Quasi-supervised Learning for Super-resolution PET

TL;DR

This paper introduces a quasi-supervised learning approach for super-resolution PET imaging that leverages unpaired image patches, improving upon existing supervised and unsupervised methods by using similarity-based patch matching.

Contribution

It proposes a novel weakly-supervised learning method that utilizes similarity between unpaired patches to enhance super-resolution PET, modifying CycleGAN for this purpose.

Findings

Outperforms state-of-the-art super-resolution methods

Qualitative and quantitative improvements demonstrated

Code is publicly available for reproducibility

Abstract

Low resolution of positron emission tomography (PET) limits its diagnostic performance. Deep learning has been successfully applied to achieve super-resolution PET. However, commonly used supervised learning methods in this context require many pairs of low- and high-resolution (LR and HR) PET images. Although unsupervised learning utilizes unpaired images, the results are not as good as that obtained with supervised deep learning. In this paper, we propose a quasi-supervised learning method, which is a new type of weakly-supervised learning methods, to recover HR PET images from LR counterparts by leveraging similarity between unpaired LR and HR image patches. Specifically, LR image patches are taken from a patient as inputs, while the most similar HR patches from other patients are found as labels. The similarity between the matched HR and LR patches serves as a prior for network construction. Our proposed method can be implemented by designing a new network or modifying an existing network. As an example in this study, we have modified the cycle-consistent generative adversarial network (CycleGAN) for super-resolution PET. Our numerical and experimental results qualitatively and quantitatively show the merits of our method relative to the state-ofthe-art methods. The code is publicly available at https://github.com/PigYang-ops/CycleGAN-QSDL.