Deep learning for undersampled MRI reconstruction

Chang Min Hyun, Hwa Pyung Kim, Sung Min Lee, Sungchul Lee, Jin Keun Seo

Research output: Contribution to journalArticlepeer-review

263 Citations (Scopus)


This paper presents a deep learning method for faster magnetic resonance imaging (MRI) by reducing k-space data with sub-Nyquist sampling strategies and provides a rationale for why the proposed approach works well. Uniform subsampling is used in the time-consuming phase-encoding direction to capture high-resolution image information, while permitting the image-folding problem dictated by the Poisson summation formula. To deal with the localization uncertainty due to image folding, a small number of low-frequency k-space data are added. Training the deep learning net involves input and output images that are pairs of the Fourier transforms of the subsampled and fully sampled k-space data. Our experiments show the remarkable performance of the proposed method; only 29 of the k-space data can generate images of high quality as effectively as standard MRI reconstruction with the fully sampled data.

Original languageEnglish
Article number135007
JournalPhysics in medicine and biology
Issue number13
Publication statusPublished - 2018 Jun 25

Bibliographical note

Funding Information:
This research was supported by the National Research Foundation of Korea No. NRF-2017R1A2B20005661. Hyun, Lee and Seo were supported by Samsung Science &; Technology Foundation (No. SSTF-BA1402-01).

Publisher Copyright:
© 2018 Institute of Physics and Engineering in Medicine.

All Science Journal Classification (ASJC) codes

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging


Dive into the research topics of 'Deep learning for undersampled MRI reconstruction'. Together they form a unique fingerprint.

Cite this