Multi-modal Brain Tensor Factorization: Preliminary Results with AD Patients
Global brain network parameters suffer from low classification performance and fail to provide an insight into the neurodegenerative diseases. Besides, the variability in connectivity definitions poses a challenge. We propose to represent multi-modal brain networks over a population with a single 4D brain tensor (B) and factorize B to get a lower dimensional representation per case and per modality. We used 7 known functional networks as the canonical network space to get a 7D representation. In a preliminary study over a group of 20 cases, we assessed this representation for classification. We used 6 different connectivity definitions (modalities). Linear discriminant analysis results in 90–95% accuracy in binary classification. The assessment of the canonical coordinates reveals Salience subnetwork to be the most powerful in classification consistently over all connectivity definitions. The method can be extended to include functional networks and further be used to search for discriminating subnetworks.
KeywordsFunctional networks Tensor factorization Structural networks Brain connectome Alzheimer’s Disease
This work was in part supported by the Turkish Ministry of Development under the TAM Project number DPT2007K120610, and in part by TUBITAK-ARDEB project number 114E053.
- 1.Fornito, A., Zalesky, A., Bullmore, E.T.: Fundamentals of Brain Network Analysis. Academic Press, San Diego (2016)Google Scholar
- 5.Williams, A.H., et al.: Unsupervised discovery of demixed, low-dimensional neural dynamics across multiple timescales through tensor component analysis. Neuron (2018)Google Scholar
- 12.Kolda, Tamara G.: Multilinear operators for higher-order decompositions, Technical report 2081. SANDIA, Albuquerque, NM (2006)Google Scholar