IDENTIFICATION OF HEAD AND NECK CANCER BY USING DECISION TREE CLASSIFIER?

Coregisteredfluoro-deoxy-glucose(FDG)positronemission tomography/computed tomography (PET/CT) has shown potential to improve the accuracy of radiation targeting of head and neck cancer (HNC) when compared to the use of CT simulation alone. The objective is to identify textural features useful in distinguishing tumor from normal tissue in head and neck via quantitative texture analysis of coregistered 18F-FDG PET and CT images. Abnormal and typical normal tissues are segmented from PET/CT images with HNC . Texture features including some derived from spatial grey-level dependence matrices (SGLDM) and neighborhood gray-tone-difference matrices (NGTDM) are selected for characterization of these segmented regions of interest (ROIs). The decision tree classifier is used to discriminate images of abnormal and normal tissues. The leave-one-out technique is used to validate the results.