On-unit CT measures as tools for artificial intelligence to identify random vs. systematic anatomical changes in radiotherapy patients
Bibliographic record
Abstract
Background: Although head and neck (H&N) cancer survival is steadily increasing, the close proximity of tumor volumes to organs at risk (OARs) makes radiotherapy planning and delivery challenging for these patients. Changes in patient anatomy (i.e. weight-loss, tumor shrinkage) over 7 weeks of daily radiotherapy may result in increased dosages of radiation to OARs relative to the original treatment plan, consequently hindering post-treatment quality of life. Artificial intelligence-based approaches can improve prediction and monitoring of these effects through identification of systematic changes.
 Objective: To collect and perform an analysis of on-unit CT measurements as surrogate measures of dose changes. Correlations among CT measures may indicate random vs. systematic changes in dose deposition (i.e. dosimetry) and further improve artificial intelligence-based approaches that determine which patients benefit most from treatment re-planning.
 Methods: 250 H&N cancer patients treated with curative chemo-radiotherapy were retrospectively analyzed. Five CT measures including face and neck diameter, chin and shoulder position, and head shift were calculated motivated by current literature. Dosimetric changes were calculated for OARs (pharyngeal constrictor, brainstem, parotid and submandibular glands) and tumour volumes. Conventional correlation analysis and hierarchical clustering were performed to assess group-wise correlations. K-medoid clustering and principal components analysis were conducted to infer groupings of the patients as random or systematic.
 Results: There is a positive correlation between increased dosages to central-axis anatomical structures (spinal cord, pharyngeal constrictor, submandibular glands) and systematic weight-loss effects (change in BMI and weight loss through the face and neck). In line with current literature, clustering indicated that 30.4% of the cohort exhibited systematic anatomical changes, potentially correctable by re-planning. MANOVA confirmed that the systematic anatomical changes corresponded to the spinal cord and brain stem (p<0.005), and Mann-Whitney U tests confirmed that the measures could identify systematic dose increases to the pharyngeal constrictor (p<0.05). Further statistical analyses will be conducted.
 Conclusions: On-unit CT measures appear to be able to distinguish random and systematic dosimetric effects, correlated with changes in dose as expected. These measures can be utilized to improve artificial intelligence-based patient monitoring and intervention techniques.
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 | 0.002 | 0.011 |
| 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 | 0.001 |
| 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".