Biography:  Weidong Liu (Chinese: 刘卫东) earned his Ph.D from Zhejiang University in 2008. During 2008-2009, he was a postdoctoral fellow in Hong Kong University of Science and Technology. After finishing postodoctoral research at HKUST, he joined Wharton School in University of Pennsylvania as a postdoctoral fellow. In 2011, he joined Shanghai Jiao Tong University. Weidong Liu has been awarded by National Excellent Doctoral Dissertation Award from China and New World Mathematics Awards, Silver Award for the Ph.D Thesis in 2010. His research interests are focused on statistics and probability. In high dimensional statistical inference, Weidong Liu and coauthors developed several new methods on the estimation of high dimensional covariance matrix/inverse matrix. In time series analysis and nonparametric estimation, he and coauthors had made important progress in several long-standing opening problems. Many of his research results were published in the top journals such as JASA、Ann.Stat.、Biometrika, Ann. Appl.Probab. and Probab Theor Relat Field.

Title: DEMO: A Flexible Deartifacting Module for Compressed Sensing MRI

Abstract: Compressed sensing (CS) has been a novel technique for fast reconstruction of magnetic resonance (MR) images from their partial k-space measurements. However, the quality of the reconstructed images could be severely affected by artifacts from various sources. In this paper, we propose a deartifacting module (DEMO) that can effectively remove the artifacts by eliminating sparse outliers in the k-space. Specifically, DEMO augments the measurements in the original loss function to approximate a new loss that is robust to outliers. Since DEMO is developed independently of any backbone algorithm to perform with, it can be flexibly Incorporated into a broad range of CS-MRI methods, including both model-based methods and unrolling deep neural networks. Extensive experiments under various settings demonstrate the effectiveness and robustness of DEMO.