Electron-tracking Compton camera, which is a complete Compton camera with tracking Compton scattering electron by a gas micro time projection chamber, is expected to open up MeV gamma-ray astronomy. The technical challenge for achieving several degrees of the point spread function is the precise determination of the electron-recoil direction and the scattering position from track images. We attempted to reconstruct these parameters using convolutional neural networks. Two network models were designed to predict the recoil direction and the scattering position. These models marked 41degrees of the angular resolution and 2.1mm of the position resolution for 75keV electron simulation data in Argon-based gas at 2atm pressure. In addition, the point spread function of ETCC was improved to 15degrees from 22degrees for experimental data of 662keV gamma-ray source. These performances greatly surpassed that using the traditional analysis.
@article{arxiv.2105.02512,
title = {Development of Convolutional Neural Networks for an Electron-Tracking Compton Camera},
author = {Tomonori Ikeda and Atsushi Takada and Mitsuru Abe and Kei Yoshikawa and Masaya Tsuda and Shingo Ogio and Shinya Sonoda and Yoshitaka Mizumura and Yura Yoshida and Toru Tanimori},
journal= {arXiv preprint arXiv:2105.02512},
year = {2022}
}