Multi-Scale Learned Iterative Reconstruction

TL;DR

This paper introduces a multi-scale learned iterative reconstruction method that enhances scalability and efficiency for large-scale 3D inverse problems like cone beam CT, reducing memory use and training time.

Contribution

It proposes a hybrid multi-scale iterative scheme combined with an expressive network architecture, enabling scalable 3D reconstruction in practical applications.

Findings

Effective in 3D cone beam CT reconstruction from real data

Significantly reduces memory and training time

Outperforms existing learned methods in scalability and quality

Abstract

Model-based learned iterative reconstruction methods have recently been shown to outperform classical reconstruction algorithms. Applicability of these methods to large scale inverse problems is however limited by the available memory for training and extensive training times, the latter due to computationally expensive forward models. As a possible solution to these restrictions we propose a multi-scale learned iterative reconstruction scheme that computes iterates on discretisations of increasing resolution. This procedure does not only reduce memory requirements, it also considerably speeds up reconstruction and training times, but most importantly is scalable to large scale inverse problems with non-trivial forward operators, such as those that arise in many 3D tomographic applications. In particular, we propose a hybrid network that combines the multi-scale iterative approach with a particularly expressive network architecture which in combination exhibits excellent scalability in 3D. Applicability of the algorithm is demonstrated for 3D cone beam computed tomography from real measurement data of an organic phantom. Additionally, we examine scalability and reconstruction quality in comparison to established learned reconstruction methods in two dimensions for low dose computed tomography on human phantoms.