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-learning 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 an improved density restoration performance. In addition, we employ physics-based constraints such as mass conservation during the 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.

© 2022 Optica Publishing Group

High-precision inversion of dynamic radiography using hydrodynamic features

Maliha Hossain, Balasubramanya T. Nadiga, Oleg Korobkin, Marc L. Klasky, Jennifer L. Schei, Joshua W. Burby, Michael T. McCann, Trevor Wilcox, Soumi De, and Charles A. Bouman
Opt. Express 30(9) 14432-14452 (2022)

Learned regularization for image reconstruction in sparse-view photoacoustic tomography

Tong Wang, Menghui He, Kang Shen, Wen Liu, and Chao Tian
Biomed. Opt. Express 13(11) 5721-5737 (2022)

Simulation-driven learning: a deep learning approach for image scanning microscopy via physical imaging models

Baoyuan Zhang, Xuefeng Sun, Hongxia Yang, Cheng Guo, Biwei Wu, Jiubin Tan, and Weibo Wang
Opt. Express 30(7) 11848-11860 (2022)

Physics-assisted generative adversarial network for X-ray tomography

Zhen Guo, Jung Ki Song, George Barbastathis, Michael E. Glinsky, Courtenay T. Vaughan, Kurt W. Larson, Bradley K. Alpert, and Zachary H. Levine
Opt. Express 30(13) 23238-23259 (2022)

DH-GAN: a physics-driven untrained generative adversarial network for holographic imaging

Xiwen Chen, Hao Wang, Abolfazl Razi, Michael Kozicki, and Christopher Mann
Opt. Express 31(6) 10114-10135 (2023)