Grade identification of astrocytoma using image processing — A literature review

摘要

Brain tumor grade identification is an invasive technique and clinicians rely on biopsy. Tumor grade (low/high) identification can be done on astrocytoma (brain tumor) using MRI, a non-invasive technique. Image segmentation, de-noising and feature extraction are the various techniques which are refined for segmenting the astrocytoma region using MRI images. Grey Level Co-occurrence Matrix (GLCM) is used for extracting the texture features from segmented tumor region. These features are then correlated with already saved features in the database. After that various classifiers are used to classify the MR images into (Low/High) grade Astrocytoma. The submitted approach of grade identification is estimated on the basis of various values such as severity, specificity and accuracy.