ABSTRACT
Objective:Proton pencil beam (PB) dose calculation can achieve rapid dose calculation, whereas it is inaccurate due to the approximation in dealing with inhomogeneities. Monte Carlo (MC) dose calculation is recognized as the most accurate method, but it is extremely time consuming. The aim of this study was to apply deep-learning methods to improve the accuracy of PB dose calculation by learning the difference between the MC and PB dose distribution.Methods:A model which could convert the PB dose into the MC dose in lung cancer patients treated with intensity-modulated proton therapy (IMPT) was established based on the Hierarchically Densely Connected U-Net (HD U-Net) network. PB dose and CT images were used as model input to predict the MC dose for IMPT. The beam dose and CT images of 27 non-small cell lung cancer patients were preprocessed to the same angle and normalized, and then used as model input. The accuracy of the model was evaluated by comparing the mean square error and γ passing rate (1 mm/1%) results between the predicted dose and MC dose.Results:The predicted dose showed good agreement with MC dose. Using the 1 mm/1% criteria, the average γ passing rate (voxels receiving more than 10% of maximum MC dose) between the predicted and MC doses reached (92.8±3.4)% for the test patients. The average dose prediction time for test patients was (6.72±2.26) s.Conclusion:A deep-learning model that can accurately predict the MC dose based on the PB dose and CT images is successfully developed, which can be used as an efficient and practical tool to improve the accuracy of PB dose calculation for IMPT in lung cancer patients.
ABSTRACT
Proton beams have been used for cancer treatment for more than 28 years, and several technological advancements have been made to achieve improved clinical outcomes by delivering more accurate and conformal doses to the target cancer cells while minimizing the dose to normal tissues. The state-of-the-art intensity modulated proton therapy is now prevailing as a major treatment technique in proton facilities worldwide, but still faces many challenges in being applied to the lung. Thus, in this article, the current status of proton therapy technique is reviewed and issues regarding the relevant uncertainty in proton therapy in the lung are summarized.
Subject(s)
Lung Neoplasms , Lung , Proton Therapy , Protons , UncertaintyABSTRACT
Objective Because of high precision and mild side effects,intensity-modulated proton therapy (IMPT) has become a hot spot in the radiotherapy field.Nevertheless,the precision of IMPT is extremely sensitive to the range uncertainties.In this paper,a novel robust optimization method was proposed to reduce the effect of range uncertainty upon IMPT.Methods Firstly,the robust optimization model was established which contained three types of range including the increased range,the normal range and the shortened range.The objective function was expressed in quadratic function.The organ dose contribution matrix of each range was calculated by proton pencil beam algorithm.The range deviation was discretized and the probability of each range was obtained based on the Gauss distribution function.Finally,the conjugate gradient method was adopted to find the optimal solution to make the actual dose coverage of the target area and the organs at risk distributed within the expected dose as possible.Results The 3 sets of simulation tests provided by the AAPM TG-119 Report were utilized to evaluate the effectiveness of this method:nasopharyngeal carcinoma,prostate and "C"-type cases.Compared with conventional IMPT optimization approach,this novel method was less sensitive to the range uncertainty.When the range deviation occurred,the dose coverage of the target area and organs at risk of the nasopharyngeal carcinoma and prostate cases almost reached the expected dose,and the high dose coverage of the target area and organs at risk protection were improved in the"C"-type cases.Conclusions To compensate for the range uncertainty,this novel method can enhance the dose coverage of the target area and reduce the dose coverage of the organs at risk.