Physics-assisted generative adversarial network for X-ray tomography

Abstract

X-ray tomography is capable of imaging the interior of objects in three dimensions non-invasively, with applications in biomedical imaging, materials science, electronic inspection, and other fields. The reconstruction process can be an ill-conditioned inverse problem, requiring regularization to obtain satisfactory results. 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 sampling 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 physics and the learned prior. Compared with methods with less physics assisting in training, PGAN can reduce the photon requirement with limited projection angles to achieve a given error rate. The advantages of using a physics-assisted learned prior in X-ray tomography may further enable low-photon nanoscale imaging.

Document Details

Document Type
Pub Defense Publication
Publication Date
Jun 10, 2022
Source ID
10.1364/oe.460208

Entities

People

  • Bradley K. Alpert
  • Courtenay T. Vaughan
  • George Barbastathis
  • Jung Ki Song
  • Kurt W. Larson
  • Michael E. Glinsky
  • Zachary H Levine
  • Zhen Guo

Organizations

  • Intelligence Advanced Research Projects Activity
  • Massachusetts Institute of Technology
  • National Institute of Standards and Technology
  • National Nuclear Security Administration
  • National Research Foundation
  • Sandia National Laboratories
  • Singapore-MIT Alliance for Research and Technology

Tags

Fields of Study

  • Physics

Readers

  • Medical Imaging.
  • Nanoscale Plasmonic Nanotechnology
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Neural Networks
  • Biotechnology
  • Microelectronics