MRI Brain Image Segmentation Using Enhanced Adaptive Fuzzy K-Means Algorithm

Medical images are widely used to plan further treatment for the patient. However, the images sometimes are corrupted with a noise, which normally exists or occurs during storage or while transferring the image. Therefore, the need to enhance the image is crucial in order to improve the image quality. Segmentation techniques for Magnetic Resonance Imaging (MRI) of the brain are one of the methods used by radiographer to detect any abnormality that has happened specifically for the brain. The method is used to identify important regions in brain such as white matter (WM), grey matter (GM) and cerebrospinal fluid spaces (CSF). The clustering method known as Enhanced Adaptive Fuzzy K-means (EAFKM) is proposed to be used in this project as a tool to classify the three regions. The results are then compared with fuzzy C-means clustering (FCM) and adaptive fuzzy k-means (AFKM).The segmented image is analyzed both qualitative and quantitative. The proposed method provides better visual quality of the image and minimum Mean Square Error.