# DeepControl: 2D RF pulses facilitating B1^+ inhomogeneity and B0 off-resonance compensation in vivo at 7T

arXiv: https://arxiv.org/abs/2009.12408 · HTML: https://mlsanity.com/paper/2009.12408/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Sep 2020.

## Built on by (most cited first, 3 of 3)

- [Deep reinforcement learning-designed radiofrequency waveform in MRI](https://mlsanity.com/paper/2105.03061/) (2021)
- [Clipped DeepControl: deep neural network two-dimensional pulse design with an amplitude constraint layer](https://mlsanity.com/paper/2201.08668/) (2022)
- [Sequence Search: Automated Sequence Design using Neural Architecture Search](https://mlsanity.com/paper/2604.14788/) (2026)

## Abstract (arXiv)

Purpose: Rapid 2D RF pulse design with subject specific B1^+ inhomogeneity and B0 off-resonance compensation at 7 T predicted from convolutional neural networks is presented. Methods: The convolution neural network was trained on half a million single-channel transmit, 2D RF pulses optimized with an optimal control method using artificial 2D targets, B1^+ and B0 maps. Predicted pulses were tested in a phantom and in vivo at 7 T with measured B1^+ and B0 maps from a high-resolution GRE sequence. Results: Pulse prediction by the trained convolutional neural network was done on the fly during the MR session in approximately 9 ms for multiple hand drawn ROIs and the measured B1^+ and B0 maps. Compensation of B1^+ inhomogeneity and B0 off-resonances has been confirmed in the phantom and in vivo experiments. The reconstructed image data agrees well with the simulations using the acquired B1^+ and B0 maps and the 2D RF pulse predicted by the convolutional neural networks is as good as the conventional RF pulse obtained by optimal control. Conclusion: The proposed convolutional neural network based 2D RF pulse design method predicts 2D RF pulses with an excellent excitation pattern and compensated B1^+ and B0 variations at 7 T. The rapid 2D RF pulse prediction (9 ms) enables subject-specific high-quality 2D RF pulses without the need to run lengthy optimizations.