Major research interests in Prof. Yi Wang’s lab are in applying and developing data science, machine learning, optimization, physics, and statistical inference techniques for medical imaging acquisition and analysis. This includes increasing imaging speed, reducing image artifacts, and generating novel image contrasts/biomarkers using computer vision and signal processing strategies. We seek to formulate medical imaging problems for disease diagnosis and therapy delivery as inverse problems from acquired signals to underlying pathogeneses based on biophysics. We work closely with clinicians to study neurological diseases such as multiple sclerosis, Parkinson’s disease, Alzheimer’s disease, stroke, cancer in various organs, liver diseases, and heart diseases. The inverse problems are often poorly conditioned and involve noisy incomplete data, resulting in reconstructed images with errors or artifacts commonly encountered in computer vision. We have developed the Bayesian statistical inference approach to removing image artifacts in MRI using prior knowledge established in biomedicine or acquired from multiple imaging modalities including immunohistochemical staining and optical imaging.
Our work is exemplified in the following:
- Quantitative susceptibility mapping (QSM) to solve the field-to-susceptibility inverse problem using the Bayesian approach. Tissue susceptibility reflects molecular electron cloud properties and QSM enables its precise quantitative study. QSM has become a very active field of studying tissue magnetism for applications in neurodegeneration, inflammation, oxygen consumption, hemorrhage, liver, osteoporosis, atherosclerosis, and drug delivery. QSM is increasingly used in clinical practice, particularly in precision targeting for deep brain stimulation, precision monitoring of chronic active hemorrhages and inflammation, precision medication for iron chelation therapy, and precision diagnosis and gadolinium-free imaging for multiple sclerosis.
- Quantitative transport mapping (QTM) to solve the inverse problem from imaging to tissue perfusion quantification. We develop fast dynamic imaging (4D) to capture tracer (drugs, contrast agents and spin labels) transport in tissue using super resolution, sparsity, and deep learning techniques. Perfusion parameters affect imaging through convolution in space time according to transport equation of mass and momentum flux laws. We develop QTM to deconvolve 4D time resolved imaging for perfusion quantification. QTM enables precise measurement of blood flow in tissue and helps with precise delivery of therapeutic drugs, cryotherapy and tissue ablation.
- Lesion segmentation from acquired images to enable automated precise measurements and analyses of disease burden. We employ various image segmentation techniques including image feature based approaches and deep neural network based approaches.
- Biomedical Imaging and Instrumentation
- Biomedical Engineering
- Image Analysis
- Signal and Image Processing
- Scientific Computing
- Biomolecular Engineering
- Artificial Intelligence
- Computational Fluid Dynamics
- Complex Systems, Network Science and Computation
- Computational Science and Engineering
- Computer Aided Diagnosis
- Statistics and Machine Learning
Principles of medical imaging, Magnetic Resonance Imaging (MRI)
- Zhang J, Liu Z, Zhang S, Zhang H, Spincemaille P, Nguyen TD, Sabuncu MR, Wang Y. "Fidelity imposed network edit (FINE) for solving ill-posed image reconstruction." Neuroimage. 2020 Jan 22:116579. doi: 10.1016/j.neuroimage.2020.116579. [Epub ahead of print] PMID: 31981779.
- Nguyen TD, Wen Y, Du J, Liu Z, Gillen K, Spincemaille P, Gupta A, Yang Q, Wang Y. "Quantitative susceptibility mapping of carotid plaques using nonlinear total field inversion: Initial experience in patients with significant carotid stenosis." Magn Reson Med. 2020 Mar 6. doi: 10.1002/mrm.28227. [Epub ahead of print] PMID: 32141644
- Cho J, Zhang S, Kee Y, Spincemaille P, Nguyen TD, Hubertus S, Gupta A, Wang Y. "Cluster analysis of time evolution (CAT) for quantitative susceptibility mapping (QSM) and quantitative blood oxygen level-dependent magnitude (qBOLD)-based oxygen extraction fraction (OEF) and cerebral metabolic rate of oxygen (CMRO2 ) mapping." 2020 Mar;83(3):844-857. doi: 10.1002/mrm.27967. [Epub ahead of print] PMID: 31502723
- Wen Y Weinsaft JW, Nguyen TD, Liu Z, Horn EM, Singh H, Kochav J, Eskreis-Winkler S, Deh K, Kim J, Wang Y, Spincemaille P. "Free Breathing Three-Dimensional Cardiac Quantitative Susceptibility Mapping for Differential Cardiac Chamber Blood Oxygenation – Initial Validation in Patients with Cardiovascular Disease inclusive of Direct Comparison to Invasive Catheterization." J Cardiovasc Magn Reson. 2019 Nov 18;21(1):70. doi: 10.1186/s12968-019-0579-7. PMID: 31735165
- Jafari R, Sheth S, Spincemaille P, Nguyen TD, Prince MR, PhD, Wen Y, Guo Y, Deh K, Liu Z, Margolis D, Brittenham GM, Kierans AS, Wang Y. "Rapid automated liver quantitative susceptibility mapping, J Magn Reson Imaging." 2019 Sep;50(3):725-732, https://doi.org/10.1002/jmri.26632. PMID: 30637892
- Kee Y, Liu Z, Zhou L, Dimov A, Cho J, de Rochefort L, Seo JK, Wang Y, "Quantitative Susceptibility Mapping (QSM) Algorithms: Mathematical Rationale and Computational Implementations." IEEE Trans Biomed Eng. 2017 Nov;64(11):2531-2545. doi: 10.1109/TBME.2017.2749298. [Epub ahead of print] PMID: 28885147
Selected Awards and Honors
- Fellow of American Institute for Medical and Biological Engineering (AIMBE) 2006
- Fellow (International Society of Magnetic Resonance in Medicine) 2012
- Fellow (Institute of Electrical and Electronics Engineers) 2013
- Advanced Richard B. Mazess Scholarship (University of Wisconsin) 1993
- Graduate Fellowship (University of Wisconsin) 1988
- B.S. (Nuclear Physics), Fudan University, 1986
- M.S. (Theoretical Physics), University of Wisconsin, Milwaukee, 1988
- Ph.D. (Medical Physics), University of Wisconsin, Madison, 1994
- Postdoc, Mayo Clinic, 1994-1996