Deep learning for medical image analysis: A brief introduction

Abstract

Advances in deep learning have led to the development of neural network algorithms which today rival human performance in vision tasks, such as image classification or segmentation. Translation of these techniques into clinical science has also significantly advanced image analysis in neuro-oncology. This has created a need in the neuro-oncology community for understanding the mechanisms behind neural networks and deep learning, as close interaction of computer scientists and neuro-oncology researchers as well as realistic expectations about the possibilities (and limitations) of the current state-of-The-Art is pivotal for successful translation of deep learning techniques into practice. In this review, we will briefly introduce the building blocks of neural networks with a particular focus on convolutional neural networks. We will explain why these networks excel at identifying relevant features and how they learn to associate these imaging features with (clinical) features of interest, such as genotype, or how they automatically segment structures of interest in the image volume. We will also discuss challenges for the more widespread use of these algorithms.