Brain tumor detection and segmentation using a wrapper based genetic algorithm for optimized feature set

The work here intends to develop an algorithm for optimizing the available feature set for identifying tumor from brain MRI images. A set of features are selected based on texture features. From the large set of features relevant features would be selected using wrapper approach. Further, an optimized subset of the relevant features is generated with the help of Genetic Algorithm. The machine learning with support vector machine algorithm is used for detection and segmentation of tumors in the brain MRI image acquired. The superiority of the algorithm is established by comparing it with the state of the art algorithms such as level set method and fuzzy based methods. The authors are using performance measurement tools including manual segmentation and volume based tools for validating the claim.