Morphological Image Processing Approach Using K-Means Clustering for Detection of Tumor in Brain

The brain is the anterior part of the central nervous system. Along with the spinal cord, it forms the central nervous system (CNS). Brain tumor is an abnormal growth caused by cells reproducing themselves in an uncontrolled manner. Magnetic resonance imaging (MRI) is the commonly used technique for diagnosis of brain tumors. In MRI, the amount of data obtained is very large to manually analyze and interpret. Segmentation is an important process in medical image analysis and it is a challenging problem due to noise present in the input images. Clustering is an efficient method for biomedical image segmentation. In this study, we propose to use K-means clustering algorithm under Morphological Image Processing (MIP). The input to this algorithm is an MR image of the human brain. The position of tumor objects is detected from an MR image by using a clustering algorithm. This enhances the tumor boundaries more precisely and the performance is evaluated based on execution time and accuracy of the algorithms. It produces the reliable results that are less sensitive to error.