CV

Education

Ph.D in University of Michigan, Ann Arbor, 2024
- GPA: 3.93/4.0
- Some Coursework: Funtional Analysis, Nonlinear Programming, Convex optimization
M.S. in University of Michigan, Ann Arbor, 2019
- GPA: 3.95/4.0
- Some Coursework: Probability and Random Process, Matrix Theory, Machine Learning, Computer Vision, Image Processing
B.S. in Huazhong University of Science and Technology, 2017
- GPA Ranking: Top 3 among over 200 students
- Qiming Honor Program (top 10%)
- Outstanding Graduates Award & Excellent Academic Performance Scholarship

Work experience

Apr 2025 - Present: Algorithm Engineer (image processing) at KLA
Jan 2025 - Apr 2025: Research Fellow at University of Michigan

Skills

Computer language
- Python: Pytorch, Tensorflow, Numpy, Scipy, Pandas
- C/C++
- MATLAB
- SQL
- Julia
Others: Cloud Computing, Linux, SLURM, Latex, Git

Research experience

Feb 2021 - Present: Research Assistant @ EECS, University of Michigan
Advisor: Jeffrey A. Fessler and Douglas C. Noll.
RF pulse design, sampling trajectories optimization and image reconstruction for novel silent MRI pulse sequence
- Programmed silent MRI pulse sequence for the research and clinical scanners from multi-vendors using TOPPE and Pulseq
- Designed functional tasks, including visual, motor and auditory simulation and collected fMRI data from over 20 subjects
- Reconstructed images using model-based methods and learning-based methods, including Plug-and-Play, unrolled neural networks to resolve image artifacts and improve image resolution
- Optimized 3D non-Cartesian sampling trajectories using learning-based methods to optimize the gradients and trajectories under the constraints of gradient peak amplitude and slew rate
- Computed the shaped RF pulse for silent MRI to create more uniform excitation profiles
- Developed spatial-temporal reconstruction methods including UNFOLD and Low-rank models for in-vivo fMRI data to boost the functional analysis
Jan 2019 - Nov 2019: Research Assistant @ Medical School, University of Michigan
Advisor: Yuni K. Dewaraja, Jeffrey A. Fessler.
This project aims to build a deep Convolutional Neural Networks to fastly and accurately predict scatter distribution of 3D SPECT/CT imaging.
- Designed multi-input physics-informed neural network architecture tailored to 3D SPECT/CT system
- Predicted the distribution of scatter from SPECT/CT using deep convolutional neural network and the estimation shows good alignment to the gold standard method
- Reduced the computational time for over 100X from multiple hours using Monte-Carlo simulation to one minute using GPU.
Jan 2018 - Aug 2018: Research Assistant , University of Michigan
Acceleration of Convolutional Dictionary Learning and Convolutional Analysis Operator Learning by applying sketching method. This project won the first place in the KLA-Tencor Image Processing Contest (Award).

Publications

Joint optimization of multi-echo reconstruction and quantitative map estimation in Looping Star

H. Xiang, I. K. Onder, A. H. Mehta, J. A. Fessler, and D. C. Noll. “Joint optimization of multi-echo reconstruction and quantitative map estimation in Looping Star”. In: Proceedings of the 33th Annual Meeting of the ISMRM. Vol. 0630. 2024

Model‐based reconstruction for looping‐star MRI

Xiang, Haowei, Jeffrey A. Fessler, and Douglas C. Noll. "Model‐based reconstruction for looping‐star MRI." Magnetic Resonance in Medicine (2024).

Spatial-temporal reconstruction using UNFOLD in looping-star silent fMRI

Xiang, Haowei, Jeìrey A. Fessler, and Douglas C. Noll. "Spatial-temporal reconstructionusing UNFOLD in looping-star silent fMRI." Proceedings of the 32th Annual Meeting of the ISMRM. Vol. 2534. 2023.

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

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.

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.

Accelerated convolutional operator learning

Xiyu Zhang*, Haowei Xiang*, Il Yong Chun, Mert Pilanci, and Jeffrey A. Fessler, Preprint

Talks

Model-Based Image Reconstruction in Functional MRI using Looping-Star

September 23, 2022

Talk at The Fall 2022 Functional MRI Symposium, Ann Arbor, MI

Scatter correction of SPECT/CT using deep convolutional neural network

November 01, 2019

Talk at Nuclear Science Symposium and Medical Imaging Conference, Manchester, UK

Teaching

Teaching Assistant

Service and leadership

Reviewer for NeuroImage, Computers in Biology and Medicine, and ISMRM