Advanced automated treatment planning for total body irradiation: Implementation and effects on standardization
Bibliographic record
Abstract
PURPOSE: This work describes the automation of our volumetric modulated arc therapy (VMAT) total body irradiation (TBI) treatment planning. It also aims to determine if plan standardization is impacted by automation. METHODS: We introduced automated beam placement for TBI in March 2021. For manual beam placement pre-2021, Python-modified DICOM files were imported to pre-set cumulative meterset weights, with other parameters selected by dosimetrists. Our automated planning script automates these processes and sets gantry stop angles and isocentre placement. To determine the impact of automation on plan standardization, we performed a retrospective review of a matched cohort of 168 patients. Plan parameters were compared with an external standard, and passing rates compared between patient cohorts. The dosimetric impact was investigated by comparing a Body-5 mm homogeneity index (HI = D2%/D98%) and mean lung dose (MLD) between cohorts. RESULTS: Results are listed for manual and automated groups respectively. Median (range) passing rates were 97.7% (96.1-100) and 99.2% (98.3-100). Automated plans had a significantly higher passing rate (p ≪ 0.05) and smaller variance (p = 0.001). Most failures were attributed to human error. Automated plans also had more consistent parameter identifiers. After considering dimensional outliers, median (range) Body-5 mm HI were 1.18 (1.14-1.23) and 1.18 (1.15-1.26), and mean ± standard deviation MLD were 103.8 ± 1.3% and 104.1 ± 0.9%. Variances were not significantly different between Body-5 mm HI (p = 0.092) but were for MLD (p = 0.013). CONCLUSIONS: Implementation of automated planning in TBI resulted in significantly improved plan standardization. The decrease in variance of the MLD for the automated planning group points towards a potential dosimetric benefit of automation.
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 | 0.008 | 0.024 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| 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".