CG-3DSRGAN: A classification guided 3D generative adversarial network for image quality recovery from low-dose PET images

TL;DR

This paper introduces CG-3DSRGAN, a novel classification-guided 3D GAN that enhances low-dose PET image quality by understanding noise levels and applying super resolution, outperforming existing methods across various dose reductions.

Contribution

The paper proposes a new multi-tasking GAN with classification guidance and a super resolution refinement stage for improved low-dose PET image synthesis.

Findings

Outperforms state-of-the-art methods across all dose reduction factors

Effectively captures noise-level features for better image reconstruction

Enhances spatial details in low-dose PET images

Abstract

Positron emission tomography (PET) is the most sensitive molecular imaging modality routinely applied in our modern healthcare. High radioactivity caused by the injected tracer dose is a major concern in PET imaging and limits its clinical applications. However, reducing the dose leads to inadequate image quality for diagnostic practice. Motivated by the need to produce high quality images with minimum low-dose, Convolutional Neural Networks (CNNs) based methods have been developed for high quality PET synthesis from its low-dose counterparts. Previous CNNs-based studies usually directly map low-dose PET into features space without consideration of different dose reduction level. In this study, a novel approach named CG-3DSRGAN (Classification-Guided Generative Adversarial Network with Super Resolution Refinement) is presented. Specifically, a multi-tasking coarse generator, guided by a classification head, allows for a more comprehensive understanding of the noise-level features present in the low-dose data, resulting in improved image synthesis. Moreover, to recover spatial details of standard PET, an auxiliary super resolution network - Contextual-Net - is proposed as a second-stage training to narrow the gap between coarse prediction and standard PET. We compared our method to the state-of-the-art methods on whole-body PET with different dose reduction factors (DRFs). Experiments demonstrate our method can outperform others on all DRF.