Artificial intelligence (AI) has emerged as a powerful tool for analyzing high-dimensional neuroimaging data. However, important challenges remain in ensuring statistical rigor and biological interpretability, which are essential for generating reliable and scientifically meaningful insights into brain function and organization. My research focuses on developing statistical AI methods that integrate modern machine learning with principled statistical modeling to address these challenges.
Working with a team of interdisciplinary researchers, we have developed novel AI frameworks for learning brain networks from functional and structural connectomes. Our contributions include BrainGB, the first unified benchmark for graph neural network (GNN)-based brain network analysis, and innovative AI methods such as FBNetGen, Brain Network Transformer, and R-Mixup. These methods leverage graph-based deep learning to capture complex brain network organization, identify informative connectivity patterns, and improve prediction of cognitive, behavioral, and clinical outcomes. Applications to large-scale neuroimaging cohorts have demonstrated their potential to characterize individual differences in brain connectivity and advance our understanding of cognition, neurodevelopment, and mental disorders. This work has been published in leading AI conferences and medical imaging journals, including KDD, NeurIPS, and IEEE Transactions on Medical Imaging.
More recently, my research has expanded toward developing statistically rigorous AI methods that integrate interpretable representation learning with statistical modeling and inference for brain connectome analysis. One direction is the development of task-aware statistical AI frameworks that jointly learn sparse, interpretable directed brain connectivity networks and low-dimensional graph representations optimized for predicting cognitive, behavioral, and clinical outcomes. This research aims to develop scalable, reliable, and interpretable AI methods to advance understanding of brain organization and uncover its role in brain health and mental disorders.
Selected References
†: denote students/postdocs advised/co-advised
Kan, X.†, Li, Z., Cui, H., Yu, Y., Xu, R., Yu, S., Zhang, Z., Guo, Y., and Yang, C. (2023). R-Mixup: Riemannian Mixup for Biological Networks. Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD).
Cui, H., Dai, W., Zhu, Y., Kan, X., Gu, A.A.C., Lukemire, J., Zhan, L., He, L., Guo, Y., and Yang, C. (2023). BrainGB: A Benchmark for Brain Network Analysis with Graph Neural Networks. IEEE Transactions on Medical Imaging, 42(2), 493–506. Paper
Kan, X.†, Dai, W., Cui, H., Zhang, Z., Guo, Y., and Yang, C. (2022). Brain Network Transformer. Advances in Neural Information Processing Systems (NeurIPS). Paper
Yang, Y., Zhu, Y., Cui, H., Kan, X., He, L., Guo, Y., and Yang, C. (2022). Data-Efficient Brain Connectome Analysis via Multi-Task Meta-Learning. Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD). Paper
Kan, X.†, Kong, Y., Yu, T., and Guo, Y. (2022). Bracenet: Graph-embedded Neural Network for Brain Network Analysis. In 2022 IEEE International Conference on Big Data . pp. 4979-4987.
Kan, X.†, Cui, H., Lukemire, J., Guo, Y., and Yang, C. (2022). FBNETGEN: Task-aware GNN-based fMRI Analysis via Functional Brain Network Generation. Proceedings of International Conference on Medical Imaging with Deep Learning, PMLR 172:618-637. Selected for oral presentation. Paper
Kan, X.†, Cui, H., Guo, Y., and Yang, C. (2021). Effective and Interpretable fMRI Analysis via Functional Brain Network Generation. Interpretable Machine Learning in Healthcare: The International Conference on Machine Learning (ICML-IMLH).
Blind source separation (BSS) methods, including independent component analysis (ICA), have become fundamental tools for identifying latent brain networks from neuroimaging data. My research established some of the first rigorous statistical modeling, estimation, and inference frameworks for BSS in multi-subject neuroimaging, providing probabilistic foundations for population-level ICA and extending these methods to account for between-subject heterogeneity, longitudinal imaging, and multimodal neuroimaging. More recently, we have extended these frameworks to brain connectomics through novel latent connectivity trait models for static, dynamic, and multiview connectomes, providing interpretable latent representations that facilitate mechanistic investigation of neurodevelopment and mental disorders.
