The image segmentation technique is considered as one of the most important aspects of processing medical images. CT scanning and MRI (Magnetic Resonance Imaging) are well-known imaging tools in medical image processing. These tools are used for discovering the inner anatomy of the internal organs in a noninvasive manner. Bone cancer is a fatal disease that might target any bone of the body. Thus, the recognition of the cancerous regions in the affected bone is necessary. In this paper, the K-means clustering is used to initialize the cluster centroids of the generated images. This would help the Fuzzy c means to have logically distributed input centroids which has a positive effect on the resulted clusters in terms of the quality of results and time-saving. Three MRI images with various clusters numbers are used in the tests. In addition, morphological operations such as dilation and opening used after the extraction of the fine tumor regions in an effective manner.

K-means, Fuzzy C Means, Medical Image, Bone Tumor, Clustering.