Modeling the temporal–spatial nature of the readout of an electronic portal imaging device (EPID)
Bibliographic record
Abstract
Purpose In real‐time electronic portal imaging device (EPID) dosimetry applications where on‐treatment measured transmission images are compared to an ideal predicted image, ideally a tight tolerance should be set on the quantitative image comparison in order to detect a wide variety of possible delivery errors. However, this is currently not possible due to the appearance of banding artifacts in individual frames of the measured EPID image sequences. The purpose of this work was to investigate simulating banding artifacts in our cine‐EPID predicted image sequences to improve matching of individual image frames to the acquired image sequence. Increased sensitivity of this method to potential treatment delivery errors would represent an improvement in patient safety and treatment accuracy. Methods A circuit board was designed and built to capture the target current (TARG‐I) and forward power signals produced by the linac to help model the discrete beam‐formation process of the linac. To simulate the temporal–spatial nature of the EPID readout, a moving read out mask was applied with the timing of the application of the readout mask synchronized to the TARG‐I pulses. Since identifying the timing of the first TARG‐I pulse affected the location of the banding artifacts throughout the image sequence, and furthermore the first several TARG‐I pulses at the beginning of “beam on” are not at full height yet (i.e., dose rate is ramping up), the forward‐power signal was also used to assist in reliable detection of the first radiation pulse of the beam delivery. The predicted EPID cine‐image sequence obtained using a comprehensive physics‐based model was modified to incorporate the discrete nature of the EPID frame readout. This modified banding predicted EPID (MBP‐EPID) image sequence was then compared to its corresponding measured EPID cine‐image sequence on a frame‐by‐frame basis. The EPID was mounted on a Clinac 2100ix linac (Varian Medical Systems, Palo Alto, CA). The field size was set to 21.4 28.6 cm2 with no MLC modulation, beam energy of 6 MV, dose rate of 600 MU/min, and 700 MU were delivered for each clockwise (CW) and counter‐clockwise (CCW) arc. No phantoms were placed in the beam. Results The dose rate ramp up effect was observed at the beginning irradiations, and the identification and timing of the radiation pulses, even during the dose rate ramp up, were able to be quantified using the TARG‐I and forward power signals. The approach of capturing individual dose pulses and synchronizing with the mask image applied to the original predicted EPID image sequence was demonstrated to model the actual EPID readout. The MBP‐EPID image sequences closely reproduced the location and magnitude of the banding features observed in the acquired (i.e., measured) image sequence, for all test irradiations examined here. Conclusions The banding artifacts observed in the measured EPID cine‐frame sequences were reproduced in the predicted EPID cine‐frames by simulating the discrete temporal–spatial nature of the EPID read out. The MBP‐EPID images showed good agreement qualitatively to the corresponding measured EPID frame sequence of a simple square test field, without any phantom in the beam. This approach will lead to improved image comparison tolerances for real‐time patient dosimetry applications.
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 | 0.000 | 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 | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".