Abstract #3195

How to train a Deep Convolutional Neural Network for Quantitative Susceptibility Mapping (QSM)

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

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

Deep convolutional neural networks have recently gained popularity for solving the ill-posed dipole inversion problem in Quantitative Susceptibility Mapping (QSM). The training of the neural networks is performed with examples of χ and f that can either be obtained from physical simulations on synthetic source distributions, or through “classical” QSM methods on real data. For both choices, there is a plethora of decisions to make and parameters to set. Here we seek to present best practices regarding the modelling of synthetic source distributions and data augmentation.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.