Brain Tumour Classification using Convolutional Neural Network

Abstract

In this extended abstract, we address the problem of classifying MRI images of di?erent brain tumours to facilitate the development of an automated system for early brain cancer detection. In particular, we adapt the convolutional neural network based on the AlexNet architecture to develop a model that achieves a classi?cation accuracy of 97.5% on average on a real-world dataset containing MRI images of healthy brains and three di?erent kinds of tumours.