Akademik Veri Yönetim Sistemi
Tezin Türü: Yüksek Lisans
Tezin Yürütüldüğü Kurum: Orta Doğu Teknik Üniversitesi, Türkiye
Tezin Onay Tarihi: 2016
Tezin Dili: İngilizce
Öğrenci: Alican Yüksel
Danışman: UĞUR HALICI
Özet:In neuroscience, there exist some studies on activations of human brain used to detect mental disorders and to extract their signatures. Obsessive Compulsive Disorder (OCD) is one of the most common mental disorder that is encountered. Although there are many studies concern about this disorder by using functional Magnetic Resonance Imagining (fMRI), there exist very limited studies for extracting OCD signature that is extracting features from brain activity data to discriminate successfully OCD and healthy subjects. Unlike the past studies which used functional connectivity analysis on fMRI to extract signature of OCD, the aim of this work is to discriminate human brain activities between OCD patients and healthy ones by using effective connectivity analysis. For this purpose, Dynamic Causal Modelling (DCM) is used on the task related fMRI data that were taken from 12 healthy people and 12 OCD patients. Models are estimated by Bayesian Method by fitting the predicted BOLD signals to real signals measured and so to determine the best fitted neuronal state parameters. After that, these effective connectivity parameters are used as features for each subject and Support Vector Machine (SVM) classification method is used to discriminate OCD and control group.