Deep Dose Plugin Towards Real-time Monte Carlo Dose Calculation Through a Deep Learning based Denoising Algorithm

TL;DR

This paper presents a deep learning-based denoising algorithm integrated with GPU Monte Carlo dose calculation, achieving real-time radiotherapy dose computation within 0.15 seconds, suitable for online adaptive treatments.

Contribution

The study introduces a novel deep learning denoiser with acceleration strategies and weakly supervised training, enabling real-time Monte Carlo dose calculation for radiotherapy.

Findings

Denoiser runs in 39 ms, 11.6 times faster than baseline.

Whole dose calculation pipeline completes within 0.15 seconds.

Enables real-time dose calculation for online adaptive radiotherapy.

Abstract

Monte Carlo (MC) simulation is considered the gold standard method for radiotherapy dose calculation. However, achieving high precision requires a large number of simulation histories, which is time consuming. The use of computer graphics processing units (GPUs) has greatly accelerated MC simulation and allows dose calculation within a few minutes for a typical radiotherapy treatment plan. However, some clinical applications demand real time efficiency for MC dose calculation. To tackle this problem, we have developed a real time, deep learning based dose denoiser that can be plugged into a current GPU based MC dose engine to enable real time MC dose calculation. We used two different acceleration strategies to achieve this goal: 1) we applied voxel unshuffle and voxel shuffle operators to decrease the input and output sizes without any information loss, and 2) we decoupled the 3D volumetric convolution into a 2D axial convolution and a 1D slice convolution. In addition, we used a weakly supervised learning framework to train the network, which greatly reduces the size of the required training dataset and thus enables fast fine tuning based adaptation of the trained model to different radiation beams. Experimental results show that the proposed denoiser can run in as little as 39 ms, which is around 11.6 times faster than the baseline model. As a result, the whole MC dose calculation pipeline can be finished within 0.15 seconds, including both GPU MC dose calculation and deep learning based denoising, achieving the real time efficiency needed for some radiotherapy applications, such as online adaptive radiotherapy.