An improved Gabor wavelet transform and rough K-means clustering algorithm for MRI brain tumor image segmentation

Abstract

Image processing is significant in the medical field which provides detailed information about medical images and image segmentation is an essential part of medical image processing. In the medical field, various modalities have been utilized such as X-ray, CT scan and MRI, etc. MRI provides accurate results than other techniques. Our proposed technique is highly focused on tumor identification using MRI image segmentation. The proposed methodology consists of five stages namely, pre-processing, feature extraction, feature selection, classification, and segmentation. Initially, input MRI images are given to the preprocessing stage to fit the images for further processing. In this preprocessing phase, the input images are converted into a transform domain with the aid of Improved Gabor Wavelet Transform (IGWT). Then, GLCM related features are extracted and important features are selected with the help of the Oppositional fruit fly algorithm (OFFA). Then, the selected features are given to the support vector machine (SVM) classifier to classify an image as normal or abnormal. After the classification process, the abnormal images are selected and given to the segmentation process. For segmentation, in this paper, we utilized an effective rough k-means algorithm. The performance of the proposed methodology is evaluated in terms of Sensitivity, Specificity, and Accuracy. The experimental results show that our proposed method attained better results compared to existing work.