Patient Specific QA Research Articles

914: Establishment of Tolerance and Action levels in IMRT/VMAT Patient Specific QA – LMIC experience

914: Establishment of Tolerance and Action levels in IMRT/VMAT Patient Specific QA – LMIC experience

Unifying gamma passing rates in patient-specific QA for VMAT lung cancer treatment based on data assimilation.

This study aimed to identify systematic errors in measurement-, calculation-, and prediction-based patient-specific quality assurance (PSQA) methods for volumetric modulated arc therapy (VMAT) on lung cancer and to standardize the gamma passing rate (GPR) by considering systematic errors during data assimilation. This study included 150 patients with lung cancer who underwent VMAT. VMAT plans were generated using a collapsed-cone algorithm. For measurement-based PSQA, ArcCHECK was employed. For calculation-based PSQA, Acuros XB was used to recalculate the plans. In prediction-based PSQA, GPR was forecasted using a previously developed GPR prediction model. The representative GPR value was estimated using the least-squares method from the three PSQA methods for each original plan. The unified GPR was computed by adjusting the original GPR to account for systematic errors. The range of limits of agreement (LoA) were assessed for the original and unified GPRs based on the representative GPR using Bland-Altman plots. For GPR (3%/2mm), original GPRs were 94.4 ± 3.5%, 98.6 ± 2.2% and 93.3 ± 3.4% for measurement-, calculation-, and prediction-based PSQA methods and the representative GPR was 95.5 ± 2.0%. Unified GPRs were 95.3 ± 2.8%, 95.4 ± 3.5% and 95.4 ± 3.1% for measurement-, calculation-, and prediction-based PSQA methods, respectively. The range of LoA decreased from 12.8% for the original GPR to 9.5% for the unified GPR across all three PSQA methods. The study evaluated unified GPRs that corrected for systematic errors. Proposing unified criteria for PSQA can enhance safety regardless of the methods used.

Correction method for depth and field size dependence in Octavius 1000 SRS patient-specific QA

Stereotactic body radiation therapy (SBRT) and stereotactic radiosurgery (SRS) are advanced techniques capable of delivering higher doses of radiation precisely to small and complex targets. As these higher doses are delivered, the significance of patient-specific quality assurance becomes increasingly crucial to ensure both the effectiveness and safety of treatment. This study investigates the depth and field size dependence in Octavius 1000 SRS patient-specific quality assurance (PSQA), which is vital for ensuring accuracy in modern radiotherapy treatments. It comprehensively compares the performance of the Octavius 1000 SRS array against standard treatment planning system calculations, focusing on various field sizes and depths. An extensive measurement process was performed, wherein output factors were analyzed across a range of field sizes, from very small (1 × 1 cm2) to larger fields (10 × 10 cm2), at different depths (5 cm, 10 cm, and 15 cm). Our results highlighted significant variations in the measurement accuracy, dependent on the field size and depth, which underscored the challenge involved in ensuring precise dosimetry in PSQA for small fields. The largest discrepancy observed was 2.65% for a 1 × 1 cm2 field size at a depth of 15 cm. Based on these findings, a novel correction method tailored for small field sizes and varying depths was proposed. This method enhances the accuracy and reliability of PSQA in advanced radiotherapy to ensure that the delivered dose conforms closely to the planned dose, which is a critical aspect in treatments targeting small and complex tumor volumes. Through the proposed correction, this study aims to bridge the gap between calculated and measured dose distributions, thus contributing significantly to the refinement of PSQA processes in radiotherapy.

2729: Machine learning model for patient-specific QA prediction in stereotactic radiosurgery

2729: Machine learning model for patient-specific QA prediction in stereotactic radiosurgery

A feasibility study to predict 3D dose delivery accuracy for IMRT using DenseNet with log files.

