Physics-assisted Generative Adversarial Network for X-Ray Tomography

Published

June 10, 2022

Author(s)

Zhen Guo, Jungki Song, George Barbastathis, Michael Glinsky, Courtenay Vaughan, Kurt Larson, Bradley Alpert, Zachary H. Levine

Abstract

X-ray tomography is capable of imaging the interior of objects in three dimensions non-invasively, with applications in biomedical imaging, materials study, electronic inspection, and other fields. The reconstruction process can be an ill-conditioned inverse problem, requiring regularization to obtain satisfactory reconstructions. Recently, deep learning has been adopted for tomographic reconstruction. Unlike iterative algorithms which require a distribution that is known a priori, deep reconstruction networks can learn a prior distribution through exploring the statistical properties of the training distributions. In this work, we develop a Physics-assisted Generative Adversarial Network (PGAN), a two-step algorithm for tomographic reconstruction. In contrast to previous efforts, our PGAN utilizes maximum-likelihood estimates derived from the measurements to regularize the reconstruction with both known physical prior and the corresponding estimates. Synthetic objects are integrated-circuits from a proposed integrated circuit (IC) model we call CircuitFaker. Compared with maximum-likelihood estimation, PGAN can dramatically improve the synthetic IC reconstruction quality when the projection angles and photon budgets are limited, reducing the photon requirement in imaging to achieve a given error rate. The advantages of using learned prior from deep learning in X-ray tomography may further enable low-photon nanoscale imaging.

Citation

Optics Express

Volume

30

Issue

13

Pub Type

Journals

Download Paper

https://doi.org/10.1364/OE.460208

Local Download

Keywords

X-ray tomography, machine learning, autoencoder

Citation

Guo, Z. , Song, J. , Barbastathis, G. , Glinsky, M. , Vaughan, C. , Larson, K. , Alpert, B. and Levine, Z. (2022), Physics-assisted Generative Adversarial Network for X-Ray Tomography, Optics Express, [online], https://doi.org/10.1364/OE.460208, https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=933970 (Accessed April 27, 2024)