Fast deep learning based reconstruction for limited angle tomography

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Salomonsson, Knut, Oldgren, Eric, Ström, Emanuel, Öktem, Ozan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916131454844928
author Salomonsson, Knut
Oldgren, Eric
Ström, Emanuel
Öktem, Ozan
author_facet Salomonsson, Knut
Oldgren, Eric
Ström, Emanuel
Öktem, Ozan
contents A major challenge in computed tomography is reconstructing objects from incomplete data. An increasingly popular solution for these problems is to incorporate deep learning models into reconstruction algorithms. This study introduces a novel approach by integrating a Fourier neural operator (FNO) into the Filtered Backprojection (FBP) reconstruction method, yielding the FNO back projection (FNO-BP) network. We employ moment conditions for sinogram extrapolation to assist the model in mitigating artefacts from limited data. Notably, our deep learning architecture maintains a runtime comparable to classical filtered back projection (FBP) reconstructions, ensuring swift performance during both inference and training. We assess our reconstruction method in the context of the Helsinki Tomography Challenge 2022 and also compare it against regular FBP methods.
format Preprint
id arxiv_https___arxiv_org_abs_2402_12141
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Fast deep learning based reconstruction for limited angle tomography
Salomonsson, Knut
Oldgren, Eric
Ström, Emanuel
Öktem, Ozan
Numerical Analysis
A major challenge in computed tomography is reconstructing objects from incomplete data. An increasingly popular solution for these problems is to incorporate deep learning models into reconstruction algorithms. This study introduces a novel approach by integrating a Fourier neural operator (FNO) into the Filtered Backprojection (FBP) reconstruction method, yielding the FNO back projection (FNO-BP) network. We employ moment conditions for sinogram extrapolation to assist the model in mitigating artefacts from limited data. Notably, our deep learning architecture maintains a runtime comparable to classical filtered back projection (FBP) reconstructions, ensuring swift performance during both inference and training. We assess our reconstruction method in the context of the Helsinki Tomography Challenge 2022 and also compare it against regular FBP methods.
title Fast deep learning based reconstruction for limited angle tomography
topic Numerical Analysis
url https://arxiv.org/abs/2402.12141