Automated contouring and radiotherapy treatment planning of spine metastases using atlas-based auto-segmentation and knowledge-based planning approaches
Bibliographic record
Abstract
OBJECTIVES: Spine metastases are routinely treated with conventional external beam radiotherapy (cEBRT) where there is no delineation of target volumes (TV) or organs at risk (OAR), or attempt to optimize dose distribution. Automated contouring and treatment planning could facilitate conformal planning of spine metastases in the clinical environment. METHODS: Atlas-based auto-segmentation (ABAS) using SmartSegmentation was developed for delineation of thoracic and lumbar vertebrae, and OAR; knowledge-based planning (KBP) using RapidPlan was developed for conformal volumetric-modulated arc therapy treatment planning. Plans produced using this automated approach were compared to the equivalent cEBRT plans. RESULTS: TV coverage for automated ABAS/KBP conformal treatment plans were superior to cEBRT. The planning target volume (PTV) Dmean = 7.86 ± 0.16 Gy, Dmin = 3.46 ± 1.79 Gy, Dmax = 8.56 ± 0.05 Gy compared to PTV Dmean = 7.78 ± 0.24 Gy, Dmin = 1.83 ± 1.08 Gy, Dmax = 10.46 ± 0.41 Gy, with homogeneity index and conformity index 0.236 ± 0.215 and 1.201 ± 0.121, respectively, for ABAS/KBP compared to 0.508 ± 0.137 and 1.789 ± 0.437 for cEBRT. Dose to dose-limiting spinal cord and cauda equina was reduced in ABAS/KBP plans, with Dmax of 7.91 ± 0.16 Gy and 7.94 ± 0.13 Gy, respectively, compared to 8.67 ± 0.13 Gy and 8.90 ± 0.16 Gy for cEBRT. CONCLUSIONS: Automated conformal treatment planning was achievable, with improved sparing of dose-limiting OAR and superior plan quality compared to cEBRT. Automation of the planning process makes this feasible for implementation in the clinical environment. ADVANCES IN KNOWLEDGE: Automated contouring and treatment planning are feasible in the clinical environment using this approach. We describe the first use of ABAS and KBP for radiotherapy treatment of spine metastases that would allow patients to receive conformal as opposed to the widely used approach of cEBRT.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".