Hui Xue
Principal Researcher at Microsoft
Redmond, Washington, United States
Summary
👤
Senior🎓
Top SchoolHui Xue is a Principal Researcher at Microsoft Research in Redmond with 13 years of experience building deep learning, imaging and cloud solutions for biomedical applications. Previously he led NHLBI’s imaging and Biomed AI programs at NIH, where he directed institution-wide AI strategy, deployed cloud GPU infrastructure, and translated advanced MRI research into clinical-grade, open-source tools. A long-time maintainer and core contributor to the widely used Gadgetron medical image reconstruction framework, he blends high-performance C++ back-end development with algorithmic research in parallel imaging, motion correction and AI-driven quantification. Trained with a PhD in Medical Imaging and a graduate certificate in AI from Stanford, he uniquely bridges academic rigor and production engineering to enable non-coding biologists and clinicians to leverage foundation models and scalable reconstruction pipelines.
13 years of coding experience
16 years of employment as a software developer
PhD Medical Imaging, PhD Medical Imaging at Imperial College LondonMSc Biomedical Engineering, MSc Biomedical Engineering at Xi'an Jiaotong UniversityGraduate Certificate Artificial Intelligence, Graduate Certificate Artificial Intelligence at Stanford University
English, Chinese
Github Skills (11)
c-language10
cprogramming-language10
medical-image-processing10
data-processing9
algorithms8
code-optimization8
numerical-optimization8
algorithm8
optimization8
optimisation8
openmp6
Programming languages (8)
Github contributions (5)
gadgetron/gadgetron
Jan 2013 - Oct 2022
Gadgetron - Medical Image Reconstruction Framework
Role in this project:
Back-end Developer & Data Scientist
Back-end Developer & Data ScientistContributions:2 releases, 79 reviews, 1639 commits in 9 years 11 months
Contributions summary:Hui primarily contributed to the medical image reconstruction framework, focusing on fixing bugs related to declaration and versioning, and addressing problems in CPU rtgrappa. The commits suggest a focus on performance optimization within the Gadgetron framework, evidenced by code changes in the GrappaWeightsCalculator and GtPlusReconGadget modules. Their work included addressing issues related to data processing and potentially contributing to the accuracy of image processing, specifically through improvements in the kernel module.
reconstructionimage-reconstructionmedical-imagedeep-learningcomputer-vision
xueh2/gadgetron
Feb 2015 - Oct 2022
Contributions:269 commits, 551 pushes, 488 branches in 7 years 9 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.