Tissue classification for MRI of thigh using a modified FCM method

Fuzzy C-means (FCM) has been frequently used to image segmentation in order to separate objects. The most used segmentation attribute is grey level of pixels. Nevertheless, this method can not identify complex image objects because grey level can not take into account all visual information. This paper describes a modified FCM method for tissue classification which integrates separation and fusion operation of partition tree with expert knowledge. Our method has been applied to 26 MRI (Magnetic Resonance Imaging) images of thigh for localizing four main anatomical tissues: muscle, adipose tissue, cortical bone, and spongy bone. A testing dataset of 6500 representative points has been created by an expert. Using our method, we obtain a high classification rate (95.73%) in the test dataset, which largely improved the classification results obtained from existing methods.