Applications of artificial intelligence in cardiovascular imaging

Research into artificial intelligence (AI) has made tremendous progress over the past decade. In particular, the AI-powered analysis of images and signals has reached human-level performance in many applications owing to the efficiency of modern machine learning methods, in particular deep learning using convolutional neural networks. Research into the application of AI to medical imaging is now very active, especially in the field of cardiovascular imaging because of the challenges associated with acquiring and analysing images of this dynamic organ. In this Review, we discuss the clinical questions in cardiovascular imaging that AI can be used to address and the principal methodological AI approaches that have been developed to solve the related image analysis problems. Some approaches are purely data-driven and rely mainly on statistical associations, whereas others integrate anatomical and physiological information through additional statistical, geometric and biophysical models of the human heart. In a structured manner, we provide representative examples of each of these approaches, with particular attention to the underlying computational imaging challenges. Finally, we discuss the remaining limitations of AI approaches in cardiovascular imaging (such as generalizability and explainability) and how they can be overcome. In this Review, Sermesant and colleagues discuss the applications of artificial intelligence (AI) in cardiovascular imaging and explain how pre-existing clinical knowledge can be included in AI methods to increase robustness. They also discuss the limitations of AI approaches in cardiovascular imaging and how they can be overcome. Artificial intelligence (AI) algorithms have shown impressive results in specific and often time-consuming cardiovascular imaging tasks such as image segmentation, anomaly detection and patient selection; however, these applications are limited to specific tasks in the clinical workflow. In cardiovascular imaging, AI algorithms are often purely data-driven but can be improved when associated with biophysical models of the heart, which enables the integration of pre-existing knowledge of human anatomy and physiology. A bottleneck in AI applications often lies in the collection of imaging data and their annotation by experts, which is limited by the lack of resources and expertise; therefore, the creation of large databases must be a community effort. The appropriate integration of AI algorithms into clinical workflows remains an unresolved problem; important security, privacy and explainability issues must be resolved to achieve a sufficiently high level of trust. AI algorithms have the potential to enrich the amount and the robustness of information extracted from cardiac images, while at the same time redistributing physician time and work towards patient interaction and complex decision-making tasks.