Artifacts and quantitative biases in neutron tomography introduced by systematic and random errors

Abstract

Systematic and random errors are often introduced in white-beam neutron Computed Tomography (CT) due to the nature of the neutron source, neutron-matter interactions or limitations in hardware. These errors can cause bias in measured linear attenuation coefficients (LACs) and artifacts in the reconstructed images, reducing image quality and impeding quantitative analysis. Three sources of error in neutron tomography were investigated and quantified that are particularly pertinent to spallation source facilities. These include detector to sample stage misalignment, beam fluctuations and undersampling due to missing CT projections. Quantitative analyses of the grayscale biases and misalignment artifacts were performed on the reconstructed data using ImageJ. Furthermore, the efficacy of classical iterative reconstruction algorithms for the suppression of missing projection artifacts was explored. Several image qualifying metrics were used to compare Filtered Back Projection (FBP) and iterative algorithms quantitatively. We show that beam intensity fluctuations if left uncorrected provide a minimal bias even when exaggerated across a stack of projections. In addition, detector-sample stage misalignment causes a geometrical misalignment blur when not corrected for and severe ring artifacts despite image rotation correction. We suggest that iterative algorithms are more favourable in suppressing missing projection neutron artifacts, however they inaccurately reproduce the LACs for missing-wedge reconstructions compared to FBP.