Integration of Fuzzy C-Means with Correlation Template and Active Contour for Brain Lesion Segmentation in Diffusion-Weighted MRI

Abstract

This study proposed automatic detection and segmentation of brain lesion in diffusion-weighted magnetic resonance images (DWI) based on Fuzzy C-Means (FCM). Due to noises and intensity inhomogeneity, FCM technique fails in producing accurate results. Active contour and correlation template are integrated to overcome this problem. The brain lesions are acute stroke and solid tumor foe hyperintense lesions, and necrosis and chronic stroke for hypointense lesions. The proposed analysis framework has been validated by using Jaccard (AO), Dice, false negative rate (FNR) and false positive rate (FPR). FCM with correlation template provides more accurate results compared with FCM with active contour. The results are 0.547, 0.258, 0.192 and 0.687 for Jaccard, FPR, FNR and Dice indices. This method also can segment the lesions precisely.