Optimal Spatial Fuzzy Clustering Algorithm Based ROI Segmentation in Ultrasound Kidney Images

The main intention of this proposed methodology is to segment the ultrasound image abnormalities (ROI region). Segmentation of ultrasound image is difficult due to discontinuity and uncertainty of segmentation boundaries caused by speckle noise. Most of the ultrasound image segmentation algorithms require high computational time and do not give good results. The fuzzy c-means (FCM) method has been one of the widely used techniques for image segmentation, but this method is sensitive to noise. Therefore, in this paper, we propose an ultrasound image segmentation approach using optimal spatial fuzzy c-means algorithm (OSFCM). Here, the centroid value is selected optimally using grey wolf optimization (GWO). The proposed system consists of three modules such as (i) preprocessing, (ii) classification and (iii) segmentation. In the pre-processing stage, the speckle noise is removed using hybridization of optimal wavelet and bilateral filter. In the classification stage, the ultrasound images are classified as normal, cyst, stone and tumor using the artificial neural network (ANN). In the segmentation stage, the ROI regions of abnormal images are segmented using optimal spatial fuzzy c-means algorithm (OSFCM). The experimentation results show that the proposed system attains the better result associated with the available methods.