Multi-Slice Fusion for Sparse-View and Limited-Angle 4D CT Reconstruction

TL;DR

This paper introduces multi-slice fusion, a novel 4D CT reconstruction method that combines multiple low-dimensional denoisers within a multi-agent consensus framework, improving quality for sparse-view and limited-angle data.

Contribution

The paper proposes a new multi-slice fusion algorithm based on multi-agent consensus equilibrium to enhance 4D reconstruction by integrating lower-dimensional denoisers, addressing high-dimensional denoising challenges.

Findings

Significantly improves 4D CT reconstruction quality over traditional methods.

Demonstrates effective parallel implementation on distributed clusters.

Validates performance with simulated and real sparse-view and limited-angle data.

Abstract

Inverse problems spanning four or more dimensions such as space, time and other independent parameters have become increasingly important. State-of-the-art 4D reconstruction methods use model based iterative reconstruction (MBIR), but depend critically on the quality of the prior modeling. Recently, plug-and-play (PnP) methods have been shown to be an effective way to incorporate advanced prior models using state-of-the-art denoising algorithms. However, state-of-the-art denoisers such as BM4D and deep convolutional neural networks (CNNs) are primarily available for 2D or 3D images and extending them to higher dimensions is difficult due to algorithmic complexity and the increased difficulty of effective training. In this paper, we present multi-slice fusion, a novel algorithm for 4D reconstruction, based on the fusion of multiple low-dimensional denoisers. Our approach uses multi-agent consensus equilibrium (MACE), an extension of plug-and-play, as a framework for integrating the multiple lower-dimensional models. We apply our method to 4D cone-beam X-ray CT reconstruction for non destructive evaluation (NDE) of samples that are dynamically moving during acquisition. We implement multi-slice fusion on distributed, heterogeneous clusters in order to reconstruct large 4D volumes in reasonable time and demonstrate the inherent parallelizable nature of the algorithm. We present simulated and real experimental results on sparse-view and limited-angle CT data to demonstrate that multi-slice fusion can substantially improve the quality of reconstructions relative to traditional methods, while also being practical to implement and train.