This study aims to explore the feasibility of DenseNet in the establishment of a three-dimensional (3D) gamma prediction model of IMRT based on the actual parameters recorded in the log files during delivery. A total of 55 IMRT plans (including 367 fields) were randomly selected. The gamma analysis was performed using gamma criteria of 3% /3 mm (Dose Difference/Distance to Agreement), 3% /2 mm, 2% /3 mm, and 2% /2 mm with a 10% dose threshold. In addition, the log files that recorded the gantry angle, monitor units (MU), multi-leaf collimator (MLC), and jaws position during delivery were collected. These log files were then converted to MU-weighted fluence maps as the input of DenseNet, gamma passing rates (GPRs) under four different gamma criteria as the output, and mean square errors (MSEs) as the loss function of this model. Under different gamma criteria, the accuracy of a 3D GPR prediction model decreased with the implementation of stricter gamma criteria. In the test set, the mean absolute error (MAE) of the prediction model under the gamma criteria of 3% /3 mm, 2% /3 mm, 3% /2 mm, and 2% /2 mm was 1.41, 1.44, 3.29, and 3.54, respectively; the root mean square error (RMSE) was 1.91, 1.85, 4.27, and 4.40, respectively; the Sr was 0.487, 0.554, 0.573, and 0.506, respectively. There was a correlation between predicted and measured GPRs (P < 0.01). Additionally, there was no significant difference in the accuracy between the validation set and the test set. The accuracy in the high GPR group was high, and the MAE in the high GPR group was smaller than that in the low GPR group under four different gamma criteria. In this study, a 3D GPR prediction model of patient-specific QA using DenseNet was established based on log files. As an auxiliary tool for 3D dose verification in IMRT, this model is expected to improve the accuracy and efficiency of dose validation.

Commissioning and clinical implementation of an independent dose calculation system for scanned proton beams.

Experimental patient-specific QA (PSQA) is a time and resource-intensive process, with a poor sensitivity in detecting errors. Radiation therapy facilities aim to substitute it by means of independent dose calculation (IDC) in combination with a comprehensive beam delivery QA program. This paper reports on the commissioning of the IDC software tool myQAiON (IBA Dosimetry) for proton therapy and its clinical implementation at the MedAustron Ion Therapy Center. The IDC commissioning work included the validation of the beam model, the implementation and validation of clinical CT protocols, and the evaluation of patient treatment data. Dose difference maps, gamma index distributions, and pass rates (GPR) have been reviewed. The performance of the IDC tool has been assessed and clinical workflows, simulation settings, and GPR tolerances have been defined. Beam model validation showed agreement of ranges within±0.2mm, Bragg-Peak widths within±0.1mm, and spot sizes at various air gaps within±5% compared to physical measurements. Simulated dose in 2D reference fields deviated by-0.3%±0.5%, while 3D dose distributions differed by 1.8% on average to measurements. Validation of the CT calibration resulted in systematic differences of 2.0% between IDC and experimental data for tissue like samples. GPRs of 99.4±0.6% were found for head, head and neck, and pediatric CT protocols on a 2%/2mm gamma criterion. GPRs for the adult abdomen protocol were at 98.9% on average with 3%/3mm. Root causes of GPR outliers, for example, implants were identified and evaluated. IDC has been successfully commissioned and integrated into the MedAustron clinical workflow for protons in 2021. IDC has been stepwise and safely substituting experimental PSQA since February 2021. The initial reduction of proton experimental PSQA was about 25% and reached up to 90% after 1 year.

Predicting the error magnitude in patient-specific QA during radiotherapy based on ResNet.

