MRI Image Segmentation using Morphological Enhancement and Noise Removal based on Fuzzy C-means

Fuzzy C-means (FCM) is one of the image segmentation algorithms that has been widely used and proven to have good performance in image segmentation. This study aims to examine the effect of pre-processing stages on the FCM algorithm to segment the MRI image especially to detect brain tumors. This research proposed a pre-processing method with opening and closing morphology technique, noise removal with Weiner filter and contrast enhancement. The morphological method is used to connect the pixels adjacent. The morphological method used is opening and closing, because it can minimize the noise that is in the image by connecting the pixels are adjacent. Furthermore, noise removal and contrast enhancement are used to complete the morphological stage to produce MRI images that have less noise but are detailed. Based on the experimental results proved that the combination of pre-processing methods can improve the results of segmentation so that the tumor objects can be detected more accurately, where the accuracy is 73.585%.