Accurate and fast deep learning dose prediction for a preclinical microbeam radiation therapy study using low-statistics Monte Carlo simulations

TL;DR

This study demonstrates a machine learning model that accurately and rapidly predicts radiation doses in microbeam radiation therapy, significantly reducing computation time while maintaining high accuracy even with low-statistics Monte Carlo training data.

Contribution

The paper introduces a novel ML dose prediction model for MRT that performs well with high-noise training data, enabling faster and more efficient dose estimations for emerging cancer treatments.

Findings

ML model achieves excellent agreement with Monte Carlo simulations

High-noise training data enables faster model training

Model effectively predicts peak and valley doses in MRT

Abstract

Microbeam radiation therapy (MRT) utilizes coplanar synchrotron radiation beamlets and is a proposed treatment approach for several tumour diagnoses that currently have poor clinical treatment outcomes, such as gliosarcomas. Prescription dose estimations for treating preclinical gliosarcoma models in MRT studies at the Imaging and Medical Beamline at the Australian Synchrotron currently rely on Monte Carlo (MC) simulations. The steep dose gradients associated with the 50$\,\mu$m wide coplanar beamlets present a significant challenge for precise MC simulation of the MRT irradiation treatment field in a short time frame. Much research has been conducted on fast dose estimation methods for clinically available treatments. However, such methods, including GPU Monte Carlo implementations and machine learning (ML) models, are unavailable for novel and emerging cancer radiation treatment options like MRT. In this work, the successful application of a fast and accurate machine learning dose prediction model in a retrospective preclinical MRT rodent study is presented for the first time. The ML model predicts the peak doses in the path of the microbeams and the valley doses between them, delivered to the gliosarcoma in rodent patients. The predictions of the ML model show excellent agreement with low-noise MC simulations, especially within the investigated tumour volume. This agreement is despite the ML model being deliberately trained with MC-calculated samples exhibiting significantly higher statistical uncertainties. The successful use of high-noise training set data samples, which are much faster to generate, encourages and accelerates the transfer of the ML model to different treatment modalities for other future applications in novel radiation cancer therapies.