Deep Convolutional Neural Network for Low Projection SPECT Imaging Reconstruction

TL;DR

This paper introduces a deep CNN-based method for reconstructing SPECT images from limited projection data, demonstrating improved image quality over traditional algorithms using both simulated and hardware phantoms.

Contribution

The paper presents a novel deep learning approach for low-projection SPECT image reconstruction, outperforming conventional methods like MLEM.

Findings

CNN-based reconstruction yields higher image quality.

Method effective with both software and hardware phantoms.

Outperforms traditional MLEM in tests.

Abstract

In this paper, we present a novel method for tomographic image reconstruction in SPECT imaging with a low number of projections. Deep convolutional neural networks (CNN) are employed in the new reconstruction method. Projection data from software phantoms were used to train the CNN network. For evaluation of the efficacy of the proposed method, software phantoms and hardware phantoms based on the FOV SPECT system were used. The resulting tomographic images are compared to those produced by the "Maximum Likelihood Expectation Maximisation" (MLEM).