A Data-Driven Reconstruction Technique based on Newton's Method for Emission Tomography

TL;DR

This paper introduces DNR-Net, a hybrid deep learning and Newton's method-based reconstruction technique for emission tomography that achieves high-quality images with less noise and higher contrast than traditional methods.

Contribution

The paper presents a novel hybrid data-driven reconstruction network inspired by Newton's method, combining deep learning with prior projection information for emission tomography.

Findings

DNR-Net achieves high-quality reconstructions comparable to OSEM.

DNR-Net produces images with higher contrast and less noise.

Quantitative metrics show improved image quality over traditional methods.

Abstract

In this work, we present the Deep Newton Reconstruction Network (DNR-Net), a hybrid data-driven reconstruction technique for emission tomography inspired by Newton's method, a well-known iterative optimization algorithm. The DNR-Net employs prior information about the tomographic problem provided by the projection operator while utilizing deep learning approaches to a) imitate Newton's method by approximating the Newton descent direction and b) provide data-driven regularisation. We demonstrate that DNR-Net is capable of providing high-quality image reconstructions using data from SPECT phantom simulations by applying it to reconstruct images from noisy sinograms, each one containing 24 projections. The Structural Similarity Index (SSIM) and the Contrast-to-Noise ratio (CNR) were used to quantify the image quality. We also compare our results to those obtained by the OSEM method. According to the quantitative results, the DNR-Net produces reconstructions comparable to the ones produced by OSEM while featuring higher contrast and less noise.