Deep Learning Methods for Medical Image Computing

Medical images play a key role in the daily work of doctors such as radiologists and physicians. When visual examination is infeasible, they rely on medical images for the detection, diagnosis, and treatment of diseases. Therefore, one way to improve the clinical healthcare is to present and analyze medical images more efficiently and intelligently. On the one hand, it means to find efficient ways to acquire high quality medical images that can readily be used by healthcare providers. On the other hand, it means to find intelligent ways to analyze medical images to facilitate the healthcare delivery. It is natural for researchers and medical professionals to seek help from computer-aided systems for better leveraging of medical images. Computers are particularly good at data-intensive, repetitive and computational tasks. It not only has the potential to unleash doctors from the tedious and laborious work of medical image acquisition and annotation, but also may help to prevent human errors in medicine. However, when it comes to design computer-aided systems for complicated tasks, high-level understanding of