Abstract
The registration of brain images is required to facilitate the study of brain mapping, treatment planning, and image-guided therapies of nervous system. In the present work a similarity measure has been implemented for affine multimodality (MR and CT) image registration of sections of the human brain. In addition, a similarity measure is built on both intensity and gradient-based images. In the present work, the region of interest (ROI), the ventricular region, is segmented using the fuzzy c-means clustering technique. The deformation or change of shape of the ventricular region captures the process of degeneracy and other abnormality in tissue regions of the human brain. The similarity metric should be maximal when two images are perfectly aligned. The genetic algorithm-based search strategy has been utilized to optimize the registration process.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call