Visual analytics of heterogeneous brain networks using multilevel methods
| Grant number: | 12/13390-9 |
| Support type: | Scholarships in Brazil - Master |
| Effective date (Start): | February 01, 2013 |
| Effective date (End): | February 28, 2014 |
| Field of knowledge: | Engineering - Biomedical Engineering - Medical Engineering |
| Principal Investigator: | João Ricardo Sato |
| Grantee: | Anderson dos Santos Siqueira |
| Home Institution: | Centro de Matemática, Computação e Cognição (CMCC). Universidade Federal do ABC (UFABC). Ministério da Educação (Brasil). Santo André , SP, Brazil |
Abstract The Attention Deficit Hyperactivity Disorder (ADHD) is a deviation in neurodevelopment which is related to the triad of symptoms: inattention, impulsivity and restlessness. The prevalence is about 3-6% of the population of children in school age, but also is present in adults. The clinical diagnosis is carried out only by symptoms description and there is no additional tests for biomarkers. The human brain is a complex organ. It has many connections and it can currently be studied by magnetic resonance imaging (fMRI), which allows an indirect measurement of brain activations by monitoring the so-called BOLD effect. The brain connectivity can be analyzed by methods based on graph theory known as analysis of complex networks. By using graphs obtained from the processing of fMRI images, some analyzes will be performed, such as closeness and betweeness among the nodes of the network, as well as their degree. Subsequently, these characteristics of the network topology will be used as variables in pattern recognition methods such as Support Vector Machine. The objective of finding patterns and connections in the brain that indicate a possible diagnosis of ADHD from functional magnetic resonance images, and thus helping to support the diagnosis of this disorder. (AU) | |