Abstract
Brain tumor is one of the most dangerous disease. Therefore brain tumor detection should be fast and accurate. The automatic brain tumor tissue detection allows to localize the mass of tumor cells in the Magnetic Resonance Images (MRI). Several automatic methods are proposed for brain tumor tissue detection. Here propose a four-step procedure, which includes k-means clustering method, Hierarchical Centroid Shape Descriptor (HCSD), Feature extraction and classification method. The brain extraction is used as the preprocessing step in order to remove the skull and noise present in the MRI. The k-means clustering method segment the tumor with surrounding healthy tissue based on the pixel intensities. Hence the HCSD method is used to segment the tumor section alone. The features extracted from the segmented tumor region and then KNN classifier(k-nearest neighbour) method will verify the tumor by using the tumor features. This method will increase the accuracy of the automatic tumor detection system.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
