1451

View Abstract / View Presentation

DeepCEST: 7T Chemical exchange saturation transfer MRI contrast inferred from 3T data via deep learning with uncertainty quantification

Leonie E. Hunger¹, Alexander German¹, Felix Glang², Katrin M. Khakzar¹, Nam Dang¹, Angelika Mennecke¹, Andreas Maier³, Frederik Laun⁴, and Moritz Zaiss^1,2
¹Department of Neuroradiology, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany, ²High-field Magnetic Resonance Center, Max Planck Institute for Biological Cybernetics, Tübingen, Germany, ³Pattern Recognition Lab, Friedrich-Alexander-University Erlangen-Nürnberg, Erlangen, Germany, ⁴Institute of Radiology, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany

The deepCEST approach enables to perform a CEST experiment at 3T and predict the contrasts of a CEST experiment at 7T with a neural network, including an uncertainty quantification.

Figure 2: DeepCEST network trained on healthy volunteers applied on a healty volunteer (a) Comparison of the predictions and the Lorentzian fit amplitudes (ground truth). (b) Error of the prediction compared to the fit. (c) Uncertainty of the prediction.

Figure 1: a) Input data: uncorrected Z-spectra of two B₁ levels acquired at 3T. b) Target data: 5-pool-Lorentzian fitted data acquired at 7T. As targets only the Lorentzian amplitudes were used.