11374

10500

كارشناسي ارشد

مخابرات سيستم

اصفهان: دانشگاه صنعتي اصفهان، دانشكده مهندسي برق و كامپيوتر

1395

سيزده، 93ص.: مصور

رسول اميرفتاحي

حميدرضا موسوي

بهزاد نظري، محمدرضا احمدزاده

1395/05/24

مهندسي برق و كامپيوتر

ID10500

Diagnosis of joints arthritis diseases in thermal images using mutual information estimation based on non parametric window Ali Nouri ali nouri@ec iut ac ir Date of Submission 2016 04 12 Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan 84156 83111 Iran Degree M Sc Language FarsiSupervisor Dr Rasoul AmirfattahiAbstractOne of the important factors of medical diagnosis is using safe and non invasive method Infraredthermal imaging as a non invasive method attracted scientists attention over the past decades andit s used in many medical diagnosis This method of imaging can provide useful information frompatient s body Some of the imaging methods which is currently used are invasive and often ex pensive One of the important applications of infrared thermography is in Rheumatology field fordiagnosis and assessment of inflammatory joint diseases Inflammatory joint diseases which con tain Rhuematoid Arthrits are very common worldwide nowadays and lots of people are dealing withthem Some of these disease are auto immune In the other words the immune system of the bodyattacks the joint for an unknown reason The cause of these kind of diseases are unknown yet andconsequently developing a method for early diagnosis of Rheumatoid Arthritis can be very impor tant Usually this disease doesn t have any special symptoms in the early stage and this makes itsdiagnosis and assessment difficult It is notable that this disease doesn t have any special treatmentand can only be stopped by special drugs In the last stages the bones which are connected to thejoints are completely deformed causing a great disability for the patient Normally the heat distribution over the skin is symmetric and any asymmetric pattern can be a signof special disease In this thesis a method based on the mutual information is developed for analyzingsymmetric pattern in the thermal images taken from patients In the proposed method images areregistered first The joint histogram of image pair is estimated using Non parametric windows andmutual information is then calculated from the estimated joint histogram To improve the efficiencyof the proposed method mean temperature as the second feature is defined Finally classificationis done based on the extracted features Results show that there is a meaningful difference betweencontrol and patient group using proposed method and these groups can be distinguished from eachother with the accuracy of 92 Keywords 1 Rheumatoid Arthritis 2 Infrared thermography 3 Non parametric windows 4 Mutual information

رسول اميرفتاحي

حميدرضا موسوي

بهزاد نظري، محمدرضا احمدزاده