Abstract: Functional MRI (fMRI) is a widely used technique to study about the brain activation and its implications through Blood Oxygenation Level Dependent (BOLD) interpretations. Data-driven analysis methods, in particular Independent Component Analysis (ICA) have proven quite useful for the analysis of fMRI data. A promising approach to multi-subject analysis is Group Independent Component Analysis (GICA), which identifies group components and reconstructs activations at the individual level. In this research, a robust model-free technique is proposed for detecting the fMRI activations during the tasks activating the language areas of the Brain. We evaluated the performance of the proposed method on a moderate size real time fMRI data acquired under three different tasks. This results in a set of spatial maps and time courses which are common to the whole group, together with an individual response activation map for each of the subjects in the group. The results show that, ICA components are involved in the direct correlation between language based tasks and their spatial/time course maps.
P. Suresh and K. Bommannaraja, 2016. Functional Mribold Interpretation of Brain Functions Using Independent Component Analysis. Asian Journal of Information Technology, 15: 1607-1620.