Identifying Grades of Glioma using Support Vector Machine Recursive Feature Elimination

Main Article Content

N.Suresh Kumar
Dr.S.Margret Anouncia


The objective of this research is to classify glioma-a type of brain tumor, according to their grades by combining various classification
methods and conventional magnetic resonance imaging. Determining Gliomas grades falls under the category medical image analysis. Image
analysis includes the following: ROI definition (extraction), feature selection and classification. Feature selection till date is done using SVMRFE
algorithm. SVM-RFE stands for Support Vector Machine- Recursive Feature Elimination. But this algorithm can only classify glioma grade
II, IV. The extracted feature of grade III is similar to the features of grade II or grade IV. Hence, they are either classified as grade II or grade IV.
This paper aims at improving the existing classification method so as to identify grade III as well. Also in the existing systems the ROI
extraction is done manually. Hence, the existing systems are semi-automatic. This work also aims at designing a fully automated system.


Keywords: conventional Magnetic Resonance Imaging, Classification Methods, ROI definition SVM-RFE


Download data is not yet available.

Article Details