The error magnitude is closely related to patient-specific dosimetry and plays an important role in evaluating the delivery of the radiotherapy plan in QA. No previous study has investigated the feasibility of deep learning to predict error magnitude. The purpose of this study was to predict the error magnitude of different delivery error types in radiotherapy based on ResNet. A total of 34 chest cancer plans (172 fields) of intensity-modulated radiation therapy (IMRT) from Eclipse were selected, of which 30 plans (151 fields) were used for model training and validation, and 4 plans including 21 fields were used for external testing. The collimator misalignment (COLL), monitor unit variation (MU), random multi-leaf collimator shift (MLCR), and systematic MLC shift (MLCS) were introduced. These dose distributions of portal dose predictions for the original plans were defined as the reference dose distribution (RDD), while those for the error-introduced plans were defined as the error-introduced dose distribution (EDD). Different inputs were used in the ResNet for predicting the error magnitude. In the test set, the accuracy of error type prediction based on the dose difference, gamma distribution, and RDD + EDD was 98.36%, 98.91%, and 100%, respectively; the root mean squared error (RMSE) was 1.45-1.54, 0.58-0.90, 0.32-0.36, and 0.15-0.24; the mean absolute error (MAE) was 1.06-1.18, 0.32-0.78, 0.25-0.27, and 0.11-0.18, respectively, for COLL, MU, MLCR and MLCS. In this study, error magnitude prediction models with dose difference, gamma distribution, and RDD + EDD are established based on ResNet. The accurate prediction of the error magnitude under different error types can provide reference for error analysis in patient-specific QA.

The Status and Challenges for Prostate Stereotactic Body Radiation Therapy Treatments in United States Proton Therapy Centers: An NRG Oncology Practice Survey

PurposeTo report the current practice pattern of the proton stereotactic body radiation therapy (SBRT) for prostate treatments. Materials and MethodsA survey was designed to inquire about the practice of proton SBRT treatment for prostate cancer. The survey was distributed to all 30 proton therapy centers in the United States that participate in the National Clinical Trial Network in February, 2023. The survey focused on usage, patient selection criteria, prescriptions, target contours, dose constraints, treatment plan optimization and evaluation methods, patient-specific QA, and image-guided radiation therapy (IGRT) methods. ResultsWe received responses from 25 centers (83% participation). Only 8 respondent proton centers (32%) reported performing SBRT of the prostate. The remaining 17 centers cited 3 primary reasons for not offering this treatment: no clinical need, lack of volumetric imaging, and/or lack of clinical evidence. Only 1 center cited the reduction in overall reimbursement as a concern for not offering prostate SBRT. Several common practices among the 8 centers offering SBRT for the prostate were noted, such as using Hydrogel spacers, fiducial markers, and magnetic resonance imaging (MRI) for target delineation. Most proton centers (87.5%) utilized pencil beam scanning (PBS) delivery and completed Imaging and Radiation Oncology Core (IROC) phantom credentialing. Treatment planning typically used parallel opposed lateral beams, and consistent parameters for setup and range uncertainties were used for plan optimization and robustness evaluation. Measurements-based patient-specific QA, beam delivery every other day, fiducial contours for IGRT, and total doses of 35 to 40 GyRBE were consistent across all centers. However, there was no consensus on the risk levels for patient selection. ConclusionProstate SBRT is used in about 1/3 of proton centers in the US. There was a significant consistency in practices among proton centers treating with proton SBRT. It is possible that the adoption of proton SBRT may become more common if proton SBRT is more commonly offered in clinical trials.

Error detection capabilities of diode detector arrays in SABR patient specific QA

Error detection capabilities of diode detector arrays in SABR patient specific QA

Workflow Considerations for Biology-Guided Radiotherapy (BgRT) Implementation.