General temporal-concatenation group ICA (TC-GICA) models that can accommodate different types of between-subject variability in temporal responses and model wide variety of neural signals under different experimental tasks (Guo and Pagnoni, 2008; Guo, Biometrics, 2011).
A hierarchical ICA framework. we have developed a novel hierarchical ICA framework to formally model subject-specific effects in both temporal and spatial domains in fMRI data (Guo and Tang, 2013; Shi and Guo, 2016). In particular, the hierarchical covariate-adjusted ICA (hc-ICA) model (Shi and Guo, 2016) provides the first group ICA method that allows formally modeling and testing of covariate effects in ICA decomposition. Our method provides a more reliable and powerful statistical tool for evaluating group differences in brain functional networks while appropriately controlling for potential confounding factors. We have released a Matlab GUI-based toolbox HINT for implementing the hc-ICA.
Longitudinal ICA. We have developed a longitudinal ICA (L-ICA) model (Wang and Guo, 2019) to investigate neurodevelopment-, disease- or treatment-related changes in brain networks. With existing ICA methods only applicable to cross-sectional imaging studies, our proposed L-ICA helps fill a major gap in ICA methodology.
SparseBayes ICA. We have developed Sparse Bayesian Independent Component Analysis (SparseBayes ICA) for reliable estimation of individual differences in brain networks. SparseBayes ICA presents a powerful approach for modeling brain network source signals using a flexible Dirichlet process mixture, coupled with sparse estimation of covariate effects via a horseshoe prior. This advanced methodology significantly enhances the accuracy of uncovering latent brain networks and also improves both the sensitivity and specificity in detecting individual differences on brain networks.
Selected References
†: denote students/postdocs advised/co-advised
Lukemire, J.*, Wang, Y. and Guo, Y.* (2026). A General Framework for Investigating Neurodevelopment of Brain Functional Networks using Multi-site and Longitudinal Neuroimaging. Annals of Applied Statistics, 20(1), p.604.
Lukemire, J.†, Pagnoni, G. and Guo, Y. (2023). Sparse Bayesian Modeling of Hierarchical ICA: Reliable Estimation of Individual Differences in Brain Networks. Biometrics. In Press
Wang, Y. † and Guo, Y (2019). A hierarchical independent component analysis model for longitudinal neuroimaging studies. NeuroImage, 189(1), 380-400.
Shi, R.† and Guo, Y (2016). Modeling Covariate Effects in Group Independent Component Analysis with Application to Functional Magnetic Resonance Imaging. Annals of Applied Statistics. (Accepted). An earlier version of the paper was selected for Best Student Paper Award, American Statistical Association (ASA) Statistics in Imaging Section.
Guo, Y and Tang, Li. (2013). A hierarchical probabilistic model for group independent component analysis in fMRI studies, Biometrics, doi: 10.1111/biom.12068.
Guo Y (2011). A general probabilistic model for group independent component analysis and its estimation methods. Biometrics. 67(4): 1532-1542.
Guo Y and Pagnoni G (2008). A unified framework for group independent component analysis for multi-subject fMRI data. NeuroImage 42: 1078-1093. Listed in ScienceDirect’s Top 25 hottest articles of NeuroImage between July-Sep. 2008.
Guo Y (2008). Group Independent Component Analysis of Multi-subject fMRI data: Connections and Distinctions between Two Methods. IEEE Proceedings of the 2008 International Conference on BioMedical Engineering and Informatics v2: 748-752.
We have developed the LOCUS framework, which employs novel low-rank, sparse decomposition methods to identify reproducible latent connectivity traits that capture the organization of brain networks while substantially reducing dimensionality and improving statistical efficiency.
Selected References
Ran, J.†, Wang, Y. and Guo, Y.* (2024). Unveiling hidden sources of dynamic functional connectome through a novel regularized blind source separation approach. Imaging Neuroscience, 2, pp.1-30.Open Access
Wang, Y.† and Guo, Y.. (2023). LOCUS: A Novel Decomposition Method for Brain Network Connectivity Matrices using Low-rank Structure with Uniform Sparsity. Annals of Applied Statistics, 17(2): 1307-1332.
