Our new paper was published in MRM 🙂 We predict the required inversion pulse power from a fast 3D localizer scan instead of a B1 map and it works well to reduce the SAR load of the sequence and save time.

The full publication can be found here: https://doi.org/10.1002/mrm.28590

The preprint is here: [1911.08118] Improving FLAIR SAR efficiency at 7T by adaptive tailoring of adiabatic pulse power using deep convolutional neural networks (arxiv.org)

The data used to train the model is on OSF:

And we also built a colab notebook (described here) so you can play with the model and train your own version :): https://colab.research.google.com/drive/1EOg5r30w0NtXJvTFdGhlR0ysGfaEaTpP


Leave a Reply

Avatar placeholder

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.