Predicting gamma evaluation results of patient‐specific head and neck volumetric‐modulated arc therapy quality assurance based on multileaf collimator patterns and fluence map features: A feasibility study

Thongsawad, Sangutid; Srisatit, Somyot; Fuangrod, Todsaporn

doi:10.1002/acm2.13622

Cited by 10 publications

(15 citation statements)

References 40 publications

(67 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…process-based tolerance introduced by AAPM TG-218 in 240 beams used as the modeling of the GAN model. 1,21 The lower control limit from I-chart was used to determine the clinical acceptance criteria, which can be calculated using Clinical acceptance criteria = aGPR − 2.66 ⋅ mR, (11) where aGPR is averaged mGPR, and mR is moving range can be calculated using…”

Section: Discussionmentioning

confidence: 99%

“…The GAN model synthesizes a gamma distribution, and the GPR and failing points are calculated. The clinical acceptance criterion of GPR is determined by process‐based tolerance introduced by AAPM TG‐218 in 240 beams used as the modeling of the GAN model 1,21 . The lower control limit from I‐chart was used to determine the clinical acceptance criteria, which can be calculated using

\begin{equation}\fontsize{9}{10}{\rm{Clinical\;acceptance\;criteria\;}} = \;a{\rm{GPR}} - 2.66 \cdot \overline {mR} ,\end{equation}

where a GPR is averaged m GPR, and

\overline {mR}

is moving range can be calculated using

\begin{equation}\overline {mR} = \frac{1}{{n - 1}}{\rm{\;}}\mathop \sum \limits_{i{\rm{\;}} = {\rm{\;}}2}^n \left| {{x_i} - {x_{i - 1}}} \right|,\end{equation}

where n is the measurement total number, and x is individual GPR.…”

Section: Methodsmentioning

confidence: 99%

“…These models use complexity metrics, fluence maps, and dose distributions as input data and successfully predict the outcome of gamma analysis directly with high accuracy. [14][15][16][17][18][19][20][21][22][23] These studies focused on predicting GPR or classifying whether the GPR meets the acceptance criteria. However, there is a limitation that the GPR value loses the locational information of dose accuracy.…”

Section: Introductionmentioning

confidence: 99%

“…Recently, artificial intelligence (AI) has been used to predict QA outcomes. These models use complexity metrics, fluence maps, and dose distributions as input data and successfully predict the outcome of gamma analysis directly with high accuracy 14–23 . These studies focused on predicting GPR or classifying whether the GPR meets the acceptance criteria.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A synthesized gamma distribution‐based patient‐specific VMAT QA using a generative adversarial network

et al. 2023

View full text Add to dashboard Cite

Background Artificial intelligence (AI)‐based gamma passing rate (GPR) prediction has been proposed as a time‐efficient virtual patient‐specific QA method for the delivery of volumetric modulation arc therapy (VMAT). However, there is a limitation that the GPR value loses the locational information of dose accuracy. Purpose The objective was to predict the failing points in the gamma distribution and the GPR using a synthesized gamma distribution of VMAT QA with a deep convolutional generative adversarial network (GAN). Methods The fluence maps of 270 VMAT beams for prostate cancer were measured using an electronic portal imaging device and analyzed using gamma evaluation with 3%/2‐mm, 2%/1‐mm, 1%/1‐mm, and 1%/0.5‐mm tolerances. The 270 gamma distributions were divided into two datasets: 240 training datasets for creating a model and 30 test datasets for evaluation. The image prediction network for the fluence maps calculated by the treatment planning system (TPS) to the gamma distributions was created using a GAN. The sensitivity, specificity, and accuracy of detecting failing points were evaluated using measured and synthesized gamma distributions. In addition, the difference between measured GPR (mGPR) and predicted GPR (pGPR) values calculated from the synthesized gamma distributions was evaluated. Results The root mean squared errors between mGPR and pGPR were 1.0%, 2.1%, 3.5%, and 3.6% for the 3%/2‐mm, 2%/1‐mm, 1%/1‐mm, and 1%/0.5‐mm tolerances, respectively. The accuracies for detecting failing points were 98.9%, 96.9%, 94.7%, and 93.7% for 3%/2‐mm, 2%/1‐mm, 1%/1‐mm, and 1%/0.5‐mm tolerances, respectively. The sensitivity and specificity were the highest for 1%/0.5‐mm and 3%/2‐mm tolerances, which were 82.7% and 99.6%, respectively. Conclusions We developed a novel system using a GAN to generate a synthesized gamma distribution‐based patient‐specific VMAT QA. The system is promising from the point of view of quality assurance in radiotherapy because it shows high performance and can detect failing points.

show abstract

Section: Discussionmentioning

confidence: 99%

\begin{equation}\fontsize{9}{10}{\rm{Clinical\;acceptance\;criteria\;}} = \;a{\rm{GPR}} - 2.66 \cdot \overline {mR} ,\end{equation}

where a GPR is averaged m GPR, and

\overline {mR}

is moving range can be calculated using

\begin{equation}\overline {mR} = \frac{1}{{n - 1}}{\rm{\;}}\mathop \sum \limits_{i{\rm{\;}} = {\rm{\;}}2}^n \left| {{x_i} - {x_{i - 1}}} \right|,\end{equation}

where n is the measurement total number, and x is individual GPR.…”

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A synthesized gamma distribution‐based patient‐specific VMAT QA using a generative adversarial network

et al. 2023

View full text Add to dashboard Cite

show abstract

“…A large number of papers further extended these approaches by developing classical machine learning and deep learning models to predict the PSQA failure based on a vast array of the plan complexity metrics as well as other heuristic features 21,22,23,24,25,26,27,28 . Thongsawad et al used MLC texture analysis and boosting algorithms for predicting gamma evaluation results 29 . Kimura et al .…”

