RadField3D: A Data Generator and Data Format for Deep Learning in Radiation-Protection Dosimetry for Medical Applications

TL;DR

RadField3D is an open-source Monte Carlo simulation tool and data format designed to generate and utilize 3D radiation field datasets for deep learning applications in medical radiation dosimetry.

Contribution

The paper introduces RadField3D, a novel Geant4-based simulation application and a new machine-interpretable data format with Python API for deep learning in radiation dosimetry.

Findings

Provides a flexible, open-source simulation tool for 3D radiation fields.

Introduces a new data format compatible with neural network research.

Facilitates research into alternative radiation simulation methods.

Abstract

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.