Scan-Specific Accelerated Mri Reconstruction Using Recurrent Neural Networks in A Regularized Self-Consistent Framework

Seyed Amir Hossein Hosseini, Burhaneddin Yaman, Chi Zhang, Kamil Ugurbil, Steen Moeller, Mehmet Akcakaya

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Long scan duration remains a challenge for high-resolution MRI. Several accelerated imaging strategies have been proposed based on deep learning (DL) that require databases of fully-sampled images for training. However, scan-specific training is desired where individual variability is important, e.g. in free-breathing cardiac MRI, or where such datasets are not available due to scan time constraints for acquiring fully-sampled data. Building on our earlier method called Self-consistent Robust Artificial-neural-networks for k-space Interpolation (sRAKI), we propose a scan-specific DL reconstruction method based on recurrent neural networks that combines training and reconstruction phases of sRAKI. We use self-consistency among coils in k-space and regularization in arbitrary domains, as well as consistency with acquired data, in each iteration of the recurrent network. Results on knee MRI show that this method improves upon parallel imaging and compressed sensing methods.

Original languageEnglish (US)
Title of host publicationISBI Workshops 2020 - International Symposium on Biomedical Imaging Workshops, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728174013
DOIs
StatePublished - Apr 2020
Event17th IEEE International Symposium on Biomedical Imaging Workshops, ISBI Workshops 2020 - Iowa City, United States
Duration: Apr 4 2020 → …

Publication series

NameISBI Workshops 2020 - International Symposium on Biomedical Imaging Workshops, Proceedings

Conference

Conference17th IEEE International Symposium on Biomedical Imaging Workshops, ISBI Workshops 2020
CountryUnited States
CityIowa City
Period4/4/20 → …

Keywords

  • compressed sensing
  • deep learning
  • image reconstruction.
  • machine learning
  • neural networks
  • Parallel imaging

Fingerprint Dive into the research topics of 'Scan-Specific Accelerated Mri Reconstruction Using Recurrent Neural Networks in A Regularized Self-Consistent Framework'. Together they form a unique fingerprint.

Cite this