RadField3D: A Data Generator and Data Format for Deep Learning in Radiation-Protection Dosimetry for Medical Applications
This work provides a tool for researchers in medical radiation protection to generate and process data for deep learning applications, but it is incremental as it focuses on data generation and format rather than novel simulation methods.
The authors developed RadField3D, an open-source Geant4-based Monte-Carlo simulation tool and data format for generating 3D radiation field datasets in medical dosimetry, aimed at enabling deep learning research for alternative radiation simulation methods.
In this research work, we present our open-source Geant4-based Monte-Carlo simulation application, called RadField3D, for generating threedimensional radiation field datasets for dosimetry. Accompanying, we introduce a fast, machine-interpretable data format with a Python API for easy integration into neural network research, that we call RadFiled3D. Both developments are intended to be used to research alternative radiation simulation methods using deep learning.