Artificial Intelligence in Musculoskeletal Medical Imaging

Deep learning and especially convolutional neural networks (CNN) have established themselves as state-of-the-art methods in the field of image and object detection throughout the last decade. In healthcare they are successfully used, for example, to detect skin or breast cancer, where they reach the level of an expert opinion. In musculoskeletal imaging, there is a wide range of tasks which can be taken over by machine learning methods. While there are many advanced algorithms in the field of two-dimensional imaging (X-rays) showing strong performances, machine learning in three-dimensional imaging (e.g., computed tomography) shows promising results yet is at an earlier stage. This chapter gives an overview of current applications in two- and three-dimensional medical imaging and also highlights some ethical, moral, legal, and socio-economic aspects of this rapidly progressing field.