Clipped DeepControl: Deep neural network two-dimensional pulse design with an amplitude constraint layer

Mads Sloth Vinding*, Torben Ellegaard Lund

*Corresponding author for this work

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

Abstract

Advanced radio-frequency pulse design used in magnetic resonance imaging has recently been demonstrated with deep learning of (convolutional) neural networks and reinforcement learning. For two-dimensionally selective radio-frequency pulses, the (convolutional) neural network pulse prediction time (a few milliseconds) was in comparison more than three orders of magnitude faster than the conventional optimal control computation. The network pulses were from the supervised training capable of compensating scan-subject dependent inhomogeneities of B 0 and B 1 + fields. Unfortunately, the network presented with a small percentage of pulse amplitude overshoots in the test subset, despite the optimal control pulses used in training were fully constrained. Here, we have extended the convolutional neural network with a custom-made clipping layer that completely eliminates the risk of pulse amplitude overshoots, while preserving the ability to compensate for the inhomogeneous field conditions.

Original languageEnglish
Article number102460
JournalArtificial Intelligence in Medicine
Volume135
ISSN0933-3657
DOIs
Publication statusPublished - Jan 2023

Keywords

  • Phantoms, Imaging
  • Neural Networks, Computer
  • Heart Rate
  • Magnetic Resonance Imaging/methods
  • Radio Waves

Fingerprint

Dive into the research topics of 'Clipped DeepControl: Deep neural network two-dimensional pulse design with an amplitude constraint layer'. Together they form a unique fingerprint.

Cite this