TH‐A‐220‐04: MVCT Noise Reduction and Feature Enhancement for Target Delineation
Bibliographic record
Abstract
Purpose: To investigate the denoising and feature enhancement of the TomoTherapy® MVCT image. The improvement on the target delineation was evaluated by the contrast to noise ratio (CNR) and by comparison of contouring on original and enhanced images. Methods: A texture enhancing anisotropic diffusion approach different from conventional method was implemented. Parameters may be tweaked to achieve the best performance. Over 300 daily MVCT images from 7 head and neck patients were used for the CNR improvement evaluation. The images were segmented into air, fat, muscle, bone and the contrast between muscle and fat was used for CNR calculation. Five physicians contoured the gross tumour volume (GTV) for three head and neck cancer patients on 34 original and enhanced MVCT images. Variation between the targets outlined using original and enhance MVCT studies was quantified by DICE coefficient and the coefficient of variance. Results: The CNR improved almost three times (from 3.5–5.5 to 10–17) while the sharp muscle‐fat boundary was preserved. Based on volume of agreement between physicians, higher correlation was observed in GTV delineation for enhanced MVCT for patients 1, 2 and 3 by 15%, 3%, and 7%, respectively, while delineation variance among physicians wasreduced using enhanced MVCT for 12 of 17 weekly image studies. Conclusions: The texture enhancing anisotropic diffusion performs well inreducing MVCT noise while enhancing image features. The improvement of the TomoTherapy® MVCT image CNR helps in target delineation.
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 | 0.001 |
| 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 | 0.000 |
| 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".