[10a-M112-1~6] 2.3 Application, radiation generators, new technology

[10a-M112-6] Estimation of Bragg-Peak Shifts via Machine Learning Using Proton-Beam Image Obtained by Secondary-Electron-Bremsstrahlung Measurement

〇Mitsutaka Yamaguchi¹, Yuto Nagao¹, Naoki Kawachi¹ (1.QST TARRI)

Keywords:particle beam cancer therapy, secondary electron bremssrtahlung, machine learning

We investigated an estimation method of Bragg-peak shifts via machine learning using proton-beam images obtained by measurement of secondary electron bremsstrahlung (SEB) by Monte Carlo simulation using PHITS. Proton beams having beam energy of 139 MeV were incident on a water phantom with randomly placed air spheres inside, and 6400 pairs of "a proton beam image" and "a Bragg-peak shift" were prepared and then multiple linear regression analysis was carried out. Consequently, a prediction model with small variance and high prediction performance was obtained.