Deep Microlocal Reconstruction for Limited-Angle Tomography

DOI10.1016/J.ACHA.2021.12.007MaRDI QIDQ6375076arXivFDO

Authors Héctor Andrade-Loarca, Gitta Kutyniok, Ozan Öktem, Philipp Petersen

Publication date 12 August 2021

Published in arXiv

Full work available at URL https://doi.org/10.1016/J.ACHA.2021.12.007

Mathematics Subject Classification ID

Wave front sets in context of PDEs (35A18) Numerical analysis (65-XX) Numerical methods for wavelets (65T60) Pattern recognition, speech recognition (68T10)

arXiv classification

cs.CVcs.LGcs.NAmath.FAmath.NA

Abstract: We present a deep learning-based algorithm to jointly solve a reconstruction problem and a wavefront set extraction problem in tomographic imaging. The algorithm is based on a recently developed digital wavefront set extractor as well as the well-known microlocal canonical relation for the Radon transform. We use the wavefront set information about x-ray data to improve the reconstruction by requiring that the underlying neural networks simultaneously extract the correct ground truth wavefront set and ground truth image. As a necessary theoretical step, we identify the digital microlocal canonical relations for deep convolutional residual neural networks. We find strong numerical evidence for the effectiveness of this approach.

This page was built for publication: Deep Microlocal Reconstruction for Limited-Angle Tomography

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6375076)