Complementary time-frequency domain networks for dynamic parallel MR image reconstruction.

Chen Qin^1,2, Jinming Duan³, Kerstin Hammernik^2,4, Jo Schlemper^2,5, Thomas Küstner^6,7, René Botnar⁶, Claudia Prieto⁶, Anthony N Price⁶, Joseph V Hajnal⁶, Daniel Rueckert^2,4

¹Institute for Digital Communications, School of Engineering, University of Edinburgh, Edinburgh, UK.

²Department of Computing, Imperial College London, London, UK.

³School of Computer Science, University of Birmingham, Birmingham, UK.

⁴Institute for AI and Informatics, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany.

⁵Hyperfine Research Inc., Guilford, CT, USA.

⁶School of Biomedical Engineering and Imaging Sciences, King's College London, London, UK.

⁷Department of Diagnostic and Interventional Radiology, Medical Image and Data Analysis, University Hospital of Tuebingen, Tuebingen, Germany.

PubMed DOI

Abstract

PURPOSE: To introduce a novel deep learning-based approach for fast and high-quality dynamic multicoil MR reconstruction by learning a complementary time-frequency domain network that exploits spatiotemporal correlations simultaneously from complementary domains. THEORY AND METHODS: Dynamic parallel MR image reconstruction is formulated as a multivariable minimization problem, where the data are…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free Account Sign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.