SU‐D‐BRA‐05: Time Series Analysis of EPID Images to Identify Patients in Need of Treatment Adaptation
Bibliographic record
Abstract
Purpose: to evaluate if time series analysis of portal dose images can be used to identify patients undergoing important anatomical changes. Methods: daily EPID images of every treatment fields were acquired for 48 patients treated for lung cancer. In addition, CBCT were acquired on a regular basis (weekly or biweekly). Gamma analysis was performed relative to the first fraction given that no significant anatomical change was observed on the CBCT of the first fraction compared to the planning CT. Several parameters were extracted from the gamma analysis (e.g. average gamma value, standard deviation, percent above 1). The gamma parameters formed a patient‐specific time series that was analyzed. The first 24 patients were retrospectively evaluated to establish an action threshold that was then applied on the remaining 24 patients. Dosimetric evaluation of patients above that threshold was performed to as assess the level of degradation compared to the initial treatment plan. Results: after performing a clinical retrospective analysis of the first 24 cases, an action threshold on the average gamma value was established at 0.6 and a warning level was set at 0.4. These thresholds were then applied to the remaining 24 cases. Of these, 6 patients (25%) were above the warning level and 4 (17%) were above the action threshold. Dosimetric evaluation was performed on the CBCT for all these 6 patients. Three of these patients had changes above 3% in their PTV coverage, one had changes of about 2% and the remaining two had negligible changes. Patients with the strongest changes all had clear trending in their gamma parameters that could be classified with techniques such as hidden Markov models. Conclusion: by using time series analysis of relative EPID image it was possible to identify a subset of patient most likely to benefit from treatment adaptation. This work was funded in part by Varian Medical Systems
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 | 0.002 |
| 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 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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".