Brain Tumor Detection Using Image Processing

Rutuja Surve; Chinmay Bhat; Janvi Ambre; Sujata Bhairnallykar

doi:10.37591/jocta.v13i2.925

Abstract

Brain tumor means the aggregation of abnormal cells in some tissues of the brain. Brain tumor can be cancerous or noncancerous. The most common types of brain tumors are Glioma, Meningioma and Pituitary tumor. Early detection of tumor cells is essential in-patient treatment and recovery. A brain tumor is typically diagnosed through a lengthy and complicated process. The MRI images of various patients at various stages can be used for the detection of tumors. It is possible to segment the brain tumor from processed MRI pictures. With the help of several image segmentation techniques, these tumors can be segmented. There are various types of feature extraction and classification methods which are used for detection of brain tumor from MRI images. Convolutional Neural Network image classification algorithm helps in detecting the tumor at early stage with high accuracy. We proposed a neural network architecture for detection of tumor cells which gives high accuracy.