Prediction of the output factor using machine and deep learning approach in uniform scanning proton therapy

Abstract

Purpose The purpose of this work is to develop machine and deep learning‐based models to predict output and MU based on measured patient quality assurance (QA) data in uniform scanning proton therapy (USPT). Methods This study involves 4,231 patient QA measurements conducted over the last 6 years. In the current approach, output and MU are predicted by an empirical model (EM) based on patient treatment plan parameters. In this study, two MATLAB‐based machine and deep learning algorithms — Gaussian process regression (GPR) and shallow neural network (SNN) — were developed. The four parameters from patient QA (range, modulation, field size, and measured output factor) were used to train these algorithms. The data were randomized with a training set containing 90% and a testing set containing remaining 10% of the data. The model performance during training was accessed using root mean square error (RMSE) and R‐squared values. The trained model was used to predict output based on the three input parameters: range, modulation, and field size. The percent difference was calculated between the predicted and measured output factors. The number of data sets required to make prediction accuracy of GPR and SNN models' invariable was also evaluated. Results The prediction accuracy of machine and deep learning algorithms is higher than the EM. The output predictions with [GPR, SNN, and EM] within ± 2% and ± 3% difference were [97.16%, 97.64%, and 92.95%] and [99.76%, 99.29%, and 97.18%], respectively. The GPR model outperformed the SNN with a smaller number of training data sets. Conclusion The GPR and SNN models outperformed the EM in terms of prediction accuracy. Machine and deep learning algorithms predicted the output factor and MU for USPT with higher predictive accuracy than EM. In our clinic, these models have been adopted as a secondary check of MU or output factors.

Auto‐Trending daily quality assurance program for a pencil beam scanning proton system aligned with TG 224

“…There is a clinical need for developing software to automatically run in the background to put the DQA data into a database and show each parameter trend with time. Few DQA literature combined the DQA data with automation and Artificial Intelligent (AI) implementation, 9 although there have been reports on machine learning applications in proton dose verifications, 10–12 Linac QA, 13–15 patient‐specific QA in radiotherapy 16–19 …”

“…There is a clinical need for developing software to automatically run in the background to put the DQA data into a database and show each parameter trend with time. Few DQA literature combined the DQA data with automation and Artificial Intelligent (AI) implementation, 9 although there have been reports on machine learning applications in proton dose verifications, [10][11][12] Linac QA, [13][14][15] patient-specific QA in radiotherapy. [16][17][18][19] Based on the clinical urgent need for DQA procedures, automation, and AI implementation, an auto trending DQA program alignment with TG 224 guideline has been developed at New York Proton Center (NYPC).…”

Monitor unit prediction model for wobbling proton therapy with ridge filters

“…Note that there is another approach, where the output prediction was performed by machine learning. 21,22 But we chose to fit the data analytically because this is transparent and easy to handle. Even though the machine learning approach could give a better prediction than the conventional method, it is hard to understand the origin of the result due to its black-box nature.…”

Integration of AI and Machine Learning in Radiotherapy QA

“…They concluded that machine learning methods can be used for a sanity check of output measurements and has the potential to eliminate time-consuming patient-specific measurements. Similarly, Grewal et al utilized 4,231 QA measurements with a train/test split of 90 and 10% to build models to predict OF and MU for uniform scanning proton beams with two learning algorithms—Gaussian process regression and shallow neural network (Grewal et al, 2020 ). They found that the prediction accuracy of machine and deep learning algorithms is higher than the empirical model currently used in the clinic.…”