am1codes / brain-tumor-detection-using-cnn

This repository contains code to the detector that can detect Brain Tumor using MRI scans.

Brain-Tumor-Detection-Using-CNN

Our Goal

We need to predict whether or not a person has brain tumor by using the different MRI scans that we are provided with. We need to build a classifier that can classify between the 3 types of tumor present in our data and also tell us if a person does not have any tumor based on the images of the MRI scans.

Some information about the Data set

The data set was taken from Kaggle which contains two folders, one is for training and the other is for testing. I split the training set into training and validation set. It has 3 types of Brain Tumor - Glioma, Meningioma and pituitary along with images of patients with no tumor.
These are the different images of the types of Tumor present in our data.

Results

We were able to achieve an accuracy of 97% on the training set whereas on the validation set we have an accuracy of 95%. Overall the model is quite good considering the amount of data that was used to train it.