Joint Rigid Motion Correction and Sparse-View CT via Self-Calibrating Neural Field

TL;DR

This paper introduces a self-calibrating neural field approach for sparse-view CT reconstruction that jointly corrects rigid motion artifacts and reconstructs high-quality images without external data, outperforming existing NeRF-based methods.

Contribution

The method jointly optimizes projection poses and image reconstruction in NeRF-based SVCT, enabling motion correction without external data or perfect pose information.

Findings

Significantly outperforms existing NeRF-based SVCT methods under motion.

Effectively recovers artifact-free images from motion-corrupted sinograms.

Robust across multiple levels of rigid motion in numerical experiments.

Abstract

Neural Radiance Field (NeRF) has widely received attention in Sparse-View Computed Tomography (SVCT) reconstruction tasks as a self-supervised deep learning framework. NeRF-based SVCT methods represent the desired CT image as a continuous function of spatial coordinates and train a Multi-Layer Perceptron (MLP) to learn the function by minimizing loss on the SV sinogram. Benefiting from the continuous representation provided by NeRF, the high-quality CT image can be reconstructed. However, existing NeRF-based SVCT methods strictly suppose there is completely no relative motion during the CT acquisition because they require \textit{accurate} projection poses to model the X-rays that scan the SV sinogram. Therefore, these methods suffer from severe performance drops for real SVCT imaging with motion. In this work, we propose a self-calibrating neural field to recover the artifacts-free image from the rigid motion-corrupted SV sinogram without using any external data. Specifically, we parametrize the inaccurate projection poses caused by rigid motion as trainable variables and then jointly optimize these pose variables and the MLP. We conduct numerical experiments on a public CT image dataset. The results indicate our model significantly outperforms two representative NeRF-based methods for SVCT reconstruction tasks with four different levels of rigid motion.