Dissertation Talk: Complex-valued Deep Learning with Applications to Magnetic Resonance Image Synthesis
Seminar: Dissertation Talk: EE | May 10 | 2-3 p.m. | 490H Cory Hall
Magnetic resonance imaging (MRI) has the ability to produce a series of images that each have different visual contrast between tissues, allowing clinicians to qualitatively assess pathologies that may be visible in one contrast-weighted image but not others. Unfortunately, these standard contrast-weighted images do not contain quantitative values, producing challenges for post-processing, assessment, and longitudinal studies. MR fingerprinting is a recent technique that produces quantitative tissue maps from a single pseudorandom acquisition, but it relies on computationally heavy nearest neighbor algorithms to solve the associated nonlinear inverse problem. In the first half of this talk, we present our deep learning methods to 1) speed up quantitative MR fingerprinting and 2) synthesize the standard contrast-weighted images directly from the same MR fingerprinting scan.
MRI signals are inherently complex-valued. However, modern neural networks are not designed to support complex values. As an example, the pervasive ReLU activation function is undefined for complex numbers. These limitations curtail the impact of deep learning for complex data applications, such as MRI, radio frequency modulation identification, and target recognition in synthetic-aperture radar images. In the second part of this talk, we will discuss the motivation for complex-valued networks, the changes that we have made to implement complex backpropagation, and our new complex cardioid activation function that made it possible to outperform real-valued networks for MR fingerprinting image synthesis.
Advisors: Miki Lustig and Stella Yu