Unsupervised deep learning with convolutional neural networks for static parallel transmit design: A retrospective study
Toygan Kilic, Patrick Liebig, Omer Burak Demirel, Jürgen Herrler, Armin M. Nagel, Kamil Ugurbil, Mehmet Akçakaya
Abstract
Purpose
To mitigate B1+ inhomogeneity at 7T for multi-channel transmit arrays using unsupervised deep learning with convolutional neural networks (CNNs).
Methods
Deep learning parallel transmit (pTx) pulse design has received attention, but such methods have relied on supervised training and did not use CNNs for multi-channel B1+ maps. In this work, we introduce an alternative approach that facilitates the use of CNNs with multi-channel B1+ maps while performing unsupervised training. The multi-channel B1+ maps are concatenated along the spatial dimension to enable shift-equivariant processing amenable to CNNs. Training is performed in an unsupervised manner using a physics-driven loss function that minimizes the discrepancy of the Bloch simulation with the target magnetization, which eliminates the calculation of reference transmit RF weights. The training database comprises 3824 2D sagittal, multi-channel B1+ maps of the healthy human brain from 143 subjects. B1+ data were acquired at 7T using an 8Tx/32Rx head coil. The proposed method is compared to the unregularized magnitude least-squares (MLS) solution for the target magnetization in static pTx design.
Results
The proposed method outperformed the unregularized MLS solution for RMS error and coefficient-of-variation and had comparable energy consumption. Additionally, the proposed method did not show local phase singularities leading to distinct holes in the resulting magnetization unlike the unregularized MLS solution.
Conclusion
Proposed unsupervised deep learning with CNNs performs better than unregularized MLS in static pTx for speed and robustness.