A three-dimensional dual-domain deep network for high-pitch and sparse helical CT reconstruction

TL;DR

This paper introduces a novel deep learning approach for high-pitch, sparse helical CT reconstruction that leverages a GPU-optimized Katsevich algorithm, effectively reducing artifacts and preserving image details.

Contribution

It presents a new GPU implementation of the Katsevich algorithm integrated into an end-to-end deep network for improved helical CT reconstruction with sparse data.

Findings

Outperforms existing methods in subjective image quality

Effectively reduces streak artifacts from sparse sinograms

Preserves fine details in reconstructed CT images

Abstract

In this paper, we propose a new GPU implementation of the Katsevich algorithm for helical CT reconstruction. Our implementation divides the sinograms and reconstructs the CT images pitch by pitch. By utilizing the periodic properties of the parameters of the Katsevich algorithm, our method only needs to calculate these parameters once for all the pitches and so has lower GPU-memory burdens and is very suitable for deep learning. By embedding our implementation into the network, we propose an end-to-end deep network for the high pitch helical CT reconstruction with sparse detectors. Since our network utilizes the features extracted from both sinograms and CT images, it can simultaneously reduce the streak artifacts caused by the sparsity of sinograms and preserve fine details in the CT images. Experiments show that our network outperforms the related methods both in subjective and objective evaluations.