Meeting Banner
Abstract #2596

Quantitative Susceptibility Mapping from Deep-Learning Based Reconstruction of Undersampled Gradient-Recalled Echo Data

Ramin Jafari1,2, Pascal Spincemaille2, Thanh D. Nguyen2, Junghun Cho1,2, Martin R. Prince2, and Yi Wang1,2
1Cornell University, Ithaca, NY, United States, 2Weill Cornell Medicine, New York, NY, United States

A single breath-hold 3D GRE acquisition with tens of seconds is used to acquire data for water/fat separation and QSM generation in liver. However, in elderly and paediatric patients long breath-holds are not feasible. Compressed sensing along with Deep Learning is an alternative to shorten the scan time and perform reconstruction on undersampled data. In this work we compare how undersampling GRE data at different rates and use of Deep Learning for reconstruction will affect the water/fat separation and QSM results.

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

Join Here