Automated review of patient position during DIBH breast hybrid IMRT using EPID images
Bibliographic record
Abstract
Deep Inspiration Breath Hold (DIBH) is a respiratory-gating technique employed in breast radiation therapy to lower the delivered radiation dose to the patient’s heart. When performing DIBH treatments, it is important to have a monitoring system to measure the quality of the patient's breath hold. In this retrospective study, we developed a system capable of monitoring DIBH breast treatments by using electronic portal imaging device (EPID) images acquired in each fraction. Three image-processing algorithms were evaluated on their ability to accurately measure the chest wall position (CWP) in EPID images. One of the algorithms is based on the use of the Canny filter while the other two analyze EPID profiles and identify the CWP as either the peak intensity or the inflection point at the lung-rib interface. The setup error and intrafraction motion were measured for all fractions of 20 left-sided breast patients, 10 treated with fields with no multi-leaf collimator (MLC) shielding and 10 with MLCs used for shielding. Setup error measurements were also collected for the first fractions of 20 additional patients. The algorithm showing the highest agreement (0.7 ± 0.5 mm) with manual measurements defined the CWP as the inflection point along the lung-rib interface on EPID profiles. This algorithm was then used to calculate intrafraction motion and setup errors. Intrafraction motion was found to be 0.7 mm on average for the group with no shielding and 0.9 mm on average for the shielded group. The largest intrafraction motion was recorded as +4.9 mm. Setup errors ranged from -7.1 mm to +5.1 mm for the unshielded group and from -4.3 mm to +8.9 mm for the shielded group. In the final group of patients where the setup errors of the first fractions were measured, these errors ranged from -5.2 mm to +7.5 mm. The most extreme motion and setup errors in all three groups of patients agreed within 2.1 mm of manual measurements. This algorithm agreement is smaller than the typical 3 mm action levels and future work could be conducted to evaluate its ability to automate tasks and/or replace surrogate-based monitoring 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 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| 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) | 0.001 | 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".