Artificial Intelligence in Medical Imaging

Artificial intelligence (AI) in cancer image interpretation continues to evolve with complementary advances in image acquisition systems, imaging protocols, and machine learning tools, as well as expanding clinical tasks. AI can be defined as having computers simulate the conduction of human intelligence tasks. Advances in computers, in terms of both computing power and memory capacity, have led to a rapid increase in assessing the potential use of AI in various tasks in medical imaging, going beyond the initial use in computer-aided detection (CADe) to include diagnosis, prognosis, response to therapy, and risk assessment, as well as in cancer discovery. AI methods are being developed for CADe and computer-aided diagnosis (CADx), for computer-aided triaging (CADt), and sometimes for use as autonomous readers, often with the need for consideration for effect on radiologists’ perception/cognitive performance and workflow. While the prospects of AI in medical image interpretation are abundant and promising, they bring along challenges and limitations. This chapter focuses on the role of AI in medical image interpretation.