Meeting Banner
Abstract #0694

Single-step Quantitative Susceptibility Mapping Reconstruction without Brain Extraction using Deep Learning

Hongjiang Wei1, Steven Cao1, Fuhua Yan2, Kristen W Yeom3, and Chunlei Liu1

1University of California, Berkeley, Berkeley, CA, United States, 2Rui Jin Hospital, Shanghai Jiao Tong University, Shanghai, China, 3Department of Radiology, Stanford University, Palo Alto, CA, United States

We propose a deep learning-based single-step QSM reconstruction method that directly estimates magnetic susceptibility from total phase images without brain extraction. 209 healthy subjects with ages ranging from 11 to 82 years were employed for network training. The trained network provides superior image quality and high reconstruction speed compared to other single-step QSM methods. In addition, the elimination of the brain extraction step makes it possible to estimate susceptibility near the boundaries and explore the magnetic susceptibility of whole brain vascular images.

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

Join Here