Quasi-supervised Learning for Super-resolution PET

1 code implementation • 3 Sep 2022 • Guangtong Yang, Chen Li, YuDong Yao, Ge Wang, Yueyang Teng

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.

Generative Adversarial Network Super-Resolution +1