文章基本信息

标题：AN EFFECTIVE TECHNIQUE FOR BRAIN TUMOUR SEGMENTATION AND DETECTION USING CUCKOO-BASED NEURO-FUZZY CLASSIFIER
本地全文：下载
作者：RAMESH BABU VALLABHANENI ; V. RAJESH
期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2014
卷号：70
期号：2
出版社：Journal of Theoretical and Applied
摘要：In this paper, we have proposed a robust technique to detect and classify the tumour part from medical brain images. In recent times, a number of image segmentation and detections techniques have been proposed in the literature. But, the detection of brain tumour through the help of classification technique has received significant interest among the research community. By considering the above issue, here, we combine three different techniques such as, cuckoo search, neural network and fuzzy classifier to detect the tumour part effectively. Our proposed approach consists of four phases, such as, pre-processing, region segmentation, feature extraction and classification. In the pre-processing phase, the anisotropic filter is used for reducing the noise and in the segmentation process; K-means clustering technique is applied. For the feature extraction, the parameters such as contrast, energy and gain are extracted. In classification, a modified technique called Cuckoo-Neuro Fuzzy (CNF) algorithm is developed and applied to detection of tumour region. In the modified algorithm, cuckoo search algorithm is employed for training the neural network and the fuzzy rules are generated according to the weights of the training sets. Then, classification is done based on the fuzzy rules generated. Experimental results shows that the proposed technique achieved the accuracy of 79.49% but existing technique achieved only 76.92%.
关键词：CNF; Contrast; Energy; Entropy; K-Means; Anisotropic Filter; Sensitivity; Specificity; Accuracy