Optimized bilevel classifier for brain tumor type and grade discrimination using evolutionary fuzzy computing

Abstract

In this paper, an optimized bilevel brain tumor diagnostic system for identifying the tumor type at the firstlevel and grade of the identified tumor at the second level is proposed using genetic algorithm, decision tree, and fuzzyrule-based approach. The dataset is composed of axial MRI of brain tumor types and grades. From the images, variousfeatures such as first and second order statistical and textural features are extracted (26 features). In the first level,tumor type classification was done using decision tree constructed with all features. Further evolutionary computingusing genetic algorithms (GA) was applied to select the optimal discriminating feature set (5 features) and classificationusing the decision tree constructed with the reduced feature set resulted in better performance. In the second level, gradeclassification, a fuzzy rule-based approach was used to resolve the uncertainty in discriminating the tumor grades II andIII. Membership functions of all grades were defined for all features extracted from brain tumor grade images, to derivethe fuzzy inference rules for grade discrimination. Similar to type classification with GA, better grade discriminationperformance was exhibited with fuzzy inference rules derived using optimal feature set (13 features) using GA. Overallperformance comparison of the proposed bilevel classifier with all features vs GA-based feature selection, shows thatevolutionary computing combined with fuzzy rule -based approach is successful in reducing false positives, therebyenhancing classifier performance.