Institute Homepage
Institute Homepage DE Sign In

Back

Miscellaneous 2019

deepCEST: 9.4 T spectral super resolution from 3 T CEST MRI data: optimization of network architectures

{Different neural network architectures for predicting 9T CEST contrasts from 3T spectral data are investigated as well as the influence of different training data sets on the quality of resulting predictions. Although optimized convolutional neural network (CNN) architectures perform well, the best results were reached with a simpler feedforward neural network (FFNN). As CNNs have many hyperparameters to tune, this work forms a basis for CNN architecture optimization for the proposed super-resolution CEST application.}

Author(s): Zaiss, M and Martin, F and Glang, F and Herz, K and Deshmane, A and Bender, B and Lindig, T and Scheffler, K
Book Title: ISMRM 27th Annual Meeting & Exhibition
Year: 2019
Bibtex Type: Miscellaneous (misc)
Electronic Archiving: grant_archive

BibTex 

@misc{item_3054622,
  title = {{deepCEST: 9.4 T spectral super resolution from 3 T CEST MRI data: optimization of network architectures}},
  booktitle = {{ISMRM 27th Annual Meeting \& Exhibition}},
  abstract = {{Different neural network architectures for predicting 9T CEST contrasts from 3T spectral data are investigated as well as the influence of different training data sets on the quality of resulting predictions. Although optimized convolutional neural network (CNN) architectures perform well, the best results were reached with a simpler feedforward neural network (FFNN). As CNNs have many hyperparameters to tune, this work forms a basis for CNN architecture optimization for the proposed super-resolution CEST application.}},
  year = {2019},
  slug = {item_3054622},
  author = {Zaiss, M and Martin, F and Glang, F and Herz, K and Deshmane, A and Bender, B and Lindig, T and Scheffler, K}
}