In 2012, a method based on deep convolutional neural networks won the Stanford ImageNet Challenge for computer vision object identification by a wide margin, almost halving the error rate from the previous year. Since then, excitement about the power of deep networks has per-vaded all aspects of artificial intelligence, including healthcare. Radiology is a field ripe for inno¬va¬tion with these techniques. In this talk, I will discuss the various ways AI, and in particular deep learning, has and will impact the radiology value chain, from the construction of new imaging machines, through image acquisition, to automated diagnosis, focusing on our recent work on deep learning-based image transformation and radiation dose reduction. Medical imaging in the future will be quite different than it is today, more valuable and more cost-efficient, and will accrue benefits for many stakeholders, including patients, radiologists, hospitals, imaging centers, and healthcare systems.
Back to Deep Learning and Medical Applications