Deep Back Projection for Sparse-View CT Reconstruction

TL;DR

This paper introduces a deep learning approach that enhances sparse-view CT reconstruction by using a novel back projection method combined with CNNs, outperforming classical FBP in quality.

Contribution

It proposes a new deep CNN-based back projection technique that improves sparse-view CT image quality over traditional filtered back projection methods.

Findings

CNN-based back projection yields higher quality reconstructions.

The method outperforms classical FBP in simulated sparse-view CT data.

Single-view back projections effectively leverage CNN spatial invariance.

Abstract

Filtered back projection (FBP) is a classical method for image reconstruction from sinogram CT data. FBP is computationally efficient but produces lower quality reconstructions than more sophisticated iterative methods, particularly when the number of views is lower than the number required by the Nyquist rate. In this paper, we use a deep convolutional neural network (CNN) to produce high-quality reconstructions directly from sinogram data. A primary novelty of our approach is that we first back project each view separately to form a stack of back projections and then feed this stack as input into the convolutional neural network. These single-view back projections convert the encoding of sinogram data into the appropriate spatial location, which can then be leveraged by the spatial invariance of the CNN to learn the reconstruction effectively. We demonstrate the benefit of our CNN based back projection on simulated sparse-view CT data over classical FBP.