An improved pre-processing technique with image mining approach for the medical image classification

The proposed system mainly concentrates on the diagnosis of brain tumor from the CT-Scan (Computerized Tomography) brain images. This work gives the neuroradiologist a second option for the easy identification of tumor cells from the brain image. The important data mining concept that has been included in the proposed work consists of pre-processing of the CT-Scan brain image. The method used for pre-processing includes Shape priori technique. The feature selection from the brain image has been done using the association rule mining. The rules generated for extracted features are stored in the transactional database have been classified using the data mining concept called Decision Tree Classification. The combination of both the association rule mining and the decision tree classification gives the high degree of accuracy and efficiency for the proposed system.