Poster — Thur Eve — 65: Optimization of an automatic image contouring system for radiation therapy
Bibliographic record
Abstract
Intensity modulated radiation therapy (IMRT) is an advanced technique used to concentrate the prescribed dose in the tumour while minimizing exposure to healthy tissues. Success in IMRT is greatly dependent upon the localization of the target volume and normal tissue, thus accurate contouring is crucial. In this paper, we describe an automated atlas-based image contouring system and our approach for improving the system by performing a full-scale optimization of registration parameters using high-performance computing. To achieve this, we use manually pre-contoured CT images of ten head and neck patients. For any parameter set, each patient data is registered with the remaining patients. Accuracy of the resulting contours is determined automatically by comparing their overlap with manually defined targets using Dice's similarity coefficient (DSC). This allows us to compare all permutations of the image registration parameter sets and input data to investigate their impact on final contour accuracy. Investigating the parameter space required 27,000 image registrations and 216,000 DSC computations. To perform these registrations we introduced a large cluster of high-performance computers and developed a parallel testing harness. The metrics collected from the tests show a wide range of performance, indicating that parameter selection is crucial in our contouring system. By selecting an optimized parameter set, we increased the mean overlap of the automatically contoured regions of interest by 50% and reduced registration time by 50% compared to the original parameters. Our findings illustrate that full-scale optimization is an effective method for improving the performance of the automated image contouring system.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.005 | 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".