Brain Tumor Categorization

Abstract

A Brain Tumor is an uncontrolled development of brain cells in brain cancer if not detected at an early stage. Early brain tumor diagnosis plays a cruicial role in treatment planning and patient’s survival rate. There are distinct forms, properties and therapy of brain tumors. Therefore manual brain tumor detection is complicated, time consuming and vulnerable in errors. Hence automated computer diagnosis system is initialized for it and is currenty in demand. This article presents segmentation through ANN architecture and the dataset is from Kaggle. The preprocessing and data augmentation concept were introduced to enhace the classification rate. The binary classification of brain tumor is performed using ANN learning through transfer learning.Results thus obtained exhibited that the proposed research framework performed better than reported in state of the art