Biology-guided radiotherapy (BgRT) is a novel platform that combines real-time PET imaging with a 6MV Linac to target tumors. The performance and safety of BgRT was assessed in the BIOGUIDE-X clinical trial. This study aims to report on the BgRT workflow steps and assess the time required for each step of the BgRT process during this trial. A total of nine patients were enrolled in the second Cohort of the BIOGUIDE-X study which included patients treated with stereotactic body radiotherapy (SBRT) for lung tumors (5) and bone tumors (4). The pre-treatment BgRT workflow includes CT simulation, contouring, imaging-only (BgRT Modeling) PET acquisition, BgRT planning, patient specific QA and plan approval. The imaging-only PET acquisition on the X1 collects a representative PET volumetric 3D image and is an input to develop the BgRT treatment plan. The steps during the BgRT delivery session are kVCT localization, PET pre-scan, PET evaluation and BgRT delivery. The PET PreScan is a 1-pass short-duration PET acquisition that is used to confirm that the PET biodistribution on the day of treatment is consistent with that of the imaging-only PET. During BIOGUIDE-X, the BgRT delivery step was replaced by a 4-pass long-PET acquisition that was used to emulate the expected BgRT dose distribution without turning the beam on. To assess BgRT workflow, times from 18F-FDG injection to image-only PET acquisition, 18F-FDG injection to PET pre-scan, Pre-scan to PET evaluation, and PET evaluation to BgRT delivery (long PET acquisition) were recorded. Time between the 18F-FDG injection and the X1 imaging-only PET scan was 84 ± 19 minutes which includes time for 18F-FDG update. Average time to perform imaging-only PET scan was 26 ± 4 minutes. During the BgRT 'delivery' session, the mean time between the kVCT acquisition and PET pre-scan acquisition was 7 ± 3 minutes. The mean time to acquire a 1-pass PET pre-scan was 6 ± 1 then followed by 6 ± 1 minutes for the PET pre-scan dose calculation to estimate the BgRT doses that it would have delivered for this fraction. On average, the PET reconstruction, the PET signal localization verification and the evaluation of safety metrics took 11 ± 4 minutes. The mean time for BgRT 'delivery' was 27 ± 5 minutes based on the 4-pass long PET acquisition. Time from the start of the BgRT session to the end of the BgRT 'delivery' with this version of the investigative product release was 65 ± 9 minutes. The new processes introduced by the BgRT technology were evaluated and found clinically feasible. Improvements are being undertaken to shorten the time required for each step and to increase patient comfort ahead of BgRT clinical implementation.

First Demonstration of the Commissioning of a New Multi-Modality Radiotherapy Platform

A new multi-modality radiotherapy platform was developed and introduced into clinical application, which has received US FDA 510k(K210921) and National Medical Products Administration (NMPA) clearance in China (20223050973). This study, for the first time, presents the technological characteristics and commissioning results of the new platform. The platform consists of 3 modules: linear accelerator, rotating gamma system, and a kV imaging system within an O-ring gantry. The O-ring gantry can rotate continuously achieved by using a slip ring. The Linac delivers a 6 MV FFF photon beam with a variable dose rate of 50 to 1400 MU/min. The delivery techniques include 3D-CRT, IMRT, and VMAT. The rotating gamma system utilizes 18 Co-60 sources with a reference dose rate of 350 cGy/min. The image-guided techniques consist of kV-kV pairs and kV-CBCT. The X-ray intensity-modulated radiotherapy and γ-ray stereotactic radiotherapy can be delivered on the same platform. The acceptance test and commissioning were performed following the vendor's customer acceptance tests (CAT) and several AAPM Task Group reports/guidelines. Regarding the Linac, all applicable validation tests recommended by the MPPG 5.a (basic photon beam model validation, IMRT/VMAT validation, E2E tests, and patient-specific QA) were performed. For the rotating gamma system, the absorbed doses were measured using a PTW31014 and PTW60016. EBT3 films were employed to measure the relative output factors (ROFs). The E2E tests were performed using a PTW31014 and EBT3 films. The coincidence between the imaging isocenter and the Linac/gamma treatment isocenter was investigated using EBT3 films. The image quality was evaluated regarding the contrast-to-noise ratio (CNR), spatial resolution, and uniformity. All tests included in the CAT met the vendor's specifications. All MPPG 5.a tests complied with the tolerances. The confidence limits for IMRT/VMAT validation were achieved according to TG-119. The point dose differences were below 1.68% and gamma pass rates (3%/2 mm) were above 95.9% for the Linac E2E tests. All plans of patient-specific QA had point dose differences below 1.79% and gamma pass rates (3%/2 mm) above 96.1% suggested by TG-218. For the rotating gamma system, the differences between the calculated and measured absorbed doses were below 1.86%. The ROFs calculated by the TPS were independently confirmed within 2% using EBT3 films. The point dose differences were below 2.57% and gamma pass rates (2%/1 mm) were above 95.3% for the E2E tests. The coincidence between the imaging isocenter and the Linac/gamma treatment isocenter was within 0.5 mm. The image quality fully complied with the vendor's specifications regarding the CNR, spatial resolution, and uniformity. This is the first report about the commissioning of a new multi-modality radiotherapy platform. The platform has been successfully commissioned and exhibits good performance in mechanical and dosimetry accuracy.

