Primal-Dual UNet for Sparse View Cone Beam Computed Tomography Volume Reconstruction

TL;DR

This paper introduces a modified Primal-Dual UNet for sparse view cone beam CT volume reconstruction, demonstrating significant PSNR improvements over traditional methods with a proof-of-concept approach.

Contribution

It adapts the Primal-Dual UNet to 3D cone beam CT, enabling volume reconstruction from sparse projections, which was not previously demonstrated.

Findings

PSNR increased by 10dB over FDK reconstruction.

Almost 3dB PSNR improvement over original Primal-Dual Network.

Method serves as a proof of concept for low-resolution volume reconstruction.

Abstract

In this paper, the Primal-Dual UNet for sparse view CT reconstruction is modified to be applicable to cone beam projections and perform reconstructions of entire volumes instead of slices. Experiments show that the PSNR of the proposed method is increased by 10dB compared to the direct FDK reconstruction and almost 3dB compared to the modified original Primal-Dual Network when using only 23 projections. The presented network is not optimized wrt. memory consumption or hyperparameters but merely serves as a proof of concept and is limited to low resolution projections and volumes.