Functional Network Modeling
Large-scale sparse functional networks from resting state fMRI
We develop a data-driven method for detecting subject-specific functional networks (FNs) while establishing group level correspondence. Our method simultaneously computes subject-specific FNs for a group of subjects regularized by group sparsity, to generate subject-specific FNs that are spatially sparse and share common spatial patterns across subjects. Our method is built upon nonnegative matrix decomposition techniques, enhanced by a data locality regularization term that makes the decomposition robust to imaging noise and improves spatial smoothness and functional coherences of the subject specific FNs.
This method has been extended for identifying subject-specific FNs at multiple spatial scales with a hierarchical organization from resting state fMRI data. Our method is built upon a deep semi-nonnegative matrix factorization framework to jointly detect the FNs at multiple scales with a hierarchical organization, enhanced by group sparsity regularization that helps identify subject-specific FNs without loss of inter-subject comparability.
- Hongming Li, Theodore D. Satterthwaite, and Yong Fan. "Large-scale sparse functional networks from resting state fMRI." NeuroImage 156 (2017): 1-13.
- Hongming Li and Yong Fan. "Interpretable, highly accurate brain decoding of subtly distinct brain states fromfunctional MRI using intrinsic functional networks and long short-term memory recurrent neural networks”, NeuroImage 202, 116059
- Hongming Li and Yong Fan. “Brain Decoding from Functional MRI Using Long Short-Term Memory Recurrent NeuralNetworks”. In: Frangi A., Schnabel J., Davatzikos C., Alberola-López C., Fichtinger G. (eds) Medical Image Computing and Computer Assisted Intervention – MICCAI 2018. MICCAI 2018. Lecture Notes in Computer Science, vol 11072. Springer, Cham
- Hongming Li, Xiaofeng Zhu, Yong Fan. “Identification of Multi-scale Hierarchical Brain Functional NetworksUsing Deep Matrix Factorization”. In: Frangi A., Schnabel J., Davatzikos C., Alberola-López C., Fichtinger G. (eds) Medical Image Computing and Computer Assisted Intervention – MICCAI 2018. MICCAI 2018. Lecture Notes in Computer Science, vol 11072. Springer, Cham
- Cui Z, Li H, Xia CH, Larsen B, Adebimpe A, Baum GL, Cieslak M, Gur RE, Gur RC, Moore TM, Oathes DJ, Alexander-Bloch AF, Raznahan A, Roalf DR, Shinohara RT, Wolf DH, Davatzikos C, Bassett DS, Fair DA, Fan Y, Satterthwaite TD. Individual Variation in Functional Topography of Association Networks in Youth. Neuron. 2020 Apr 22;106(2):340-353.e8. doi: 10.1016/j.neuron.2020.01.029. Epub 2020 Feb 19. PMID: 32078800; PMCID: PMC7182484.
Group information guided ICA for fMRI data analysis
The toolbox is for group-information guided ICA (GIG-ICA). In GIG-ICA, group information captured by standard Independent Component Analysis (ICA) on the group level is used as guidance to compute individual subject specific Independent Components (ICs) using a multi-objective optimization strategy. For computing subject specific ICs, GIG-ICA is applicable to subjects that are involved or not involved in the computation of the group information. Besides the group ICs, group information captured from other imaging modalities and meta analysis could be used as the guidance in GIG-ICA too.
- Yuhui Du, Yong Fan. Group information guided ICA for fMRI data analysis. Neuroimage. 2013 Apr 1;69:157-97. doi: 10.1016/j.neuroimage.2012.11.008. Epub 2012 Nov 27. PMID: 23194820.
- Yuhui Du, Yong Fan. Group information guided ICA for analysis of multi-subject fMRI data. 2011, 17th Annual Meeting of the Organization for Human Brain Mapping, Quebec City, Canada. Trainee Abstract Travel Awards, Interactive poster.