Development of the Independent Dose Verification Method for the Ring Gantry PET/CT Linac

The RefleXion Xi is a new external beam radiotherapy delivery modality combining kilovoltage fan-beam CT and on-board PET for Biology-guided Radiotherapy. Although the machine shares similar components with the Tomotherapy machine, it has unique hardware features such as stationary beam delivery system with couch increments. The goal of this study is to develop an in-house independent secondary dose calculation method for this ring gantry PET/CT Linac. The method aggregates the beam intensities at each discrete firing gantry angle and couch moving position. The non-uniform intensity map is decomposed into a series of segments of uniform beam intensities, and then coordinates of beam segments were modified based on the relative distance from the dose calculation point to keep the calculation point in the same spot along the gantry rotation. The dose to the calculation point of each segment is determined by using measured tissue-maximum-ratio, output factors, and off-axis ratio by independent binary collimators. Two-dimensional convolution method is applied to integrate all dose contribution components in segment areas for efficient calculation. The final dose is obtained by summing all dose to the calculation point of segments for all firing gantry angle and couch position. Twenty patients with different treatment sites including head and neck, prostate, and lung regions were analyzed. Comparison of the point dose calculated by the independent program to that calculated by the planning system has shown reasonable agreement within ±5%. The independent dose verification program has been developed as an initial patient specific QA for improving patient safety. Further study will be performed to enhance the accuracy and reliability by including additional leakage and scatter models.

Development of a LINAC head model for the CyberKnife VSI-System using EGSnrc Monte Carlo system.

In order to understand the interaction processes of photons and electrons of the CyberKnife VSI-System, a modeling of the LINAC head must take place. Here, a Monte Carlo simulation can help. By comparing the measured data with the simulation data, the agreement can be checked. For the Monte Carlo simulations, the toolkit EGSnrc with the user codes BEAMnrc and DOSXZYnrc was used. The CyberKnife VSI-System has two collimation systems to define the field size of the beam. On the one hand, it has 12 circular collimators and, on the other, an IRIS-aperture. The average energy, final source width, dose profiles, and output factors in a voxel-based water phantom were determined and compared to the measured data. The average kinetic energy of the electron beam for the CyberKnife VSI LINAC head is 6.9 MeV, with a final source width of 0.25cm in x-direction and 0.23cm in y-direction. All simulated dose profiles for both collimation systems were able to achieve a global gamma criterion of 1%/1mm to the measured data. For the output factors, the deviation from simulated to measured data is<1% from a field size of 12.5mm for the circular collimators and from a field size of 10mm for the IRIS-aperture. The beam characteristics of the CyberKnife VSI LINAC head could be exactly simulated with Monte Carlo simulation. Thus, in the future, this model can be used as a basis for electronic patient-specific QA or to determine scattering processes of the LINAC head.

Patient-specific QA for the HyperArc technique using gafchromic film with multiple calibration methods

