MO‐D‐105‐05: A Novel Web‐Based Tool for Quantification of VMAT/IMRT Treatment Plan Quality
Bibliographic record
Abstract
Purpose: To develop a novel web‐based tool for VMAT/IMRT treatment plan evaluation and to design a unique plan Quality Index (QI) quantifier to aid in decision‐making for SRS, SBRT, and ENT treatment planning and evaluationMethods: A high level Python web‐framework, Django, is used to develop the web application. Django uses an SQL‐like database for data storage and retrieval. The front‐end of the web application is styled with CSS and written in HTML. Tumor site dependent evaluation templates for SRS, SBRT and ENT plans are created in collaboration with physicians at our institution. Previously approved treatment plans are imported into the web application to populate the database for analysis. With physician feedback, retrospective treatment plans are subjected to scoring algorithms to develop a plan QI. Results: The web tool is currently deployed internally at our institution for VMAT treatment planners. The web site also serves as a portal for site‐specific treatment planning instructions. Specific plan details are imported to an SQL‐like database when treatment plans are pushed to the tool. The electronic nature of the database allows new retrospective studies to be easily conducted. A site specific QI is developed to quantify SRS, SBRT, and ENT plan quality. When the tool is used, QIs are generated automatically and a histogram of site specific QIs is produced. This information can then be used to evaluate the best candidate plan for treatment approval. The database can be used to query legacy plan specific details in order to extract the optimization objectives that best fit the anatomy and prescription doses from a new planning case. Conclusion: The full implementation of the tool aims to standardize and unify the planning and evaluation of IMRT/VMAT techniques. Validation of the QI robustness will include correlation with clinical outcome and inter‐institutional case studies.
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 | 0.002 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.018 | 0.004 |
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".