Detection and Classification of Brain cancer using BPNN and PNN

There are over 120 types of brain and central nervous system tumors. Brain tumor is one of the major causes of death among people. It is evident that the chances of survival can be increased if the tumor is detected and classified correctly at its early stage. Magnetic resonance (MR) imaging is currently an indispensable diagnostic imaging technique in the study of the human brain. A brain tumor is defined as an abnormal growth of cells within the brain or the central spinal canal. So tumor detection needs to be fast enough as the patient cannot recover if the damage is more than 50%. For detecting this tumor CT or MRI scan is done. This CT or MRI scan images are taken for this project to process it. This paper presents the artificial neural network approach namely Back propagation network (BPNs) and probabilistic neural network (PNN). It is used to classify the type of tumor in CT or MRI images of different patients with Astrocytoma type of brain tumor. K-means clustering method have been developed for detection of the tumor in the CT or MRI images. Gray Level Co-occurrence Matrix (GLCM) is used to achieve the feature extraction. The whole system worked in two modes firstly Training/Learning mode and secondly Testing/Recognition mode finally gets a classified output.