[8p-E204-1~15] 2.2 Radiation generators, Detector development, Measurement technology

4:15 PM - 4:30 PM JST(7:15 AM - 7:30 AM UTC)

[8p-E204-11] Development of a Machine Learning–Based Electron Track Reconstruction Method for an Electron-Tracking Compton Camera

〇Tomonori Ikeda¹, Tatsuya Sawano², Yoshitaka Mizumura³, Naomi Tsuji⁴ (1.AIST, 2.Kanazawa Univ., 3.JAXA/ISAS, 4.Univ. of Tokyo)

Keywords:

Gamma-ray camera,radiation imaging

Accurate and efficient visualization of radioactive source distributions is crucial for nuclear decommissioning and environmental radiation monitoring. In particular, improving the point spread function (PSF) of gamma-ray imaging systems remains a major challenge for characterizing radioactive contamination in complex structures and over large areas. The electron-tracking Compton camera (ETCC) is a promising technique for quantitative gamma-ray imaging; however, its PSF strongly depends on the accuracy of the reconstructed electron-recoil direction. To address this issue, we have developed a deep-learning–based reconstruction method using two-dimensional optical track images and one-dimensional waveform data. This presentation reports the initial results obtained with the proposed approach.