Premium
Technical Note: Machine learning approaches for range and dose verification in proton therapy using proton‐induced positron emitters
Author(s) -
Li Zhongxing,
Wang Yiang,
Yu Yajun,
Fan Kuanjun,
Xing Lei,
Peng Hao
Publication year - 2019
Publication title -
medical physics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.473
H-Index - 180
eISSN - 2473-4209
pISSN - 0094-2405
DOI - 10.1002/mp.13827
Subject(s) - proton therapy , proton , imaging phantom , positron emission tomography , artificial neural network , range (aeronautics) , artificial intelligence , positron , noise (video) , mean squared error , feed forward , computer science , quality assurance , physics , algorithm , nuclear medicine , mathematics , materials science , nuclear physics , statistics , optics , engineering , electron , medicine , image (mathematics) , control engineering , composite material , external quality assessment , operations management
Purpose/objective(s) Online proton range/dose verification based on measurements of proton‐induced positron emitters is a promising strategy for quality assurance in proton therapy. Because of the nonlinear correlation between the dose distribution and the activity distribution of positron emitters in addition to the presence of noise, machine learning approaches were proposed to establish their relationship. Materials/methods Simulations were carried out with a spot‐scanning proton system using GATE‐8.0 and Geant4‐10.3 toolkit with a computed tomography (CT)‐based patient phantom. The one‐dimensional (1D) distributions of positron emitters and radiation dose were obtained. A feedforward neural network classification model comprising two hidden layers, was developed to estimate whether the range is within a preset threshold. A recurrent neural network (RNN) regression model comprising three layers and ten neurons in each hidden layer was developed to estimate dose distribution. The performance was quantitatively studied in terms of mean squared error (MSE) and mean absolute error (MAE) under different signal‐to‐noise ratio (SNR) values. Results The feasibility of proton range and dose verification using the proposed neural network framework was demonstrated. The feedforward NN model achieves high classification accuracy close to 100% for individual classes without bias. The RNN model is able to accurately predict the 1D dose distribution for different energies and irradiation positions. When the SNR of the input activity profiles is above 4, the framework is able to predict with an MAE of ~0.60 mm and an MSE of ~0.066. Moreover, the model demonstrates a good capability of generalization. Conclusions The RNN model is found to be effective in identifying the relationship between the distributions of dose and positron emitters. The machine learning‐based framework and RNN models may be a useful tool to allow for accurate online range and dose verification based on proton‐induced positron emitters.