NEWTON-KRYLOV METHODS FOR POLYCHROMATIC X-RAY CT

Abstract

Most lab-based X-ray sources are polychromatic, making the acquisition follow a non-linear model. However, widespread reconstruction algorithms, such as FBP and SIRT, assume the reconstruction to be a linear problem, leading to artefacts in the reconstructions. We propose a non-linear optimization technique, Newton-Krylov, to minimize a polychromatic objective function instead. The objective function can also easily be extended with regularisation terms, in a mathematically sound framework. Results on Monte-Carlo simulated projection data show a lower error in the data fidelity term, as well as improved reconstruction quality.