Learning Sampling and Model-Based Signal Recovery for Compressed Sensing MRI

Iris Huijben, Bastiaan S. Veeling, Ruud J.G. van Sloun

Research output: Contribution to conferencePaperAcademic

1 Citation (Scopus)
6 Downloads (Pure)

Abstract

Compressed sensing (CS) MRI relies on adequate undersampling of the k-space to accelerate the acquisition without compromising image quality. Consequently, the design of optimal sampling patterns for these k-space coefficients has received significant attention, with many CS MRI methods exploiting variable-density probability distributions. Realizing that an optimal sampling pattern may depend on the downstream task (e.g. image reconstruction, segmentation, or classification), we here propose joint learning of both task-adaptive k-space sampling and a subsequent model-based proximal-gradient recovery network. The former is enabled through a probabilistic generative model that leverages the Gumbel-softmax relaxation to sample across trainable beliefs while maintaining differentiability. The proposed combination of a highly flexible sampling model and a model-based (sampling-adaptive) image reconstruction network facilitates exploration and efficient training, yielding improved MR image quality compared to other sampling baselines.
Original languageEnglish
Pages8906-8910
Number of pages5
DOIs
Publication statusPublished - May 2020
Event2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) - Virtual, Barcelona, Spain
Duration: 4 May 20208 May 2020
Conference number: 2020
https://2020.ieeeicassp.org/

Conference

Conference2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Abbreviated titleICASSP
CountrySpain
CityBarcelona
Period4/05/208/05/20
Internet address

Keywords

  • Compressed sensing
  • magnetic resonance imaging
  • model-based deep learning

Fingerprint Dive into the research topics of 'Learning Sampling and Model-Based Signal Recovery for Compressed Sensing MRI'. Together they form a unique fingerprint.

Cite this