Menu
Home
Teaching
Publications
Research Group

Zhuo-Xu Cui (崔卓须)

Zhuo-Xu Cui

Ph.D
Associate Professor
Applied Mathematics
Shenzhen Institutes of Advanced Technology (SIAT), Chinese Academy of Sciences
No. 1068, Xueyuan Avenue, Xili Shenzhen University Town, Nanshan District
Shenzhen, P.R.China 518055
Email: zx.cui [@] siat [DOT] ac [DOT] cn

Research

My research interests include

  • Computational MRI

  • Inverse Problems

  • Deep Learning

Selected Topics

Fundamental Model-Assisted Image Reconstruction

(In Progress)

"White-Box" Transformer for MRI

(In Progress)

Ultra-High-Field MRI

(In Progress)

Model Driven Diffusion

By employing an optimization model in MRI, we guide the formulation of forward and reverse diffusion equations with inherent physical significance. This process facilitates the reconstruction of MR images or the completion of missing k-space data under imposed physical constraints.

  • Chentao Cao#, Zhuo-Xu Cui#, Shaonan Liu, Dong Liang, and Yanjie Zhu*. "High-Frequency Space Diffusion Models for Accelerated MRI." IEEE Transactions on Medical Imaging, 2024. [ journal] (code)

  • Zhuo-Xu Cui#, Chentao Cao#, Jing Cheng, Sen Jia, Hairong Zheng, and Dong Liang, Yanjie Zhu*. "SPIRiT-Diffusion: Self-Consistency Driven Diffusion Model for Accelerated MRI". submitted to IEEE Transactions on Medical Imaging, revision. [arXiv]

Physics-Informed DeepMRI

Based on MR physical priors and some fundamental physical principles, we design interpretable deep learning algorithms, involving the redesign of loss functions, inference algorithms, and network architectures.

  • Zhuo-Xu Cui, Sen Jia, Qingyong Zhu, Congcong Liu, Zhilang Qiu, Yuanyuan Liu, Jing Cheng, Haifeng Wang, Yanjie Zhu, and Dong Liang*. "K-UNN: k-space interpolation with untrained neural network." Medical Image Analysis, 2023, 88: 102877. [journal] (code)

  • Yanjie Zhu, Jing Cheng, Zhuo-Xu Cui, Qingyong Zhu, Leslie Ying, Dong Liang*. "Physics-Driven Deep Learning Methods for Fast Quantitative Magnetic Resonance Imaging: Performance improvements through integration with deep neural networks." IEEE Signal Processing Magazine, 2023 40(2): 116-128. [journal]

  • Zhuo-Xu Cui, Congcong Liu, Xiaohong Fan, Chentao Cao, Jing Cheng, Qingyong Zhu, Yuanyuan Liu, Sen Jia, Yihang Zhou, Haifeng Wang, Yanjie Zhu, Jianping Zhang, Qiegen Liu, Dong Liang*. "Physics-Informed DeepMRI: Bridging the Gap from Heat Diffusion to k-Space Interpolation." submitted to IEEE Transactions on Medical Imaging, revision. [arXiv]

Learnable Regularization

Regularization guides interpretable deep learning approaches for solving inverse problems. Under specific conditions, it ensures that the developed deep learning methods maintain physical interpretability, meeting theoretical properties like existence, uniqueness, and regularity.

  • Zhuo-Xu Cui#, Qingyong Zhu#, Jing Cheng, Bo Zhang, and Dong Liang. "Deep Unfolding as Iterative Regularization for Imaging Inverse Problems." Inverse Problems, 2024. [journal]

  • Zhuo-Xu Cui, Sen Jia, Jing Cheng, Qingyong Zhu, Yuanyuan Liu, Kankan Zhao, Ziwen Ke, Wenqi Huang, Haifeng Wang, Yanjie Zhu, and Dong Liang. "Equilibrated zeroth-order unrolled deep network for parallel mr imaging". IEEE Transactions on Medical Imaging, 2023, 24(12): 3540-3554. [journal]

  • Huayu Wang, Chen Luo, Taofeng Xie, Qiyu Jin, Guoqing Chen, Zhuo-Xu Cui*, Dong Liang*. "Convex Latent-Optimized Adversarial Regularizers for Imaging Inverse Problems". arXiv preprint arXiv:2309.09250, 2023. [arXiv]

  • Chen Luo, Huayu Wang, Taofeng Xie, Qiyu Jin, Guoqing Chen, Zhuo-Xu Cui*, Dong Liang*. "Matrix Completion-Informed Deep Unfolded Equilibrium Models for Self-Supervised k-Space Interpolation in MRI". arXiv preprint arXiv:2309.13571, 2023. [arXiv]

Low-field MRI

Utilizing artificial intelligence technology, we achieve the reconstruction of high-field like MR images from data acquired on low-field MR devices.

  • Zhuo-Xu Cui#, Congcong Liu#, Chentao Cao, Yuanyuan Liu, Jing Cheng, Qingyong Zhu, Yanjie Zhu, Haifeng Wang, Dong Liang. "Meta-Learning Enabled Score-Based Generative Model for 1.5 T-Like Image Reconstruction from 0.5 T MRI". submitted to Medical Image Analysis, revision. [arXiv]

Funding

  • 国家自然科学基金青年基金项目 (NSFC), 2023-2025, 30万, 主持, 在研.

  • 中国科学院特别研究助理项目, 2023-2024, 80万, 主持, 在研.

  • 博士后留深科研资助项目, 2023-2025, 30万, 主持, 在研.

  • 中国科学院深圳先进技术研究院优秀青年创新基金, 2022-2023, 10万, 主持, 在研.

  • 中国博士后科学基金面上项目 (China Postdoctoral Science Foundation), 2020-2022, 8万, 主持, 已结题.

  • 国家自然科学基金重点项目 (NSFC), 2024-2027, 240万, 参与, 在研.

  • 国家自然科学基金数学天元基金 (NSFC), 2023-2025, 200万, 参与, 在研.

  • “十四五”国家重点研发计划“数学和应用研究”重点专项 (National Key R&D Program of China), 2023-2027, 1700万, 科研骨干, 在研.

  • “十四五”国家重点研发计划“工程科学与综合交叉”重点专项 (National Key R&D Program of China), 2022-2026, 1770万, 科研骨干, 在研.

Selected Academic Presentations

About me

    I received my Ph.D. degree from the Department of Applied Mathematics at Wuhan University in 2020 under the guidance of Prof. Qibin Fan. From 2020 to 2022, I served as a postdoctoral researcher at Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences (SIAT), collaborating with Prof. Dong Liang as my mentor. Since 2022, I have been working at the Research Center for Medical Artificial Intelligence at SIAT.

More profiles

Google Scholar.
Researchgate.
A brief cv.