Section: Introductionmentioning

confidence: 99%

Patient-specific Quality Assurance Failure Prediction with Deep Tabular Models

Levin

Aravkin

Kim

2022

Preprint

View full text Add to dashboard Cite

Background: Patient-specific quality assurance (PSQA) is part of the standard practice to ensure that a patient receives the dose from intensity-modulated radiotherapy (IMRT) beams as planned in the treatment planning system (TPS). PSQA failures can cause a delay in patient care and increase workload and stress of staff members. A large body of previous work for PSQA failure prediction focuses on non-learned plan complexity measures. Another prominent line of work uses machine learning methods, often in conjunction with feature engineering. Currently, there are no machine learning solutions which work directly with multi-leaf collimator (MLC) leaf positions, providing an opportunity to improve leaf sequencing algorithms using these techniques. Purpose: To improve patient safety and work efficiency, we develop a tabular transformer model based directly on the MLC leaf positions (without any feature engineering) to predict IMRT PSQA failure. This neural model provides an end-to-end differentiable map from MLC leaf positions to the probability of PSQA plan failure, which could be useful for regularizing gradient-based leaf sequencing optimization algorithms and generating a plan that is more likely to pass PSQA. Method: We retrospectively collected DICOM RT PLAN files of 968 patient plans treated with volumetric arc therapy. We construct a beam-level tabular dataset with 1873 beams as samples and MLC leaf positions as features. We train an attention-based neural network FT-Transformer to predict the ArcCheck-based PSQA gamma pass rates. In addition to the regression task, we evaluate the model in the binary classification context predicting the pass or fail of PSQA. The performance was compared to the results of the two leading tree ensemble methods (CatBoost and XGBoost) and a non-learned method based on mean MLC gap. Results: The FT-Transformer model achieves 1.44% Mean Absolute Error (MAE) in the regression task of the gamma pass rate prediction and performs on par with XGBoost (1.53 % MAE) and CatBoost (1.40 % MAE). In the binary classification task of PSQA failure prediction, FT-Transformer achieves 0.85 ROC AUC (with CatBoost and XGBoost achieving 0.87 ROC AUC and the mean-MLC-gap complexity metric achieving 0.72 ROC AUC). %While AUC summarizes the performance of binary classification models for all prediction thresholds, the performance at specific thresholds that maximize the true positive rate of PSQA failure identification while maintaining low false positive rate is of interest for clinical applications. Moreover, FT-Transformer, CatBoost, and XGBoost all achieve 80\% true positive rate while keeping the false positive rate under 20%. Conclusions: We demonstrate that reliable PSQA failure predictors can be successfully developed based solely on MLC leaf positions. Our FT-Transformer neural network can reduce the need for patient rescheduling due to PSQA failures by 80% while sending only 20% of plans that would not have failed the PSQA for replanning. FT-Transformer achieves comparable performance with the leading tree ensemble methods while having an additional benefit of providing an end-to-end differentiable map from MLC leaf positions to the probability of PSQA failure.

show abstract

Predicting gamma evaluation results of patient‐specific head and neck volumetric‐modulated arc therapy quality assurance based on multileaf collimator patterns and fluence map features: A feasibility study

Thongsawad

Srisatit

Fuangrod

2022

J Applied Clin Med Phys

Self Cite

View full text Add to dashboard Cite

The purpose of this study was to develop a predictive model for patient‐specific VMAT QA results using multileaf collimator (MLC) effect and texture analysis. The MLC speed, acceleration and texture analysis features were extracted from 106 VMAT plans as predictors. Gamma passing rate (GPR) was collected as a response class with gamma criteria of 2%/2 mm and 3%/2 mm. The model was trained using two machine learning methods: AdaBoost classification and bagged regression trees model. GPR was classified into the “PASS” and “FAIL” for the classification model using the institutional warning level. The accuracy of the model was assessed using sensitivity and specificity. In addition, the accuracy of the regression model was determined using the difference between predicted and measured GPR. For the AdaBoost classification model, the sensitivity/specificity was 94.12%/100% and 63.63%/53.13% at gamma criteria of 2%/2 mm and 3%/2 mm, respectively. For the bagged regression trees model, the sensitivity/specificity was 94.12%/91.89% and 61.18%/68.75% at gamma criteria of 2%/2 mm and 3%/2 mm, respectively. The root mean square error (RMSE) of difference between predicted and measured GPR was found at 2.44 and 1.22 for gamma criteria of 2%/2 mm and 3%/2 mm, respectively. The promising result was found at tighter gamma criteria 2%/2 mm with 94.12% sensitivity (both bagged regression trees and AdaBoost classification model) and 100% specificity (AdaBoost classification model).

show abstract

Predicting gamma evaluation results of patient‐specific head and neck volumetric‐modulated arc therapy quality assurance based on multileaf collimator patterns and fluence map features: A feasibility study

Cited by 10 publications

References 40 publications

A synthesized gamma distribution‐based patient‐specific VMAT QA using a generative adversarial network

A synthesized gamma distribution‐based patient‐specific VMAT QA using a generative adversarial network

Patient-specific Quality Assurance Failure Prediction with Deep Tabular Models

Predicting gamma evaluation results of patient‐specific head and neck volumetric‐modulated arc therapy quality assurance based on multileaf collimator patterns and fluence map features: A feasibility study

Contact Info

Product

Resources

About