Cerebral Sulcus Labeling with Fuzzy Boundary Optimization Algorithm

Abstract

It is very likely that the cerebral disease of infant leaves permanent brain disorder. The regions of disorder are different by a symptom, and brain is atrophied and deformed by degree of symptom. Therefore, it is effective for diagnosing such cerebral symptoms to measure the surface area of each gyrus. However, gyrus segmentation method for infantile brain is not yet established. This paper proposes the gyrus labeling method with fuzzy boundary optimization algorithm for infantile brain in magnetic resonance (MR) images. The proposed method was applied to 14 infantile subjects (3 weeks – 4 years 3 months old). The results showed that the cerebral gyri were successfully labeled with a mean sensitivity of 90.8% and a mean false positive rate of 0.1%.