Better than Real: Complex-valued Neural Nets for MRI Fingerprinting
This work addresses the problem of slow and non-scalable tissue parameter identification in MRI for medical imaging applications, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles the scalability and speed issues in MRI fingerprinting by using deep learning as an efficient nonlinear inverse mapping approach, and introduces a complex-valued neural network with cardioid activation functions, achieving higher accuracy than real-valued networks.
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.