Abstract

BackgroundThis paper describes the development of a predicted electronic portal imaging device (EPID) transmission image (TI) using Monte Carlo (MC) and deep learning (DL). The measured and predicted TI were compared for two-dimensional in vivo radiotherapy treatment verification.MethodsThe plan CT was pre-processed and combined with solid water and then imported into PRIMO. The MC method was used to calculate the dose distribution of the combined CT. The U-net neural network-based deep learning model was trained to predict EPID TI based on the dose distribution of solid water calculated by PRIMO. The predicted TI was compared with the measured TI for two-dimensional in vivo treatment verification.ResultsThe EPID TI of 1500 IMRT fields were acquired, among which 1200, 150, and 150 fields were used as the training set, the validation set, and the test set, respectively. A comparison of the predicted and measured TI was carried out using global gamma analyses of 3%/3 mm and 2%/2 mm (5% threshold) to validate the model's accuracy. The gamma pass rates were greater than 96.7% and 92.3%, and the mean gamma values were 0.21 and 0.32, respectively.ConclusionsOur method facilitates the modelling process more easily and increases the calculation accuracy when using the MC algorithm to simulate the EPID response, and has potential to be used for in vivo treatment verification in the clinic.

Highlights

  • Intensity-modulated radiation therapy (IMRT) and volumetric-modulated arc therapy (VMAT) technologies can control the irradiation area more accurately, ensure that the tumour target receives higher and more conformal doses, reduce the effects on surrounding normal tissues or prevent unnecessary radiation, and these technologies are becoming increasingly common in radiotherapy [1].Compared with traditional three-dimensional conformal therapy, IMRT is more complicated, with a greater probability of errors in radiotherapy

  • The combined computed tomography (CT) and the new plan were imported into PRIMO to simulate the dose distribution of the combined CT, and the dose of the equivalent electronic portal imaging device (EPID) plane was derived as the input of the deep learning (DL) training model

  • PRIMO calculated the dose distribution of the equivalent EPID, and the transmission image (TI) was predicted by the trained DL prediction model

Read more

Summary

Introduction

Intensity-modulated radiation therapy (IMRT) and volumetric-modulated arc therapy (VMAT) technologies can control the irradiation area more accurately, ensure that the tumour target receives higher and more conformal doses, reduce the effects on surrounding normal tissues or prevent unnecessary radiation, and these technologies are becoming increasingly common in radiotherapy [1].Compared with traditional three-dimensional conformal therapy, IMRT is more complicated, with a greater probability of errors in radiotherapy. If the dose received in the target deviates significantly from the dose planned by the treatment planning system (TPS), radiation therapy (RT) accidents may occur. Electronic portal imaging device (EPID) has been applied in dose verification by many researchers due to its fast image acquisition speed, high resolution, good linear dose response, long-term stability, and ability to be mounted on the linac [2–4]. Dose verification with EPID is mainly divided into pre-treatment verification [5–7] and in vivo verification [3, 8–11]. Pre-treatment verification cannot detect setup errors that occur during treatment, and in vivo treatment verification is more sensitive to possible dose deviations due to changes in tumor size, patient weight and organ motion; in vivo treatment verification is more meaningful. The measured and predicted TI were compared for two-dimensional in vivo radiotherapy treatment verification

Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call