Myocardial perfusion imaging (MPI) is one of the most commonly ordered cardiac imaging tests, with prominent clinical roles for disease diagnosis and risk prediction. The potential applications of artificial intelligence (AI) to MPI, by single photon emission computed tomography (SPECT) or positron emission tomography (PET), have been increasing exponentially.1 These algorithms could be applied at any point along the typical MPI workflow in order to improve the overall clinical utility, from image acquisition through to clinical reporting and risk estimation as shown in Figure 1. Given the rapidly expanding evidence base, it is difficult even for clinicians and researchers in the field to stay up to date with the latest applications of AI.

This review presents an updated perspective for clinicians and researchers, highlighting recently described approaches in the application of AI to MPI. We summarize recent AI approaches for image reconstruction which could be used to improve image quality or reduce radiation exposure as well as methods to provide correction for soft-tissue attenuation. We also discuss algorithms which leverage the vast array of clinical, stress, and imaging information available from MPI to predict the presence of obstructive coronary artery disease (CAD) and predict risk. We will focus on recent AI applications which can maximize clinical information. Finally, we will delve into the future prospects and directions for AI advancements in MPI obtained from available computed tomography (CT) imaging obtained with hybrid MPI.