Classification of Brain Tumor Types in MRI Scans Using Normalized Cross-Correlation in Polynomial Domain

Biomedical research in last decade or so has seen the development of highly accurate algorithms focused on the detection and classification of the brain tumor into malignant or benign. As a result of these advancements a new research direction has emerged which focuses on categorizing the brain tumors based on their types, such as Glioma, Metastases, and Meningioma etc. In this paper, we present a novel application of normalized cross-correlation in polynomial domain technique (predominately used in image registration) to classify Magnetic Resonance Image (MRI) of a brain into one of eight (8) different categories with high accuracy. The MRI scan is transformed into polynomial domain by first calculating its central moments and then fitting them to a 2nd order polynomial space. Experimental results show that the proposed approach provides very accurate and stable classification in real time.