Brain Tumor Detection Using Adaptive K-Means Clustering Segmentation

Abstract

Magnetic resonance imaging (MRI) is widely preferred technique to access the Brain tumor, But Due
to large amount of data produced by MRI prevents manual segmentation in a reasonable time. So, efficient segmentation
methods are required for MRI Brain tumor detection. The watershed transform has interesting property and is popular
that make it useful for many segmentation application. The drawback associated with watershed transform is the over
segmentation which results in MRI brain image. In this paper an adaptive K-Means clustering algorithm is used for
detection of brain tumor on segmentation and morphological operator. The proposed method allows the segmentation of
tumor tissues with accuracy compared to manual segmentation. The quantitative and visual segmentation result shows
the superiority of the proposed method.