Artificial Intelligence in Cardiovascular Imaging

Abstract

Data science is likely to lead to major changes in cardiovascular imaging. Problems with timing, efficiency, and missed diagnoses occur at all stages of the imaging chain. The application of artificial intelligence (AI) is dependent on robust data; the application of appropriate computational approaches and tools; and validation of its clinical application to image segmentation, automated measurements, and eventually, automated diagnosis. AI may reduce cost and improve value at the stages of image acquisition, interpretation, and decision-making. Moreover, the precision now possible with cardiovascular imaging, combined with "big data" from the electronic health record and pathology, is likely to better characterize disease and personalize therapy. This review summarizes recent promising applications of AI in cardiology and cardiac imaging, which potentially add value to patient care.

Towards a personalised approach in exercise-based cardiovascular rehabilitation: How can translational research help? A ‘call to action’ from the Section on Secondary Prevention and Cardiac Rehabilitation of the European Association of Preventive Cardiology

“…These techniques, grouped under the term 'machine learning', can be either supervised (the user determines the relation between subjects) such as traditional regression analysis, or unsupervised (the computer determines the relation between subjects) such as clustering analysis. 132,133 Some of these novel techniques have already been applied to translational exercise research. In 2009, Goud et al set up a cluster-randomised trial in 21 CR centres, comparing effects of a computerised decision support system to standard care.…”

“…Imaging is especially suited for the application of machine learning because images contain a rich amount of data both within the image itself and through the extraction of quantitative features. 132 Furthermore, powerful computational approaches to handle image data have undergone extensive development within academic clinical research and non-medical fields such as facial recognition and image searching. 141 Combined with the recent availability of large imaging datasets, 142 this has meant that artificial intelligence approaches to identify images, automatically quantify image features and predict disease from the patterns in the image have developed rapidly within cardiology and radiology.…”

Artificial Intelligence in the Management of Intracranial Aneurysms: Current Status and Future Perspectives

“…Finally, it is necessary to further validate the usefulness of ML models in real-world practice. 10 Traditional ML algorithms predefine engineered features that can describe the patterns inherent in regions of interest with explicit parameters based on expert knowledge. Support vector machines (SVM) and random forests are classic ML techniques.…”

Diagnostic evaluation of chest pain

“…81,82 Rest myocardial perfusion CT and fractional flow reserve CT appear promising to further improve the diagnostic yield by evaluating the functional consequence of a stenosis. 83,84 A fractional flow reserve CT-guided strategy has been associated with fewer unnecessary invasive coronary angiograms in patients with new-onset chest pain. 85 Delayed enhancement CT may be used to visualize scar similar to delayed enhancement CMR.…”

“…Novel insights from artificial intelligence combined with big data will help the clinician with automated measurements, finding the correct diagnosis and estimating future adverse events. 84 A recent study showed that machine learning (combining CTA and clinical data) performs significantly better in predicting 5 year prognosis when compared to a visual CTA assessment and established clinical risk scores in patients with suspected coronary artery disease. 85 It is expected, that future scanning reports will be extended with estimates of disease and risk of adverse outcome based on automated analyses and report information on pulmonary emphysema index, bone density, epicardial fat, left ventricular mass, extracellular cardiac fibrosis, vascular calcifications, aneurysms, liver fat, (cardiac) incidentalomas, etc.…”