A Few-Shot Learning Approach for Accelerated MRI via Fusion of Data-Driven and Subject-Driven Priors
This work addresses the challenge of acquiring large datasets for deep learning in medical imaging, offering a more practical solution for MRI reconstruction.
The paper tackled the problem of accelerated MRI reconstruction by proposing a few-shot learning approach that combines subject-driven priors from physical models with data-driven priors from limited training samples, achieving results that outperform traditional parallel imaging and DNN algorithms with just a few samples.
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.