ML Based Model for Detection of Brain Tumor

Tumors are hazardous for human life present in any part of the body particularly present in the brain is dangerous to life. It is good to predict in the initial stages and treated to save the life. This paper presents a comprehensive solution for brain tumor prediction using deep learning and transfer learning techniques implemented in python with Tensor flow, Keras libraries and flask framework. The workflow encompasses data augmentation, model creation, training, testing and validation. The dataset, consisting of brain MRI images subjected to data augmentation to improve model performance. The pre-trained image dataset is employed as the backbone for feature extraction, followed by a custom dense layer for prediction of the tumor. The model is trained and evaluated over 15 epochs achieving a remarkable accuracy of approximately 94.94 in training and in testing the accuracy ranges around 90.0%. The model is trained to accept single MRI image from the image database for the prediction of the tumor.