupling the objective functions such that they iteratively reinforce one another. Methods: The JR divergence was used as an energy function and with a finite difference scheme, the level set differential equation was solved for an active contour along with the energy gradient of control points placed using an adaptive mesh. The segmentation portion has been validated using three data sets; PET and CBCT images of an in‐house phantom for various image qualities, 7 PET scans of head and neck cases from the Louvain database and 22 PET/CT scans of patients with non‐small cell lung carcinoma from the MAASTRO database. Results: Segmentation of an in‐house phantom using the JR divergence showed a marked improvement in concordance index (CI) by almost a factor of 2 compared to the mutual information metric below SNR values of 35.3 and 24.0 for the CBCT and PET images. Average CI for the 7 Louvain cases was found to be 0.56. An average error in estimating the maximal tumor diameters of the 22 MAASTRO cases was found to be 63%, 19.5% and 14% using CT, PET and combined PET/ CT modalities. Conclusion: The JR divergence metric was applied to the task of segmentation using a level sets active contour. It was found to provide improved noise tolerance and competitive segmentation accuracy compared to 9 other PET segmentation methods. A coupled segmentation/registration scheme has been implemented using the JR divergence. Validation is currently being performed using plasticized pig lungs. Funding was provided by the Natural Sciences and Engineering Research Council of Canada. (NSERC‐RGPIN 397711‐11) and the Research Institute of the McGill University Health Centre. HZ is supported by the Swiss National Science Foundation under grant SNSF 31003A‐135576, Geneva Cancer League and the Indo‐Swiss Joint Research Programme ISJRP 138866.
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 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".