Physics-Driven Learning of Wasserstein GAN for Density Reconstruction in Dynamic Tomography

TL;DR

This paper presents a physics-informed Wasserstein GAN approach for denoising and reconstructing object densities in dynamic tomography, effectively handling uncharacterized noise and artifacts in noisy projection data.

Contribution

It introduces a novel physics-guided deep learning framework combining WGANs with mass conservation constraints for improved density reconstruction in dynamic imaging.

Findings

Effective artifact removal in noisy density data

Enhanced reconstruction accuracy with physics-based constraints

Robust denoising performance on simulated datasets

Abstract

Object density reconstruction from projections containing scattered radiation and noise is of critical importance in many applications. Existing scatter correction and density reconstruction methods may not provide the high accuracy needed in many applications and can break down in the presence of unmodeled or anomalous scatter and other experimental artifacts. Incorporating machine-learned models could prove beneficial for accurate density reconstruction particularly in dynamic imaging, where the time-evolution of the density fields could be captured by partial differential equations or by learning from hydrodynamics simulations. In this work, we demonstrate the ability of learned deep neural networks to perform artifact removal in noisy density reconstructions, where the noise is imperfectly characterized. We use a Wasserstein generative adversarial network (WGAN), where the generator serves as a denoiser that removes artifacts in densities obtained from traditional reconstruction algorithms. We train the networks from large density time-series datasets, with noise simulated according to parametric random distributions that may mimic noise in experiments. The WGAN is trained with noisy density frames as generator inputs, to match the generator outputs to the distribution of clean densities (time-series) from simulations. A supervised loss is also included in the training, which leads to improved density restoration performance. In addition, we employ physics-based constraints such as mass conservation during network training and application to further enable highly accurate density reconstructions. Our preliminary numerical results show that the models trained in our frameworks can remove significant portions of unknown noise in density time-series data.