Solving optical tomography with deep learning

DOI10.4310/AMSA.2022.V7.N2.A3MaRDI QIDQ2084728zbMATHOpenAlexFDO

Authors Yu-Wei Fan, Lexing Ying

Publication date 13 October 2022

Published in Annals of Mathematical Sciences and Applications (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1910.04756

zbMATH Keywords

deep learninginverse problemsradiative transfer equationoptical tomography

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Numerical methods for inverse problems for boundary value problems involving PDEs (65N21) Inverse problems (including inverse scattering) in optics and electromagnetic theory (78A46) Radiative transfer in astronomy and astrophysics (85A25)

Abstract: This paper presents a neural network approach for solving two-dimensional optical tomography (OT) problems based on the radiative transfer equation. The mathematical problem of OT is to recover the optical properties of an object based on the albedo operator that is accessible from boundary measurements. Both the forward map from the optical properties to the albedo operator and the inverse map are high-dimensional and nonlinear. For the circular tomography geometry, a perturbative analysis shows that the forward map can be approximated by a vectorized convolution operator in the angular direction. Motivated by this, we propose effective neural network architectures for the forward and inverse maps based on convolution layers, with weights learned from training datasets. Numerical results demonstrate the efficiency of the proposed neural networks.

Recommendations

• Solving electrical impedance tomography with deep learning
• Solving traveltime tomography with deep learning
• Learn an index operator by CNN for solving diffusive optical tomography: a deep direct sampling method
• Solving inverse wave scattering with deep learning
• Solving ill-posed inverse problems using iterative deep neural networks

Cited in

(9)

• Solving traveltime tomography with deep learning
• Neural-network approach for optical tomography
• Solving inverse wave scattering with deep learning
• Solving electrical impedance tomography with deep learning
• Learnable Douglas-Rachford iteration and its applications in DOT imaging
• Online learning in optical tomography: a stochastic approach
• Dynamic Fourier ptychography with deep spatiotemporal priors
• Learn an index operator by CNN for solving diffusive optical tomography: a deep direct sampling method
• Deep neural networks for inverse problems with pseudodifferential operators: an application to limited-angle tomography

This page was built for publication: Solving optical tomography with deep learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2084728)