The stochastic nature of 3-D Monte Carlo (MC) photon transport simulations requires simulating a large number of photons to achieve stable solutions. In this work, we explore state-of-the-art deep-learning (DL) based image denoising techniques, including the proposal of cascaded DnCNN and UNet denoising networks, aiming at significantly reducing the stochastic noise in low-photon MC simulations to achieve both high speed and high image quality. We demonstrate that all tested DL based denoisiers are significantly more effective compared to model-based denoising methods. In our benchmarks, our cascaded denoisier has achieved a signal enhancement equivalent to running 25x-78x more photons.

© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.

Matin Raayai Ardakani, Leiming Yu, David R. Kaeli, and Qianqian Fang, "A framework for enhancing Monte Carlo photon transport simulations using deep learning," Proc. SPIE PC12371, Multimodal Biomedical Imaging XVIII, PC123710E (Presented at SPIE BiOS: January 29, 2023; Published: 6 March 2023); https://doi.org/10.1117/12.2659549.6321506647112.