Deep Neural Networks for Inverse Problems with Pseudodifferential Operators: An Application to Limited-Angle Tomography

DOI10.1137/20M1343075zbMath1489.44003arXiv2006.01620MaRDI QIDQ5860291

Matti Lassas, Samuli Siltanen, Luca Ratti, Marco Prato, Tatiana A. Bubba, Mathilde Galinier

Publication date: 19 November 2021

Published in: SIAM Journal on Imaging Sciences (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2006.01620

zbMATH Keywords

wavelets; pseudodifferential operators; Fourier integral operators; microlocal analysis; X-ray transform; sparse regularization; convolutional neural networks; deep neural networks; limited-angle tomography

Mathematics Subject Classification ID

68T07: Artificial neural networks and deep learning

92C55: Biomedical imaging and signal processing

44A12: Radon transform

58J40: Pseudodifferential and Fourier integral operators on manifolds

35S30: Fourier integral operators applied to PDEs

Uses Software

• scikit-image
• ASTRA
• Adam
• ODL
• GitHub
• PyWavelets
• tfwavelets
• ISTA-Net
• DeepAdverserialRegulariser