Sparse-View CT Reconstruction using Recurrent Stacked Back Projection

TL;DR

This paper introduces RSBP, a novel deep neural network method for direct sparse-view CT reconstruction that leverages sequential backprojections and recurrent processing to improve image quality efficiently.

Contribution

The paper presents RSBP, a new recurrent neural network architecture that directly reconstructs CT images from sparse-view data using sequential backprojection inputs.

Findings

RSBP outperforms DNN post-processing methods in image quality.

RSBP achieves comparable results to MBIR with lower computational cost.

Validated on both simulated and real data.

Abstract

Sparse-view CT reconstruction is important in a wide range of applications due to limitations on cost, acquisition time, or dosage. However, traditional direct reconstruction methods such as filtered back-projection (FBP) lead to low-quality reconstructions in the sub-Nyquist regime. In contrast, deep neural networks (DNNs) can produce high-quality reconstructions from sparse and noisy data, e.g. through post-processing of FBP reconstructions, as can model-based iterative reconstruction (MBIR), albeit at a higher computational cost. In this paper, we introduce a direct-reconstruction DNN method called Recurrent Stacked Back Projection (RSBP) that uses sequentially-acquired backprojections of individual views as input to a recurrent convolutional LSTM network. The SBP structure maintains all information in the sinogram, while the recurrent processing exploits the correlations between adjacent views and produces an updated reconstruction after each new view. We train our network on simulated data and test on both simulated and real data and demonstrate that RSBP outperforms both DNN post-processing of FBP images and basic MBIR, with a lower computational cost than MBIR.