期刊名称：International Journal of Computer Science and Information Technologies
电子版ISSN：0975-9646
出版年度：2015
卷号：6
期号：5
页码：4829-4832
出版社：TechScience Publications
摘要：Last decade has seen lots of research in automatic brain tumour classification by using metabolite lipids like NAcetylasparate, Creatine and Choline values from Magnetic Resonance Spectroscopy (MRS) graphs. Accurate identification of the type of the brain abnormality is highly essential since the treatment planning is different for all the brain abnormalities. Any false detection may lead to a wrong treatment which ultimately leads to fatal results. Early detection and diagnosis of brain tumour can reduce fatality to an extent. This research aims at supporting clinicians in preliminary decision making. It does the same by improving the accuracy of the classifiers by significantly reducing false positives .The classifiers employed are Naïve Bayes Classifier, Random Tree and Instance based classifier. The maximum classification accuracy of around 95%-100% is achieved.
