Meeting Banner
Abstract #3202

U3-Net for Deep Vector QSM – Solving the Susceptibility Tensor Phase Model in Single-Orientation MRI

Edith Franziska Baader1, Thomas Jochmann2, Jens Haueisen2, Robert Zivadinov1,3, and Ferdinand Schweser1,3
1Buffalo Neuroimaging Analysis Center, Department of Neurology at the Jacobs School of Medicine and Biomedical Sciences, University at Buffalo, The State University of New York, Buffalo, NY, United States, 2Department of Computer Science and Automation, Technische Universität Ilmenau, Ilmenau, Germany, 3Center for Biomedical Imaging, Clinical and Translational Science Institute, University at Buffalo, The State University of New York, Buffalo, NY, United States

Quantitative susceptibility mapping (QSM) is increasingly being used to study the brain iron homeostasis and white matter pathology. However, all QSM algorithms that are currently used in the clinical setting use a physical model that neglects the well-established anisotropic magnetic susceptibility of myelin. In this work, we demonstrate that an extended U-Net allows solving a Vector QSM model that accounts for field perturbations caused by off-diagonal tensor elements. The proposed Deep Vector QSM yielded improved estimates of χ33 compared to conventional QSM.

This abstract and the presentation materials are available to 2020 meeting attendees and eLibrary customers only; a login is required.

Join Here