Meeting Banner
Abstract #3996

Quantitative Susceptibility Mapping of Liver Iron Overload using Deep Learning

Ruiyang Zhao1,2, Collin J Buelo2, Julia V Velikina1, Steffen Bollmann3, Ante Zhu4, Scott B Reeder1,2,5,6,7, and Diego Hernando1,2
1Radiology, University of Wisconsin-Madison, Madison, WI, United States, 2Medical Physics, University of Wisconsin-Madison, Madison, WI, United States, 3School of Information Technology and Electrical Engineering, University of Queensland, Brisbane, Australia, 4GE Global Research, Niskayuna, NY, United States, 5Biomedical Engineering, University of Wisconsin-Madison, Madison, WI, United States, 6Medicine, University of Wisconsin-Madison, Madison, WI, United States, 7Emergency Medicine, University of Wisconsin-Madison, Madison, WI, United States

A novel deep learning-based technique for quantitative susceptibility mapping (QSM) of liver iron overload was developed and validated. The proposed method relies on a 3D fully convolutional neural network, trained using synthetic dataset from a digital torso phantom that includes major organs. This study also included patients with iron overload who were imaged under 3T with using a single breath-hold multi-echo acquisition. Results showed promising performance and agreement with reference susceptibility measurements across a wide range of iron overload cases.

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

Join Here