Using fuzzy C-means index matrix to depict for the focal cortical dysplasia region on T1 brain MRI images

摘要

Focal cortical dysplasia (FCD) is a common disorder of cortical development that underlies the susceptibility of epileptogenicity of focal cortical region. However, FCD may not be visualized easily in regular MRI images by physicians, especially in the early stage. Hence, video-monitored EEGs are still the diagnosis gold standard in hospital. Based on fuzzy C-means (FCM) segmentation technologies, we proposed a fuzzy C-means index matrix (FCMIM) to depict for the FCD region on brain MRI images to valid the cortical micro-disorganization. The technique can help a practitioner of neurology or neurosurgeon to define the focal lesion when an epilepsy surgery is planned to conduct. The proposed method successfully detected FCD regions in 5 out of 8 patients for this investigation. It is promising that the proposed method provides blurring junction area detection without using normal brain database (NDB). Our experiment results provided suggestions on invisible information discovery on MRI images for future neuroimaging research to prevent disorders in early stages.