To Recurse or not to Recurse,a Low Dose CT Study

TL;DR

This paper explores the use of Recurrent Neural Networks for enhancing low dose CT images, showing improved performance over feedforward networks in high noise scenarios and comparing their computational costs.

Contribution

It introduces a framework utilizing RNNs for streak artifact removal in low dose CT imaging, highlighting their advantages over traditional feedforward networks in noisy conditions.

Findings

RNN achieves comparable results to feedforward networks in low noise.

RNN outperforms feedforward networks in high noise conditions.

RNN has different computational costs compared to feedforward networks.

Abstract

Restoring high-quality CT images from low dose CT counterparts is an ill-posed, nonlinear problem to which Deep Learning approaches have been giving superior solutions compared to classical model-based approaches. In this article, a framework is presented wherein a Recurrent Neural Network (RNN) is utilized to remove the streaking artefacts from low projection number CT imaging. The results indicate similar image restoration performance for the RNN compared to the feedforward network in low noise cases while in high noise levels the RNN returns better results. The computational costs are also compared between RNN and feedforward networks.