Probabilistic approach to limited-data computed tomography reconstruction

TL;DR

This paper introduces a Gaussian process-based method for limited-data CT reconstruction that automatically tunes parameters and reduces artifacts, outperforming traditional techniques in simulated and real scenarios.

Contribution

It presents a novel Gaussian process approach that eliminates manual parameter tuning and improves artifact suppression in limited-data CT reconstruction.

Findings

Reduces streak artifacts compared to filtered backprojection.

Automatically estimates hyperparameters from data.

Efficiently reformulates classical regularization as Gaussian process regression.

Abstract

In this work, we consider the inverse problem of reconstructing the internal structure of an object from limited x-ray projections. We use a Gaussian process prior to model the target function and estimate its (hyper)parameters from measured data. In contrast to other established methods, this comes with the advantage of not requiring any manual parameter tuning, which usually arises in classical regularization strategies. Our method uses a basis function expansion technique for the Gaussian process which significantly reduces the computational complexity and avoids the need for numerical integration. The approach also allows for reformulation of come classical regularization methods as Laplacian and Tikhonov regularization as Gaussian process regression, and hence provides an efficient algorithm and principled means for their parameter tuning. Results from simulated and real data indicate that this approach is less sensitive to streak artifacts as compared to the commonly used method of filtered backprojection.