Structural Subnetwork Analysis

In brain networks, the identification of subnetworks (grouping of densely connected regions) can contribute towards understanding how the complex behavioral repertoire of the human mind emerges from the parallel processes of segregated neuronal clusters and their integration during complicated cognitive tasks. Relying on the advances in diffusion imaging and network theoretic analysis of imaging data, we are developing new methodologies to identify subnetworks of the brain network with distinct connectivity patterns or distinct biological or behavioral correlates. Our methods integrate traditional network analysis tools with advanced machine learning techniques, utilizing a wide range of approaches, including multivariate pattern analysis, non-negative matrix factorization, spectral clustering, and probabilistic generative models, in order to identify both data-driven and functionally defined subnetworks.

 

 

Publications
  1. Takanori Watanabe, Birkan Tunç, Drew Parker, Junghoon Kim, Ragini Verma, Label-Informed Non-negative Matrix Factorization with Manifold Regularization for Discriminative Subnetwork Detection, International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2016.
  2. Birkan Tunç, Berkan Solmaz, Drew Parker, Theodore D Satterthwaite, Mark A Elliott, Monica E Calkins, Kosha Ruparel, Raquel E Gur, Ruben C Gur, Ragini Verma, Establishing a link between sex-related differences in the structural connectome and behaviour, Phil. Trans. R. Soc. B, 371 (1688), pp. 20150111, 2016.
  3. Birkan Tunç, Ragini Verma, Unifying Inference of Meso-Scale Structures in Networks, PloS one, 10 (11), pp. e0143133-e0143133, 2015.
  4. Yasser Ghanbari, Luke Bloy, Birkan Tunc, Varsha Shankar, Timothy PL Roberts, J Christopher Edgar, Robert T Schultz, Ragini Verma, On Characterizing Population Commonalities and Subject Variations in Brain Networks, Medical Image Analysis, 2015.
  5. Birkan Tunç, Varsha Shankar, Drew Parker, Robert T Schultz, Ragini Verma, Towards a quantified network portrait of a population, International Conference on Information Processing in Medical Imaging (IPMI), 2015.
  6. Yasser Ghanbari, Alex R Smith, Robert T Schultz, Ragini Verma, Identifying group discriminative and age regressive sub-networks from DTI-based connectivity via a unified framework of non-negative matrix factorization and graph embedding, Medical image analysis, 18 (8), pp. 1337-1348, 2014.
  7. Yasser Ghanbari, Luke Bloy, Varsha Shankar, J Christopher Edgar, Timothy PL Roberts, Robert T Schultz, Ragini Verma, Functionally driven brain networks using multi-layer graph clustering, International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2014.
  8. Yasser Ghanbari, Alex R. Smith, Robert T. Schultz, Ragini Verma, Connectivity Subnetwork Learning for Pathology and Developmental Variations, International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2013.
  9. Yasser Ghanbari, John Herrington, Ruben C Gur, Robert T Schultz, Ragini Verma, Locality Preserving Non-negative Basis Learning with Graph Embedding, International Conference on Information Processing in Medical Imaging (IPMI), 2013.
  10. Madhura Ingalhalikar, Alex R Smith, Luke Bloy, Ruben Gur, Timothy PL Roberts, Ragini Verma, Identifying sub-populations via unsupervised cluster analysis on multi-edge similarity graphs, International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2012.
  11. Yasser Ghanbari, Luke Bloy, Nematolah Kayhan Batmanghelich, Timothy Roberts, Ragini Verma, Dominant Component Analysis of Electrophysiological Connectivity Networks, International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2012.
Funding