Multi-omic feature reliability of deformable image registration-based images
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Abstract Purpose . To evaluate the reliability of radiomic and dosiomic (multi-omic) features extracted from synthetic CT images generated using two commercially available deformable image registration workflows. Materials and Methods . Multi-omic features were extracted from organs at risk (OAR) contoured on a cohort of 58 head and neck (HN) radiotherapy patients. The contours were propagated from the planning CT to synthetic CTs of the final fraction cone-beam CT (CBCT) anatomy using MIM and Velocity deformable image registration workflows. The workflows were validated using radiation oncologist contours on the planning CT and final fraction CBCT according to TG-132 guidelines. The OAR volumes and mean dose on the synthetic CTs from two workflows were compared using a signed Wilcoxon rank test. In addition, the dose distributions were evaluated using a gamma analysis using clinical criteria. The multi-omic features were extracted using region-of-interest extraction on the OAR with the original and wavelet filters. The feature reliability was evaluated for four OAR: spinal cord, parotid glands, submandibular glands, and pharyngeal constrictors. The reliability was evaluated using the intraclass correlation coefficient (ICC) with features exceeding 0.75 considered moderately reliable. Results . The volume and mean OAR dose were found to be statistically similar between the MIM and Velocity synthetic CT workflows. In addition, the gamma analysis resulted in 83% of plans exceeding 95% gamma passing rate at 3%/3 mm criteria. Across all HN OAR multi-omic features, fewer radiomic features (21%) were found to be moderately reliable compared to dosiomic features (59%) between the two synthetic CT workflows. The HN OAR with the most moderately reliable features was the spinal cord (46% radiomic, 85% dosiomic). Conclusion . Radiomics features presented worse reliability compared to dosiomic features across different synthetic CT deformable image registration workflows. Care should be taken when implementing predictive models using features extracted from different synthetic CT workflows.
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.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 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 it