MRI super-resolution via realistic downsampling with adversarial learning

Bangyan Huang, Haonan Xiao, Weiwei Liu, Yibao Zhang, Hao Wu, Weihu Wang, Yunhuan Yang, Yidong Yang, G. Wilson Miller, Tian Li, Jing Cai

Research output: Journal article publicationJournal articleAcademic researchpeer-review

11 Citations (Scopus)


Many deep learning (DL) frameworks have demonstrated state-of-the-art performance in the super-resolution (SR) task of magnetic resonance imaging, but most performances have been achieved with simulated low-resolution (LR) images rather than LR images from real acquisition. Due to the limited generalizability of the SR network, enhancement is not guaranteed for real LR images because of the unreality of the training LR images. In this study, we proposed a DL-based SR framework with an emphasis on data construction to achieve better performance on real LR MR images. The framework comprised two steps: (a) downsampling training using a generative adversarial network (GAN) to construct more realistic and perfectly matched LR/high-resolution (HR) pairs. The downsampling GAN input was real LR and HR images. The generator translated the HR images to LR images and the discriminator distinguished the patch-level difference between the synthetic and real LR images. (b) SR training was performed using an enhance4d deep super-resolution network (EDSR). In the controlled experiments, three EDSRs were trained using our proposed method, Gaussian blur, and k-space zero-filling. As for the data, liver MR images were obtained from 24 patients using breath-hold serial LR and HR scans (only HR images were used in the conventional methods). The k-space zero-filling group delivered almost zero enhancement on the real LR images and the Gaussian group produced a considerable number of artifacts. The proposed method exhibited significantly better resolution enhancement and fewer artifacts compared with the other two networks. Our method outperformed the Gaussian method by an improvement of 0.111 0.016 in the structural similarity index and 2.76 0.98 dB in the peak signal-to-noise ratio. The blind/reference-less image spatial quality evaluator metric of the conventional Gaussian method and proposed method were 46.6 4.2 and 34.1 2.4, respectively.

Original languageEnglish
Article number205004
JournalPhysics in Medicine and Biology
Issue number20
Publication statusPublished - 21 Oct 2021

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging


Dive into the research topics of 'MRI super-resolution via realistic downsampling with adversarial learning'. Together they form a unique fingerprint.

Cite this