Robust fuzzy RBF network based image segmentation and intelligent decision making system for carotid artery ultrasound images

In this paper, a robust image segmentation and intelligent decision making system for carotid artery ultrasound images is proposed. Medical images may have various types of inherent degradations due to imaging equipments, operating environment, etc. For instance, carotid artery ultrasound images are affected by low resolution, speckle noise, and wave interferences. Hence, robust medical image clustering technique is inevitable for obtaining accurate results in the subsequent stages. In this context, a robust fuzzy radial basis function network (RFRBFN) technique is proposed. The proposed technique modified fuzzy RBF algorithm by incorporating spatial information and a smoothing parameter into its objective function, consequently, the proposed technique is able to cope with noise related variations. To assess the effectiveness, the RFRBFN technique is applied to segment carotid artery ultrasound images and its performance has been evaluated against impulse, and Gaussian noises of various intensities. Performance comparison with existing methods shows that the proposed RFRBFN outperforms the existing fuzzy based c-means and RBF techniques in case of both noisy and noise-free images. Experiments on 200 real carotid artery ultrasound images reveal the proposed technique offers effective segmentation results. Finally, intima-media thickness is measured from the obtained segmented images and multi-layer backpropagation neural network is employed to classify the segmented images into normal or diseased subjects. The proposed intelligent decision making system can thus be used as a secondary observer for identification of plaque in the carotid artery.