Segmentation of MR brain images using FCM technique in Frontotemporal Dementia

Frontotemporal Dementia (FTD) is a progressive neurodegenerative disorder characterized by focal grey matter atrophy of orbitomesial frontal and anterior temporal regions. The overlapping nature of behavioral changes in this young onset dementia makes it difficult to differentiate from other forms of dementia such as Alzheimer's disease (AD). Neuroimaging analysis especially Magnetic Resonance Imaging (MRI) plays a vital role in the differential diagnosis of this dread demending disease. Automatic segmentation of brain MR images helps in the quantification of atrophy rate longitudinally. Fuzzy c means algorithm (FCM) is an unsupervised algorithm, have been widely used in automated image segmentation. This study aims to explore the effectiveness of FCM technique for the longitudinal analysis of cerebral atrophy in FTD subjects compared with normal controls. We showed that the analysis was effective in the quantification of structural brain changes overtime and could serve as predictive marker of impending behavioural changes in FTD.