Application of artificial intelligence in cardiac CT: From basics to clinical practice

Abstract

Research into the possibilities of AI in cardiac CT has been growing rapidly in the last decade. With the rise of publicly available databases and AI algorithms, many researchers and clinicians have started investigations into the use of AI in the clinical workflow. This review is a comprehensive overview on the types of tasks and applications in which AI can aid the clinician in cardiac CT, and can be used as a primer for medical researchers starting in the field of AI. The applications of AI algorithms are explained and recent examples in cardiac CT of these algorithms are further elaborated on. The critical factors for implementation in the future are discussed.

Radiomics in Cardiovascular Disease Imaging: from Pixels to the Heart of the Problem

“…Another application of ML, especially DL, is represented by improvements in image acquisition. Specifically, DL models may be trained to reduce image noise, artifacts, radiation dose, and inter-and intra-observer variation of measurements [78]. For instance, ML has been used to improve echocardiography acquisition, facilitating access to this imaging modality in the emergency setting.…”

Integration of artificial intelligence into clinical patient management: focus on cardiac imaging

“…DL methods have been applied to learn with low-dose CT images and reconstruct them to routine-dose CT images, synthesize contrast CT images from non-contrast images, reduce noise in low-dose CT scans, enable lower-dose CT and sparse-sampling CT; and reduce metal artifacts. 24 These examples of AI contributions to image acquisition will prove valuable in medical education, time-efficiency, cost-reduction, and patient safety.…”

La integración de la inteligencia artificial en el abordaje clínico del paciente: enfoque en la imagen cardiaca

“…22 CT has also seen promising advances from ML aimed at speeding up reconstruction times, but also at reducing radiation dose. DL methods have been applied to learn with low-dose CT images and reconstruct them to routine-dose CT images, synthesize contrast CT images from non-contrast images, reduce noise in low-dose CT scans, enable lower-dose CT and sparse-sampling CT; and reduce metal artifacts 23 . These examples of AI contributions to image acquisition will prove valuable in medical education, time-efficiency, cost-reduction, and patient safety.…”