This is the authors' abstract. We don't add key points for this paper.
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. Proton beams having energy of 139 MeV were incident on a water phantom with randomly placed air spheres inside, and 6400 pairs of “proton-beam images” and “a Bragg-peak shift” were prepared and then multiple linear regression analysis was carried out. A good agreement was found between the actual Bragg-peak shifts and predicted values in both the training and test sets. The coefficients of determination of the obtained prediction model were 0.899 for the training set and 0.894 for the test set. Consequently, we found that a prediction model with small variance and high prediction performance could be obtained using the SEB data.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Yamaguchi et al. (2019) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: