Meeting Banner
Abstract #5001

Reducing Streaking Artifacts in Quantitative Susceptibility Mapping via Deep Learning

Jie Liu1, Yida Wang1, Yang Song1, Haibin Xie1, Jianqi Li1, and Guang Yang1

1Shanghai Key Laboratory of Magnetic Resonance, East China Normal University, Shanghai, China

In this study, we proposed a new approach to reduce streaking artifacts in quantitative susceptibility mapping via deep learning. It combined two convolutional neural networks to reduce streaking artifacts from classic threshold-based k-space division (TKD) . The proposed method achieved impressive performance both visually and statistically.

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

Join Here