Fast deep learning based reconstruction for limited angle tomography

TL;DR

This paper presents a fast deep learning-based reconstruction method for limited angle tomography by integrating a Fourier neural operator into the FBP algorithm, effectively reducing artefacts while maintaining rapid processing speeds.

Contribution

Introduces the FNO-BP network that combines Fourier neural operators with FBP, utilizing moment conditions for sinogram extrapolation to improve limited data reconstructions.

Findings

Achieves artefact reduction comparable to advanced methods.

Maintains classical FBP runtime during inference and training.

Performs well in the Helsinki Tomography Challenge 2022.

Abstract

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.