16102

14377

كارشناسي ارشد

مهندسي پزشكي

اصفهان : دانشگاه صنعتي اصفهان

1399

دوازده، 112ص.: مصور، جدول، نمودار

مرضيه كمالي، فرزانه شايق

جلال ذهبي، احسان روحاني

1399/09/29

كتابنامه

برق و كامپيوتر

مهندسي برق و كامپيوتر

1399/10/03

2658709

112AbstractThe human brain is like a network composed of different areas Each of these areas has its function as well they interchange their data continuously Nowadays modeling the brain network andachieving the states it encounters during various behaviors are essential To this aim it is requiredto have some knowledge about both structure and function of the brain areas against eachother Each function in the brain is the result of a circuit of some connected areas of the brain Cognitive disorders occur when there is some kind of abnormality in these areas activity and thelevel of connectivity between them In other words brain disorders affect the way the brainconnectivity In this research the focus is on the effects of autism disorder ASD on theseconnectivities Autism is a disorder that affects the brain s growth in childhood and is characterizedby symptoms like difficulty in social interactions Many reports are illustrating the difference infunctional effective connectivity between autism and healthy people These investigations aremainly based on fMRI images of the brain during task or rest states Standard methods forevaluating the connectivities are based on seed based and ROI based correlation between differentbrain areas ROIs have defined by clustering methods like independent component analysis ICA Although these researches declared many facts about autism and its mechanisms none can besufficiently accurate to early diagnosis of autism in clinical usage Assuming functionalconnectivity constant during fMRI imaging referred to as static functional connectivity is themain drawback of this researches In this project we consider temporal changes of functionalconnectivity dynamic functional connectivity to find a more reliable pattern discriminatingagainst the healthy and autistic brain This idea leads us to a significant amount of connectivityparameters i e a sequence of connectivity matrices Different methods including clustring ofconnectivity matrices using kmeans cmeans and ICA methods extraction of information of thesematrices as a feature vector using different entropy methods are proposed We evaluate our methodby ABIDE1 database including 573 healthy and 539 ASD people Finally by combiningcorrelation methods and feature selection methods introduced in this study the accuracy of autismdiagnosis is improved Finally we conclude that the cmean algorithm is more accurate than theother algorithms used when all laboratories are classified at the same time The average accuracyobtained using this algorithm is 69 4 The best algorithm used for the case where laboratories areclassified independently is the kmean algorithm with an average accuracy of 84 9 We also foundthat communication power is greater in healthy people than in people with autism Key words functional connectivity fuzzy cluster entropy autism Magnetic resonance imaging classification

مرضيه كمالي، فرزانه شايق

جلال ذهبي، احسان روحاني