Institute Homepage
Institute Homepage DE Sign In

Back

Miscellaneous 2021

MRzero with dAUTOMAP reconstruction: automated invention of MR acquisition and neural network reconstruction

{We present an end-to-end optimized T1 mapping utilizing MRzero - a fully differentiable Bloch-equation-based MRI sequence invention framework. A convolutional neural network is employed for combined image reconstruction and parameter mapping. The pipeline performs a joint optimization of sequence parameters and neural network parameters to create a full autoencoder for T1 mapping. We demonstrate for in vivo measurements at 3T, that the CNN based reconstruction and T1 mapping outperformes a conventional reconstruction with pixelwise neural network based T1 quantification.}

Author(s): Dang, HN and Weinmüller, S and Loktyushin, A and Glang, F and Dörfler, A and Maier, A and Schölkopf, B and Scheffler, K and Zaiss, M
Book Title: 2021 ISMRM & SMRT Annual Meeting & Exhibition (ISMRM 2021)
Year: 2021
Bibtex Type: Miscellaneous (misc)
Electronic Archiving: grant_archive

BibTex 

@misc{item_3320994,
  title = {{MRzero with dAUTOMAP reconstruction: automated invention of MR acquisition and neural network reconstruction}},
  booktitle = {{2021 ISMRM \& SMRT Annual Meeting \& Exhibition (ISMRM 2021)}},
  abstract = {{We present an end-to-end optimized T1 mapping utilizing MRzero - a fully differentiable Bloch-equation-based MRI sequence invention framework. A convolutional neural network is employed for combined image reconstruction and parameter mapping. The pipeline performs a joint optimization of sequence parameters and neural network parameters to create a full autoencoder for T1 mapping. We demonstrate for in vivo measurements at 3T, that the CNN based reconstruction and T1 mapping outperformes a conventional reconstruction with pixelwise neural network based T1 quantification.}},
  year = {2021},
  slug = {item_3320994},
  author = {Dang, HN and Weinm\"uller, S and Loktyushin, A and Glang, F and D\"orfler, A and Maier, A and Sch\"olkopf, B and Scheffler, K and Zaiss, M}
}