In this work, we have analysed bipolar disorder using fMRI based on brain regional activity measurements. In this research work, we have located the eights regions as per the literature review which are strongly affected brain regions because of BPD. For those regions, the below operations are carried out. Initially functional points are identified using independent component analysis and their connectivity has been established using correlation coefficients. Then located the activated points using Hierarchical Modular Analysis based on the strength of the interregional connectivity. Followed by constructing network between the activated points of each brain regions. Property of network parameters like centrality page rank and centrality degree, centrality closeness, assortativity and clustering coefficients are extracted. Finally, adaboost classifier consist of three weak classifiers, KNN, GDA and naïve bayes are experimented. It was found that this work had given 94.2% accuracy comparatively better than earlier research works.

In the study, a supervised learning framework is focussed to identify the bipolar disorder (BD) using structural magnetic resonance imaging is focussed. The work is based on the newly developed 3D SIFT and 3D SURF feature vectors with pattern recognition technique.The overall hypothesis is to deduct BD results from dysfunctional cellular metabolism within specific brain systems (i.e., anterior limbic brain network) as reflected in abnormalities in brain activation patterns and in specific neurochemical measures. The proposed method is used to integrate neuroimaging in exploring the biomarkers of bipolar disorder to reveal the mechanism. In the method, two newly developed feature vectors and kernel PCA are combined or connected to project the feature vectors. Diagnosis process is done by Random Forest. The results reveal that the method has high potential to identify the BD than earlier works, and an average accuracy of 77.77% is reached. This research reveals that neuroimaging studies will help to differentiate bipolar disorder from healthy controls.