Better than Real: Complex-valued Neural Networks for MRI Fingerprinting

TitleBetter than Real: Complex-valued Neural Networks for MRI Fingerprinting
Publication TypeConference Paper
Year of Publication2017
AuthorsVirtue, P., Yu S. X., & Lustig M.
Published inProceedings of the International Conference on Image Processing 2017
Keywordscomplex-valued neural networks, MRI fingerprinting

The task of MRI fingerprinting is to identify tissue parameters from complex-valued MRI signals. The prevalent approach is dictionary based, where a test MRI signal is compared to stored MRI signals with known tissue parameters and the most similar signals and tissue parameters retrieved. Such an approach does not scale with the number of parameters and is rather slow when the tissue parameter space is large.

Our first novel contribution is to use deep learning as an efficient nonlinear inverse mapping approach. We generate synthetic (tissue, MRI) data from an MRI simulator, and use them to train a deep net to map the MRI signal to the tissue parameters directly. Our second novel contribution is to develop a complex-valued neural network with new cardioid activation functions. Our results demonstrate that complex-valued neural nets could be much more accurate than real-valued neural nets at complex-valued MRI fingerprinting. 


This research was supported in part by the National Institutes of Health R01EB009690 grant and a Sloan Research Fellowship. We thank Michael Kellman, Frank Ong, Jonathan Tamir, and Hong Shang for great discussions about complex calculus, fingerprinting, pulse sequences, and simulator software.

ICSI Research Group