Our research is generously supported by National Science Foundation (NSF), National Institutes of Health (NIH), Department of Homeland Security, Department of Veterans Affairs, Center for Clinical and Translational Science (CCTS), and VCOM.

Developing Manifold-based Methods for Spatial-temporal Data Analysis

Spatial-temporal data is a prevalent data type in biomedical domains, encompassing instances like multi-channel EEG and fMRI. In the analysis of such data, the connectivity matrix (e.g., functional brain connectivity derived from fMRI) is widely extracted and analyzed. Rather than examining the connectivity matrix within the Euclidean space, we consider each matrix as a point situated on the manifold of positive semi-definite matrices coupled with Bures-Wasserstein distance. Within this framework, we aim to establish the mathematical foundation for the distance metric, the barycenter of matrices, and the geometry of the manifold. We've introduced three algorithms for estimating the barycenter of a set of matrices, along with a novel kernel function suitable for integration with kernel-based techniques like kernel SVM.

Time-frequency Analysis of Scalp EEG Signals

Electroencephalography (EEG) is a brain imaging approach that has been widely used in neuroscience and clinical settings. Neural responses are naturally heterogeneous by showing variations in frequency bands of brainwaves and peak frequencies of oscillatory modes across individuals. We present several systematic approaches for analyzing scalp EEG signals including data-driven analysis, functional data analysis, and manifold learning, which can be generalized to the spatial-temporal data in other fields.

• Jingyi Zheng*, Mingli Liang, Arne Ekstrom, and Fushing Hsieh. "Time-frequency Analysis of Scalp EEG with Hilbert-Huang transform and deep learning", IEEE Journal of Biomedical and Health Informatics, 2021. DOI:10.1109/JBHI.2021.3110267.
• Yuyan Yi, Nedret Billor, Mingli Liang, Xuan Cao, Arne Ekstrom, Jingyi Zheng*, "Classification of EEG signals: An interpretable approach using functional data analysis", Journal of Neuroscience Methods, 2022. DOI:10.1016/j.jneumeth.2022.109609.
• Mingli Liang, Jingyi Zheng, Eve Isham, and Arne Ekstrom, "Common and Distinct Roles of Frontal Midline Theta and Occipital Alpha Oscillations in Coding Temporal Intervals and Spatial Distances", Journal of Cognitive Neuroscience, 2021. DOI:10.1162/jocn\_a\_01765.
• Jia Liu, Jingyi Zheng, Prahalada Rao, Zhenyu Kong, "Machine learning–driven in situ process monitoring with vibration frequency spectra for chemical mechanical planarization", The International Journal of Advanced Manufacturing Technology, 2020. DOI:10.1007/s00170-020-06165-1.
• Jingyi Zheng, Mingli Liang, Arne Ekstrom, Linqiang Ge, Wei Yu, and Fushing Hsieh, "On Association Study of Scalp EEG Data Channels Under Different Circumstances", In: Chellappan S., Cheng W., Li W. (eds) Wireless Algorithms, Systems, and Applications. WASA 2018. DOI: 10.1007/978-3-319-94268-1\_56. 

Analysis of Cardiac Magnetic Resonance Images via Statistical Learning and Deep Learning

Machine learning algorithms, especially deep learning architectures, have demonstrated immense potential for biomedical image analysis, often surpassing expert-level performance. We present several projects for analyzing MRI images via statistical methods and deep learning.

• Jingyi Zheng, Yuexin Li, Nedret Billor, Mustafa Ahmed, Efstathia Andrikopoulou, Yu-Hua Fang, Betty Pat, Thomas Denney, Louis Dell'Italia, Understanding Post-Surgical Decline in Left Ventricular Function in Primary Mitral Regurgitation Using Statistical and Machine Learning models, 2023, Frontier in Cardiovascular Medicine, DOI:10.3389/fcvm.2023.1112797.  
• Mustafa Ahmed, Efstathia Andrikopoulou, Jingyi Zheng, et al.  Interstitial Collagen Loss, Myocardial Remodeling, and Function in Primary Mitral Regurgitation, JACC: Basic to Translational Science. 2022. DOI: 10.1016/j.jacbts.2022.04.014.
• Xuan Cao, Fang Yang, Jingyi Zheng, Xiao Wang, and Qingling Huang. "Aberrant Structure MRI in Parkinson’s Disease and Comorbidity with Depression Based on Multinomial Tensor Regression Analysis". Journal of Personalized Medicine 12, no. 1: 89. 2022. DOI: 10.3390/jpm12010089.
• Xulian Zhang, Xuan Cao, Chen Xue, Jingyi Zheng, Shaojun Zhang, Qingling Huang, and Weiguo Liu, "Aberrant functional connectivity and activity in Parkinson’s disease and comorbidity with depression based on radiomic analysis", Brain and Behavior, 10 March 2021. DOI: 10.1002/brb3.2103.
• Sujata Sinha, Thomas Denney, Yang Zhou, and Jingyi Zheng*, "Automated Semantic Segmentation of Cardiac Magnetic Resonance Images with Deep Learning", in the Proceeding of 19th IEEE International Conference on Machine Learning and Applications (ICMLA), 2020, pp. 1362-1368, DOI: 10.1109/ICMLA51294.2020.00212.

Brain-wide Calcium Imaging Video Analysis: Epilepsy Diagnosis and Seizure Prediction

Epilepsy is a neurological disorder in the brain characterized by recurrent, unprovoked seizures. In this project, we worked on three aspects of epilepsy study: (epilepsy) diagnosis, (epileptic seizures) prediction, and spatiotemporal structure discovery. By analyzing the zebrafish's brain-wide calcium imaging video, we proposed a data-driven approach to effectively predict the epileptic seizures. Furthermore, we explored the macroscopic patterns of epileptic and control cases, and built classifiers via machine learning models. Finally, we discovered the spatial structure based on mutual conditional entropy and recover the temporal system state trajectory that leads to epileptic seizures.

• Jingyi Zheng, Fushing Hsieh, and Linqiang Ge, "A Data-driven Approach to Predict and Classify Epileptic Seizures From Brain-wide Calcium Imaging Video Data", in IEEE/ACM Transactions on Computational Biology and Bioinformatics, vol. 17, no. 6, pp. 1858-1870, 2020, DOI: 10.1109/TCBB.2019.2895077. 
• Fushing Hsieh, and Jingyi Zheng, "Unraveling pattern-based mechanics defining self-organized recurrent behaviors in a complex system: a Zebrafish #39's calcium brain-wide imaging example", Frontiers in Applied Mathematics and Statistics, 5, 2019.