Brain Tumor Segmentation in MRI images using unsupervised Artificial Bee Colony algorithm and FCM clustering

Tumor Segmentation of MRI Brain images is still a challenging problem. The paper proposes a fast MRI Brain Image segmentation method based on Artificial Bee Colony (ABC) algorithm and Fuzzy-C Means (FCM) algorithm. The value in continuous gray scale interval is searched using threshold estimation. The optimal threshold value is searched with the help of ABC algorithm. In order to get an efficient fitness function for ABC algorithm the original image is decomposed by discrete wavelet transforms. Then by performing a noise reduction to the approximation image, a filtered image reconstructed with low-frequency components, is produced. The FCM algorithm is used for clustering the segmented image which helps to identify the brain tumor.