Abstract #0320

U2-Net for DEEPOLE QUASAR–A Physics-Informed Deep Convolutional Neural Network that Disentangles MRI Phase Contrast Mechanisms

Thomas Jochmann¹, Jens Haueisen¹, Robert Zivadinov^2,3, and Ferdinand Schweser^2,3

¹Department of Computer Science and Automation, Technische Universität Ilmenau, Ilmenau, Germany, ²Buffalo Neuroimaging Analysis Center, Department of Neurology, Jacobs School of Medicine and Biomedical Sciences, Buffalo, NY, United States, ³Clinical and Translational Science Institute, University at Buffalo, Buffalo, NY, United States

Magnetic susceptibility is a physical property of tissues that changes with iron level and (de-)myelination. Mapping the susceptibility can help us improve our understanding of the brain and its diseases, such as multiple sclerosis and Alzheimer disease. Quantitative Susceptibility Mapping (QSM) derives the susceptibility using MRI phase data. QUASAR adds a more sophisticated physical model to QSM. Our novel U2-Net for DEEPOLE QUASAR uses deep learning to separate the magnetic field into two components from different contrast mechanisms, yields an improved susceptibility map, and shows where in the brain the tissue does not adhere to the basic QSM model, e.g. due to microstructural anisotropy.

This abstract and the presentation materials are available to members only; a login is required.

Join Here