Purpose This study aims to evaluate different methods for calibrating EBT-XD films to develop a precise pre-treatment verification method for stereotactic radiotherapy (SRT) patients using the HyperArc (HA, Varian Medical System) technique. Methods Gafchromic EBT-XD films were calibrated using three different approaches: manual calibration, EDW calibration, and PDD calibration. Films were digitalized with an Epson V850 Pro scanner applying the local scanning protocol. Three clinical treatment plans were selected for evaluation. Patient-specific QA films were irradiated in the Mobius MVP phantom and the STEEV phantom. Scanned film images were converted into dose images using the calibration curves. Gamma analysis was performed to compare film dose and TPS calculated dose with various criteria. Results The scan-to-scan variation was evaluated to be ≤ 0.2%. The accuracy of the calibration curves was verified and the deviation from the converted dose deviates ≤ 3% from the known delivered dose. The gamma passing rate for all calibration methods was found to be over 94% with clinically relevant criteria. EDW calibration demonstrated higher average gamma passing rates compared to the manual method for single target plans, which is 99% ± 1.2% and 98.8% ± 1.5%, respectively. PDD method demonstrated improved agreement for multiple targets with the result of 99.3% ± 0.8%. Conclusions The three calibration methods were validated, and they produced accurate calibration curves for EBT-XD films to enable pre-treatment patient-specific QA for stereotactic radiotherapy.

Generation, validation, and benchmarking of a commercial independent Monte Carlo calculation beam model for multi-target SRS

BackgroundDosimetric validation of single isocenter multi-target radiosurgery plans is difficult due to conditions of electronic disequilibrium and the simultaneous irradiation of multiple off-axis lesions dispersed throughout the volume. Here we report the benchmarking of a customizable Monte Carlo secondary dose calculation algorithm specific for multi-target radiosurgery which future users may use to guide their commissioning and clinical implementation. PurposeTo report the generation, validation, and clinical benchmarking of a volumetric Monte Carlo (MC) dose calculation beam model for single isocenter radiosurgery of intracranial multi-focal disease. MethodsThe beam model was prepared within SciMoCa (ScientificRT, Munich Germany), a commercial independent dose calculation software, with the aim of broad availability via the commercial software for use with single isocenter radiosurgery. The process included (1) definition & acquisition of measurement data required for beam modeling, (2) tuning model parameters to match measurements, (3) validation of the beam model via independent measurements and end-to-end testing, and finally, (4) clinical benchmarking and validation of beam model utility in a patient specific QA setting. We utilized a 6X Flattening-Filter-Free photon beam from a TrueBeam STX linear accelerator (Siemens Healthineers, Munich Germany). ResultsIn addition to the measured data required for standard IMRT/VMAT (depth dose, central axis profiles & output factors, leaf gap), beam modeling and validation for single-isocenter SRS required central axis and off axis (5 cm & 9 cm) small field output factors and comparison between measurement and simulation of backscatter with aperture for jaw much greater than MLCs. Validation end-to-end measurements included SRS MapCHECK in StereoPHAN geometry (2%/1 mm Gamma = 99.2% ± 2.2%), and OSL & scintillator measurements in anthropomorphic STEEV phantom (6 targets, volume = 0.1–4.1cc, distance from isocenter = 1.2–7.9 cm) for which mean difference was −1.9% ± 2.2%. For 10 patient cases, MC for individual PTVs was −0.8% ± 1.5%, −1.3% ± 1.7%, and −0.5% ± 1.8% for mean dose, D95%, and D1%, respectively. This corresponded to custom passing rates action limits per AAPM TG-218 guidelines of ±5.2%, ±6.4%, and ±6.3%, respectively. ConclusionsThe beam modeling, validation, and clinical action criteria outlined here serves as a benchmark for future users of the customized beam model within SciMoCa for single isocenter radiosurgery of multi-focal disease.

AAPM Task Group Report 307: Use of EPIDs for Patient-Specific IMRT and VMAT QA.