Brain connectome analysis has become a cornerstone of modern neuroscience for understanding the neural circuitry underlying cognition, neurodevelopment, aging, and mental disorders. We have developed a broad class of statistical methods for estimating, integrating, and comparing functional and structural brain connectomes using sparse graphical models, Bayesian hierarchical modeling, and multilevel network models. These contributions include statistically rigorous methods for direct functional connectivity estimation, differential network analysis, dynamic functional connectivity modeling, multimodal integration of structural and functional connectomes, and joint analysis of multiple brain networks across cognitive tasks, imaging modalities, and longitudinal studies.
Wang, Y., Kang, J., Kemmer, P.B., and Guo, Y. (2016). An efficient and reliable statistical method for estimating functional connectivity in large-scale brain networks using partial correlation. Frontiers in Neuroscience, 10:123. Paper
Dai, T. and Guo, Y. (2017). Predicting Individual Brain Functional Connectivity Using a Bayesian Hierarchical Model. NeuroImage, 147, 772–787.
Higgins, I.A., Kundu, S., and Guo, Y. (2018). Integrative Bayesian Analysis of Brain Functional Networks Incorporating Anatomical Knowledge. NeuroImage, 181, 263–278.
Lukemire, J., Kundu, S., Pagnoni, G., and Guo, Y. (2020). Bayesian Joint Modeling of Multiple Brain Functional Networks. Journal of the American Statistical Association.
Higgins, I.A., Kundu, S., Choi, K.S., Mayberg, H., and Guo, Y. (2019). A Differential Degree Test for Comparing Brain Networks. Human Brain Mapping.
Chen, H., Guo, Y., He, Y., Ji, J., Liu, L., Shi, Y., Wang, Y., Yu, L., and Zhang, X. (2021). Simultaneous Differential Network Analysis and Classification for Matrix-variate Data with Application to Brain Connectivity. Biostatistics.
Liu, D., Zhao, C., He, Y., Liu, L., Guo, Y., and Zhang, X. (2023). Simultaneous Cluster Structure Learning and Estimation of Heterogeneous Graphs for Matrix-variate fMRI Data. Biometrics, 79(3), 2246–2259.
Chen, H., Guo, D., Guo, Y., He, Y., Liu, D., Liu, L., Yin, Y., and Zhou, X. (2025). Cooperative Differential Network Learning with Hub Detection for Multi-center Neuroimaging Data. Annals of Applied Statistics, 19(2), 1578–1602.
Kundu, S., Ming, J., Pierce, J., McDowell, J., and Guo, Y. (2018). Estimating Dynamic Brain Functional Networks Using Multi-subject fMRI Data. NeuroImage, 183, 635–649.
Kundu, S., Lukemire, J., Wang, Y., and Guo, Y. (2019). A Novel Joint Brain Network Analysis Using Longitudinal Alzheimer's Disease Data. Scientific Reports, 9.
Lukemire, J., Wang, Y., and Guo, Y. (2026). A General Framework for Investigating Neurodevelopment of Brain Functional Networks Using Multi-site and Longitudinal Neuroimaging. Annals of Applied Statistics, 20(1), 604.
Kemmer, P., Wang, Y., Bowman, F.D., Mayberg, H., and Guo, Y. (2018). Evaluating the Strength of Structural Connectivity Underlying Brain Functional Networks. Brain Connectivity.
Murden, R., Zhang, Z., Guo, Y., and Risk, B. (2022). Interpretive JIVE: Connections with CCA and an Application to Brain Connectivity. Frontiers in Neuroscience, 16.
Hu, Y., Zeydabadinezhad, M., Li, L., and Guo, Y. (2022). A Multimodal Multilevel Neuroimaging Model for Investigating Brain Connectome Development. Journal of the American Statistical Association, 117(539), 1134–1148.
