About me
Haowei Xiang is currently a 4th year PhD student studying Electrical and Computer Engineering at University of Michigan and he is co-advised by Prof. Jeffrey Fessler and Prof. Douglas Noll. He has been working on developing algorithms for novel silent MRI techniques, optimizing k-space trajectories, and using spatial-temporal model for image reconstruction. In his past project, he used machine learning and deep Convolutional Neural Networks (CNN) to predict SPECT/CT scatter by levering the historical and simulation data. In addition to his research, he was the graduate student instructor for graduate-level courses including Probability and Random Process, and Matrix Methods for Signal Processing, Data Analysis and Machine Learning.
Research Interest
His major is Signal & Image Processing, and Machine Learning. His research interests include machine learning, image reconstruction, inverse problems, medical imaging, MRI and optimization.
Publications
SPECT/CT scatter estimation using a deep convolutional neural network: implementation in Y-90 imaging
Xiang, Haowei, et al. "SPECT/CT scatter estimation using a deep convolutional neural network: implementation in Y-90 imaging." 2019 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC). IEEE, 2019.
A deep neural network for fast and accurate scatter estimation in quantitative SPECT/CT under challenging scatter conditions
Xiang, Haowei, et al. "A deep neural network for fast and accurate scatter estimation in quantitative SPECT/CT under challenging scatter conditions." European journal of nuclear medicine and molecular imaging 47 (2020): 2956-2967.
Model-based Image Reconstruction in Looping-star MRI
Xiang, Haowei, Jeffrey A. Fessler, and Douglas C. Noll. "Model-based Image Reconstruction in Looping-star MRI." 2022 ISMRM
Accelerated convolutional operator learning
Xiyu Zhang, Haowei Xiang, Il Yong Chun, Mert Pilanci, and Jeffrey A. Fessler, Preprint
Talks
Scatter correction of SPECT/CT using deep convolutional neural network
Talk at Nuclear Science Symposium and Medical Imaging Conference, Manchester, UK
Model-Based Image Reconstruction in Functional MRI using Looping-Star
Talk at The Fall 2022 Functional MRI Symposium, Ann Arbor, MI