Properties of 2D MR image reconstructions with deep neural networks at high acceleration rates

Matthew J. Muckley, Tullie Murrell, Alireza Radmanesh, Florian Knöll, Zhengnan Huang, Anuroop Sriram, Daniel K. Sodickson, Yvonne W. LuiProceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition 2023 · DOI

Abstract

We assess the properties of deep neural network-reconstructed brain MR images in the high acceleration regime at factors up to 100. We have three contributions: 1) metrics on model performance from 2- to 100-fold accelerations, 2) a Monte Carlo procedure for scoring the quality of model reconstructions using only subsampled data, and 3) assessment of the acceleration effects on pathology in six cases. Our Monte Carlo procedure can estimate ground truth PSNR with coefficients of determination greater than 0.5 using only subsampled data. Our pathology results were stable in DNN reconstructions up to 8-fold acceleration.
BibTeX
@inproceedings{muckley2023properties,
  author = {Matthew J. Muckley and Tullie Murrell and Alireza Radmanesh and Florian Knöll and Zhengnan Huang and Anuroop Sriram and Daniel K. Sodickson and Yvonne W. Lui},
  title = {{Properties of 2D MR image reconstructions with deep neural networks at high acceleration rates}},
  booktitle = {Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition},
  year = {2023},
  doi = {10.58530/2022/0849},
}

Loading related content...

Figure