期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2015
卷号：3
期号：5
DOI：10.15680/ijircce.2015.0305162
出版社：S&S Publications
摘要：In the analysis of Medical images for computer-aided diagnosis and treatment, segmentation is requiredas a primary stage. Medical image segmentation is a complex and challenging task due to the intrinsic nature of theimages. The brain has particularly complex structure and its precise segmentation is very useful for detecting tumors,edema, and necrotic tissues, in order to prescribe related therapy. Magnetic resonance imaging (MRI) is an importantdiagnostic imaging technique for the early detection of abnormal changes in tissues and organs. MRI Imaging formsone of the core methods to identify Brain Tumors, and access the existence, size and volume of the tumor. Clusteringis one of the widely used image segmentation techniques which divide patterns in such a way that samples of the samegroup are more similar to one another than samples belonging to different groups. Use of Genetic Algorithm withOPTICS method will extract the tumor more accurately then compare to other segmentation method. This paperpresents review on some of segmentation methods based on clustering and Region Based with their advantages anddisadvantages. Here, also include various measurements like Sensitivity, Specificity and Accuracy of tumor.
