Artificial Intelligence (AI)-Empowered Echocardiography Interpretation: A State-of-the-Art Review

Abstract

Echocardiography (Echo), a widely available, noninvasive, and portable bedside imaging tool, is the most frequently used imaging modality in assessing cardiac anatomy and function in clinical practice. On the other hand, its operator dependability introduces variability in image acquisition, measurements, and interpretation. To reduce these variabilities, there is an increasing demand for an operator- and interpreter-independent Echo system empowered with artificial intelligence (AI), which has been incorporated into diverse areas of clinical medicine. Recent advances in AI applications in computer vision have enabled us to identify conceptual and complex imaging features with the self-learning ability of AI models and efficient parallel computing power. This has resulted in vast opportunities such as providing AI models that are robust to variations with generalizability for instantaneous image quality control, aiding in the acquisition of optimal images and diagnosis of complex diseases, and improving the clinical workflow of cardiac ultrasound. In this review, we provide a state-of-the art overview of AI-empowered Echo applications in cardiology and future trends for AI-powered Echo technology that standardize measurements, aid physicians in diagnosing cardiac diseases, optimize Echo workflow in clinics, and ultimately, reduce healthcare costs.

Longitudinal Assessment of Global and Regional Left Ventricular Strain in Patients with Multisystem Inflammatory Syndrome in Children (MIS-C)

“…Additionally, though to our knowledge there have been no head to head comparisons of strain values generated by tablet-based portable devices versus cart-based echocardiographic devices, TOMTEC's vendor-independent calculations have been shown to have minimal differences between devices [9]. By harnessing the power of machine learning and artificial intelligence, software such as TOMTEC may pave the way for more widespread use of tablet-based ultrasound, thereby reducing costs and increasing accuracy, as some have speculated [29]. Finally, within our echocardiography laboratory, we also did an internal quality review of the studies obtained on our tablet during the acute pandemic phase and established that no critical information was compromised [30].…”

Application of AI in cardiovascular multimodality imaging

“…However, despite achievable advantages in image analysis and interpretation, AI may also guarantee wider access to care and help reduce the cost of undergoing testing via a primary imaging modality such as echocardiography [ 102 ].…”

Point-of-care ultrasound for critically-ill patients: A mini-review of key diagnostic features and protocols

“…Currently, there has also been increasing interest in the use of artificial intelligence that provides real-time guidance for probe placement, aids acquisition of optimal images[ 23 ], and helps to reduce exposure of healthcare workers to highly infectious cases[ 24 ]. Such technology has also been used to help users identify anatomy and do measurements of cardiac function[ 23 ]. Whether these algorithms are able to replace a trained sonographer, improve scan durations and accuracy, and improve healthcare delivery or patient outcomes remain uncertain.…”