English

A Few-Shot Learning Approach for Accelerated MRI via Fusion of Data-Driven and Subject-Driven Priors

Computer Vision and Pattern Recognition 2021-03-16 v1 Image and Video Processing

Abstract

Deep neural networks (DNNs) have recently found emerging use in accelerated MRI reconstruction. DNNs typically learn data-driven priors from large datasets constituting pairs of undersampled and fully-sampled acquisitions. Acquiring such large datasets, however, might be impractical. To mitigate this limitation, we propose a few-shot learning approach for accelerated MRI that merges subject-driven priors obtained via physical signal models with data-driven priors obtained from a few training samples. Demonstrations on brain MR images from the NYU fastMRI dataset indicate that the proposed approach requires just a few samples to outperform traditional parallel imaging and DNN algorithms.

Keywords

Cite

@article{arxiv.2103.07790,
  title  = {A Few-Shot Learning Approach for Accelerated MRI via Fusion of Data-Driven and Subject-Driven Priors},
  author = {Salman Ul Hassan Dar and Mahmut Yurt and Tolga Çukur},
  journal= {arXiv preprint arXiv:2103.07790},
  year   = {2021}
}

Comments

Accepted for presentation at the 29th Annual Meeting of the International Society of Magnetic Resonance in Medicine (ISMRM)