Proton path reconstruction for pCT using Neural Networks

TL;DR

This paper introduces a deep neural network approach for proton path reconstruction in pCT that matches or exceeds the accuracy of the traditional MLP method, especially in cases involving nuclear interactions, while also being faster.

Contribution

The authors develop a DNN-based method for proton path estimation that improves accuracy with nuclear interactions and reduces computation time compared to MLP.

Findings

DNN achieves equivalent accuracy to MLP when only MCS occurs.

DNN provides increased accuracy in the presence of nuclear interactions.

DNN is significantly faster than the MLP algorithm.

Abstract

The Most Likely Path formalism (MLP) is widely established as the most statistically precise method for proton path reconstruction in proton computed tomography (pCT). However, while this method accounts for small-angle Multiple Coulomb Scattering (MCS) and energy loss, inelastic nuclear interactions play an influential role in a significant number of proton paths. By applying cuts based on energy and direction, tracks influenced by nuclear interactions are largely discarded from the MLP analysis. In this work we propose a new method to estimate the proton paths based on a Deep Neural Network (DNN). Through this approach, estimates of proton paths equivalent to MLP predictions have been achieved in the case where only MCS occurs, together with an increased accuracy when nuclear interactions are present. Moreover, our tests indicate that the DNN algorithm can be considerably faster than the MLP algorithm.