Electronic portal imaging devices (EPIDs) have been widely utilized for patient-specific quality assurance (PSQA) and their use for transit dosimetry applications is emerging. Yet there are no specific guidelines on the potential uses, limitations, and correct utilization of EPIDs for these purposes. The American Association of Physicists in Medicine (AAPM) Task Group 307 (TG-307) provides a comprehensive review of the physics, modeling, algorithms and clinical experience with EPID-based pre-treatment and transit dosimetry techniques. This review also includes the limitations and challenges in the clinical implementation of EPIDs, including recommendations for commissioning, calibration and validation, routine QA, tolerance levels for gamma analysis and risk-based analysis. Characteristics of the currently available EPID systems and EPID-based PSQA techniques are reviewed. The details of the physics, modeling, and algorithms for both pre-treatment and transit dosimetry methods are discussed, including clinical experience with different EPID dosimetry systems. Commissioning, calibration, and validation, tolerance levels and recommended tests, are reviewed, and analyzed. Risk-based analysis for EPID dosimetry is also addressed. Clinical experience, commissioning methods and tolerances for EPID-based PSQA system are described for pre-treatment and transit dosimetry applications. The sensitivity, specificity, and clinical results for EPID dosimetry techniques are presented as well as examples of patient-related and machine-related error detection by these dosimetry solutions. Limitations and challenges in clinical implementation of EPIDs for dosimetric purposes are discussed and acceptance and rejection criteria are outlined. Potential causes of and evaluations of pre-treatment and transit dosimetry failures are discussed. Guidelines and recommendations developed in this report are based on the extensive published data on EPID QA along with the clinical experience of the TG-307 members. TG-307 focused on the commercially available EPID-based dosimetric tools and provides guidance for medical physicists in the clinical implementation of EPID-based patient-specific pre-treatment and transit dosimetry QA solutions including intensity modulated radiation therapy (IMRT) and volumetric modulated arc therapy (VMAT) treatments.

Virtual pretreatment patient-specific quality assurance of volumetric modulated arc therapy using deep learning.

Automatic patient-specific quality assurance (PSQA) is recently explored using artificial intelligence approaches, and several studies reported the development of machine learning models for predicting the gamma pass rate (GPR) index only. To develop a novel deep learning approach using a generative adversarial network (GAN) to predict the synthetic measured fluence. A novel training method called "dual training," which involves the training of the encoder and decoder separately, was proposed and evaluated for cycle GAN (cycle-GAN) and conditional GAN (c-GAN). A total of 164 VMAT treatment plans, including 344 arcs (training data: 262, validation data: 30, and testing data: 52) from various treatment sites, were selected for prediction model development. For each patient, portal-dose-image-prediction fluence from TPS was used as input, and measured fluence from EPID was used as output/response for model training. Predicted GPR was derived by comparing the TPS fluence with the synthetic measured fluence generated by the DL models using gamma evaluation of criteria 2%/2 mm. The performance of dual training was compared against the traditional single-training approach. In addition, we also developed a separate classification model specifically designed to detect automatically three types of errors (rotational, translational, and MU-scale) in the synthetic EPID-measured fluence. Overall, the dual training improved the prediction accuracy of both cycle-GAN and c-GAN. Predicted GPR results of single training were within 3% for 71.2% and 78.8% of test cases forcycle-GAN and c-GAN, respectively. Moreover, similar results for dual training were 82.7% and 88.5% for cycle-GAN and c-GAN, respectively. The error detection model showed high classification accuracy (>98%) for detecting errors related to rotational and translational errors. However, it struggled to differentiate the fluences with "MU scale error" from "error-free" fluences. We developed a method to automatically generate the synthetic measured fluence and identify errors within them. The proposed dual training improved the PSQA prediction accuracy of both the GAN models, with c-GAN demonstrating superior performance over the cycle-GAN. Our results indicate that the c-GAN with dual training approach combined with error detection model, can accurately generate the synthetic measured fluence for VMAT PSQA and identify the errors. This approach has the potential to pave the way for virtual patient-specific QA of VMAT treatments.

PO-1764 Implementation of SunCHECK Patient for systematic selection of gamma metrices in patient specific QA

PO-1764 Implementation of SunCHECK Patient for systematic selection of gamma metrices in patient specific QA

PO-1751 Correlation between tolerances for EPID metrics and CI dose deviation for patient-specific VMAT QA

PO-1751 Correlation between tolerances for EPID metrics and CI dose deviation for patient-specific VMAT QA

PO-1784 A study of the impact of the dose per pulse on two different detectors for patient-specific QA

PO-1784 A study of the impact of the dose per pulse on two different detectors for patient-specific QA