Identification of activity patterns of brain networks in stroke by community detection

• Grant number: 19/09319-6
• Support type: Scholarships in Brazil - Master
• Effective date (Start): December 01, 2019
• Effective date (End): November 30, 2021
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Zhao Liang
• Grantee: Paulo Henrique Lima de Paula
• Home Institution: Faculdade de Filosofia, Ciências e Letras de Ribeirão Preto (FFCLRP). Universidade de São Paulo (USP). Ribeirão Preto , SP, Brazil

Abstract

The human (animal) brain is a complex network divided into interconnected structural and functional regions. Functional connectivity has been used to model anatomically separated regions of the brain by describing the temporal dependence of neuronal activity patterns. In this context, complex network theory and Functional Magnetic Resonance Imaging (fMRI) techniques are used to map the brain into a network, called the Brain Network. This project aims to analyze connectivity patterns of the brain network with the data of patients suffering from Stroke or Cerebral Vascular Accident (CVA), which is a serious disease and the second major cause of death in the world. Specifically, we propose to apply the particle competition model, an unsupervised machine learning technique, to detect and characterize brain network communities in different conditions, i.e., post-stroke and healthy brains. Topological analysis of the networks will also be performed, observing the dissimilarity between the brain communities based on the particle dynamics and identifying the impact of the brain injury in the stroke process. It is believed that the analysis of dynamic changes in the functional organization of the brain network in the stroke process is important for a better understanding of the mechanism of the disease and its diagnosis. (AU)