INVESTIGATION ON CLUSTERING ALGORITHMS IN MRI IMAGES

Abstract

Brain tumor is an accumulation of abnormal cells in the brain. Detection of tumor from magnetic resonance imaging (MRI) brain scan is one of the most promising research topics in medical image processing. This paper presents a novel tumor detection system in MRI images using k-means technique integrated with Fuzzy c-means (FCM) clustering algorithm and artificial neural network (ANN). ANN is used to classify the MRI images into two categories; normal and tumor image. The proposed system takes benefit of both integrated algorithms in the aspect of minimal computation time and accuracy. The method proposed in this paper is fuzzy c-means (FCM) and is compared with K-Means segmentation. Followed by tumor detection which will display the presence of a tumor as Abnormal brain whereas the absence of tumor as a normal brain. In the different clusters obtained, it shows different elements of the brain such as white matter, gray matter, edema and CSF (Cerebrospinal fluid) and tumor. A user-friendly environment is created by using GUI in MATLAB which in turn saves the precious time of doctor to diagnose the tumor automatically. Performance analysis using various parameters such as PSNR, Global Consistency error (GCE), Variation of Information (VOI), area, elapsed time, reproducibility, and Rand Index (RI) is done.