Abstract
Keywords: registration, medical image registration, follow-up change detection inserial MRI, contrast enhanced T1-weighted magnetic resonance imagesIn many problems involving multiple image analysis, an image registration step isrequired. One such problem appears in brain tumor imaging, where baseline andfollow-up image volumes from a tumor patient are often to-be compared. Natureof the registration for a change detection problem in brain tumor growth analy-sis is mainly rigid. Contrast enhanced T1-weighted MR images (CE-T1 MRI) arewidely used in clinical practice for monitoring brain tumors. Over this modality,contours of the active tumor cells and whole tumor borders and margins are vi-sually enhanced. In this thesis, a new technique to register serial CE-T1 MRI ispresented. The proposed fully-automated method is based on ¯ve anatomical land-marks: eye balls, nose, con°uence of sagittal sinus, and apex of superior sagittalsinus. After extraction of anatomical landmarks from ¯xed and moving volumes, arigid transformation is estimated by minimizing the sum of squared distances be-tween the landmark coordinates. Final result is re¯ned with a surface registration,which is based on head masks con¯ned to the surface of the scalp, as well as toa plane constructed from three of the extracted features. The overall registrationis not intensity based, and it depends only on the inherent anatomical structures.Validation studies using both synthetically transformed MRI data, and real MRIscans, which included several markers over the head of the patient were performed.In addition, comparison studies against manual landmarks marked by a radiologist,as well as against the results obtained from ITK mean squares and cross correlationbased methods were carried out to demonstrate the e®ectiveness of the proposedmethod.