My research has developed Bayesian and statistical machine learning methods for imaging-based prediction of treatment response, disease progression, and cognitive function. These methods integrate neuroimaging with behavioral and clinical information to improve prediction accuracy while providing interpretable models that can facilitate individualized risk assessment and treatment planning. More recently, my work has emphasized biologically informed prediction based on latent neural representations and brain connectivity. These methods contribute to the development of predictive neuroimaging tools for precision mental health care.
1. A predictive model for forecasting future neural activation. This predictive model has potentials in helping select optimal treatment plans for individual patients in clinical practice. For example, it has been successfully applied in a neuroimaging study of schizophrenia to predict patients’ post-treatment neural activity after various treatments (Guo et al., Human Brain Mapping, 2008).
2. A weighted cluster kernel PCA model for predicting subjects’ cognitive states using brain images (Guo, 2010). The kernel PCA model improves prediction accuracy by capturing nonlinearity patterns in images and is robust to outlying subjects.
3. A Bayesian hierarchical model to provide predictive information on disease progression- or treatment-related changes in brain connectivity. The proposed method improves the accuracy of individualized prediction of connectivity by combining information from both group-level connectivity patterns that are common across subjects as well as unique individual-level connectivity features. Our predictive model has been applied to Alzheimer's Disease Neuroimaging Initiative (ADNI) data to predict longitudinal changes in neural circuits in Alzheimer patients (Dai and Guo, NeuroImage, 2017).
References
Dai, T† and Guo, Y * (2017). Predicting Individual Brain Functional Connectivity Using a Bayesian Hierarchical Model. NeuroImage.147(15): 772–787.
Guo Y (2010). A weighted cluster kernel PCA prediction model for multi-subject brain imaging data. Statistics And Its Interface. 3:103-111.
Guo Y, Bowman FD, Kilts C (2008). Predicting the brain response to treatment using a Bayesian Hierarchical model . Human Brain Mapping, 29(9): 1092-1109.
Agreement studies have wide and important applications in biomedical research and clinical practices since multiple-raters/methods measurements commonly occur in such settings. One challenging topic in agreement studies is how to account for censored or truncated observations such as those observed in survival studies. Our work in this area includes: 1) development of one of the first nonparametric estimation methods for agreement measures in the presence of censoring (Guo and Manatunga, 2007 and 2009), 2) development of agreement methods to accommodate different types of survival outcomes including both discrete (Guo and Manatunga, 2005 and 2009) and continuous data (Guo and Manatunga, 2007 and 2010); 3) development of modeling tools in agreement studies that allow for modeling subjects’ covariate effects on the strength of agreement (Guo and Manatunga, 2005). Recently, we have developed a novel framework for assessing agreement based on survival processes (Guo et al., 2013). This new framework circumvents the need of estimating moment functions of survival times in the previous agreement methods and can be widely applied to survival studies with various study lengths.
We have developed new statistical methods that extend the existing agreement paradigm to handle multiple scale (continuous/ordinal) scenarios. Additionally, we have worked on development of new agreement methodology to investigate the alignment between traditional behavior/clinical outcomes and neuroimaging biomarkers and to assess agreement between images acquired from multi-center neuroimaging studies.
References
Guo Y, Li R, Peng L and Manatunga AK. (2013). A new agreement measures based on survival processes, Biometrics, doi: 10.1111/biom.12063.
Peng L, Li R, Guo Y, and Manatunga AK.(2011). Assessing Broad Sense Agreement between Ordinal and Continuous Measurements. Journal of American Statistician Association. 106: 1592-1601. Selected as JASA Featured Article.
Guo Y and Manatunga AK (2010). A note on assessing agreement for frailty models. Statistics and Probability Letters. 80: 527-533.
Guo Y and Manatunga AK (2009). Measuring agreement of multivariate discrete survival times using a modified weighted kappa coefficient. Biometrics, 65(1):125-34.
Guo Y and Manatunga AK (2007). Nonparametric estimation of the concordance correlation coefficient under univariate censoring. Biometrics, 63(1): 164-172.
Guo Y and Manatunga AK (2005). Modeling the agreement of discrete bivariate survival times using kappa coefficient. Lifetime Data Analysis, 11(3): 309-332