SU‐E‐T‐275: Evaluation of Deformable Contour Propagation
Bibliographic record
Abstract
Purpose: Deformable contour propagation, when performed accurately, can potentially reduce the workload associated with manual contouring and minimize inter‐observer variability. In this work, we have compared propagated contours to physician‐drawn ones for gynecologic brachytherapy (GYN) and head and neck (HN) external beam radiotherapy cases.Methods: Eleven HN and sixteen GYN cases were randomly and retrospectively chosen for this study. These cases included their respective pre‐treatment (pCT) and follow‐up CT (fCT) scans along with their respective physician‐drawn structures. The pCT volume was registered using a deformable algorithm to the fCT and the resulting deformation field was applied to the pCTˈs structure set to propagate it to the fCT, this was done using Velocity Medical Solutionsˈ VelocityAI software. The propagated contours were compared to the physician drawn‐contours using the Dice similarity coefficient (DSC).Results: Eleven organs at risk (OAR) and the clinical target volume (CTV) were analyzed for the HN cases and two OARs, as well as the Miami applicator and the CTV for the GYN cases. The propagated contours for the brain, brainstem, spinal cord, esophagus, eyes, larynx, mandible, oral cavity, parotids and the CTV yielded mean DSCs ranging between 0.635–0.979 for the HN cases with a poor outcome for the sphincter muscle (mean DSC = 0.576). The mean DSCs ranged between 0.702–0.804 for the Miami applicator, bladder, rectum and CTV for the GYN cases Conclusions: This work has shown that deformable contour propagation is quite accurate and requires minimal modification. The HN cases slightly outperformed the GYN cases primarily due to the fact that the GYN scans are low in contrast and contain high deformation tissues such as the bladder and rectum.
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 | 0.004 | 0.014 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".