Estimating Spatially Resolved Radiation Fields Using Neural Networks
This work addresses radiation protection dosimetry for medical professionals in fields like interventional radiology and cardiology, but it is incremental as it focuses on evaluating existing neural network architectures on new synthetic data.
The authors tackled the problem of estimating spatially resolved radiation fields for medical radiation protection dosimetry by developing and evaluating neural network architectures on synthetic datasets generated via Monte-Carlo simulation, achieving results that demonstrate effective design decisions for reconstructing fluence and spectra distributions.
We present an in-depth analysis on how to build and train neural networks to estimate the spatial distribution of scattered radiation fields for radiation protection dosimetry in medical radiation fields, such as those found in interventional radiology and cardiology. We present three different synthetically generated datasets with increasing complexity for training, using a Monte-Carlo Simulation application based on Geant4. On those datasets, we evaluate convolutional and fully connected architectures of neural networks to demonstrate which design decisions work well for reconstructing the fluence and spectra distributions over the spatial domain of such radiation fields. All our datasets, as well as our training pipeline, are published as open source in separate repositories.