Artificial intelligence in cardiovascular imaging: state of the art and implications for the imaging cardiologist

Abstract

Healthcare, conceivably more than any other area of human endeavour, has the greatest potential to be affected by artificial intelligence (AI). This potential has been shown by several reports that demonstrate equal or superhuman performance in medical tasks that aim to improve efficiency, diagnosis and prognosis. This review focuses on the state of the art of AI applications in cardiovascular imaging. It provides an overview of the current applications and studies performed, including the potential value, implications, limitations and future directions of AI in cardiovascular imaging.

Heart teams in the Netherlands: From teamwork to data‑driven decision-making

“…Strict guidelines for the information required to enter the process and objective interpretation of images based on algorithms and machine learning can prevent wasting time debating the interpretation and the need to assemble all the experts [4][5][6][7]. Possibilities include image recognition, natural language processing and decision support systems [19]. Other technological advancements for the heart team include 3D printing of devices or valvular heart disease, wearable patient technology for monitoring and big-data analytics.…”

The history of transcatheter aortic valve implantation: The role and contribution of an early believer and adopter, the Netherlands

“…2 and 3. Beyond the analysis of outcomes and the underlying mechanisms in single, multicentre national and international initiatives and collaborations, research has been initiated to elucidate and predict the interaction between the device and host as well as the role of Artificial Intelligence in TAVI [26][27][28][29][30][31][32][33][34][35]. The clinical drive of innovation providing the best possible care to the individual patient and the scientific work (volume and content) of all Dutch medical professionals is an expression of the stimulating environment in which they have the pleasure to live and work.…”

Deep learning reveals 3D atherosclerotic plaque distribution and composition

“…Deep learning has in recent years revolutionized automated image classification and object detection methods 20 – 23 . The field of radiology has a long history of applying deep learning 24 – 26 , in recent years the technology has also been combined with LSFM to enhance the segmentation of labelled structures 13 , 27 , 28 . Here we apply deep learning in two steps of our workflow: we divide the aorta into different anatomical segments and in each of them quantify individual atherosclerotic plaque objects and their volume.…”