Deblurring for Spiral Real-Time MRI Using Convolutional Neural Networks
Abstract
Spiral acquisitions are preferred in real-time MRI because of their time efficiency. A fundamental limitation of spirals is image blurring due to off-resonance, which degrades image quality significantly at air-tissue boundaries. Here, we demonstrate a simple CNN-based deblurring method for spiral real-time MRI of human speech production. We show the CNN-based deblurring is capable of restoring blurred vocal tract tissue boundaries, without a need for exam-specific field maps. Deblurring performance is superior to a current auto-calibrated method, and slightly inferior to ideal reconstruction with perfect knowledge of the field maps.
Cite
@article{arxiv.2001.09427,
title = {Deblurring for Spiral Real-Time MRI Using Convolutional Neural Networks},
author = {Yongwan Lim and Shrikanth S Narayanan and Krishna S Nayak},
journal= {arXiv preprint arXiv:2001.09427},
year = {2020}
}
Comments
Presented at International Conference on Medical Imaging with Deep Learning (MIDL 2020) (A short conference paper of the full journal paper in the earlier submission version)