An overview of deep learning in medical imaging focusing on MRI
Contributors: Alexander Selvikvåg Lundervold and Arvid Lundervold
What has happened in machine learning lately, and what does it mean for the future of medical image analysis? Machine learning has witnessed a tremendous amount of attention over the last few years. The current boom started around 2009 when so-called deep artificial neural networks began outperforming other established models on a number of important benchmarks. Deep neural networks are now the state-of-the-art machine learning models across a variety of areas, from image analysis to natural language processing, and widely deployed in academia and industry.
These developments have a huge potential for medical imaging technology, medical data analysis, medical diagnostics and healthcare in general, slowly being realized. We provide a short overview of recent advances and some associated challenges in machine learning applied to medical image processing and image analysis. As this has become a very broad and fast expanding field we will not survey the entire landscape of applications, but put particular focus on deep learning in MRI.
Deep learning: Traditionally, machine learning models are trained to perform useful tasks based on manually designed features extracted from the raw data, or features learned by other simple machine learning models. In deep learning, the computers learn useful representations and features automatically, directly from the raw data, bypassing this manual and difficult step. By far the most common models in deep learning are various variants of artificial neural networks, but there are others. The main common characteristic of deep learning methods is their focus on feature learning: automatically learning representations of data. This is the primary difference between deep learning approaches and more “classical” machine learning. Discovering features and performing a task is merged into one problem, and therefore both improved during the same training process. See ,  for general overviews of the field.
Deep Learning in Medical Imaging: In medical imaging the interest in deep learning is mostly triggered by convolutional neural networks (CNNs) ,14 a powerful way to learn useful representations of images and other structured data. Before it became possible to use CNNs efficiently, these features typically had to be engineered by hand, or created by less powerful machine learning models. Once it became possible to use features learned directly from the data, many of the handcrafted image features were typically left by the wayside as they turned out to be almost worthless compared to feature detectors found by CNNs. There are some strong preferences embedded in CNNs based on how they are constructed, which helps us understand why they are so powerful.
Healthcare providers generate and capture enormous amounts of data containing extremely valuable signals and information, at a pace far surpassing what “traditional” methods of analysis can process. Machine learning therefore quickly enters the picture, as it is one of the best ways to integrate, analyze and make predictions based on large, heterogeneous data sets. Healthcare applications of deep learning range from one-dimensional biosignal analysis and the prediction of medical events, e.g. seizures and cardiac arrests, to computer-aided detection and diagnosis supporting clinical decision making and survival analysis, to drug discovery and as an aid in therapy selection and pharmacogenomics, to increased operational efficiency, stratified care delivery, and analysis of electronic health records.