Artificial Intelligence in Cardiac Imaging With Statistical Atlases of Cardiac Anatomy

Abstract

In many cardiovascular pathologies, the shape and motion of the heart provide important clues to understanding the mechanisms of the disease and how it progresses over time. With the advent of large-scale cardiac data, statistical modeling of cardiac anatomy has become a powerful tool to provide automated, precise quantification of the status of patient-specific heart geometry with respect to reference populations. Powered by supervised or unsupervised machine learning algorithms, statistical cardiac shape analysis can be used to automatically identify and quantify the severity of heart diseases, to provide morphometric indices that are optimally associated with clinical factors, and to evaluate the likelihood of adverse outcomes. Recently, statistical cardiac atlases have been integrated with deep neural networks to enable anatomical consistency of cardiac segmentation, registration, and automated quality control. These combinations have already shown significant improvements in performance and avoid gross anatomical errors that could make the results unusable. This current trend is expected to grow in the near future. Here, we aim to provide a mini review highlighting recent advances in statistical atlasing of cardiac function in the context of artificial intelligence in cardiac imaging.

Characterizing interactions between cardiac shape and deformation by non-linear manifold learning

“…The low-dimensional embedding of myocardial shape or motion/deformation has been thoroughly explored in research, as reviewed in (Gilbert et al, 2020;Duchateau et al, 2020). Nonetheless, shape and deformation should not be considered independently from each other.…”

Detection of abnormal left ventricular geometry in patients without cardiovascular disease through machine learning: An ECG‐based approach

“… 1 ML has the potential to radically change the way we practice cardiovascular medicine by providing new tools for interpreting data and making clinical decisions. While still a new player in cardiology, ML has already made its mark in clinical diagnostics 2 , 3 and research, 4 , 5 and continues to evolve rapidly. Physicians can leverage ML to make more accurate and prompt diagnoses, identify hidden opportunities to improve patient management, and avoid unnecessary spending.…”

“…Innovative solutions are needed to improve risk stratification of patients without established CVD, and ML may enable progress in this direction. clinical diagnostics 2,3 and research, 4,5 and continues to evolve rapidly. Physicians can leverage ML to make more accurate and prompt diagnoses, identify hidden opportunities to improve patient management, and avoid unnecessary spending.…”

Prediction of abnormal left ventricular geometry in patients without cardiovascular disease through machine learning: An ECG-based approach

“…1 AI techniques have the potential to radically change the way we practice cardiovascular medicine, providing new tools to interpret data and make clinical decisions. While still a new player in cardiology, ML has already made its mark in clinical diagnostics 2,3 and research 4,5 and continues to evolve rapidly. AI offers opportunities not only to physicians to make more accurate and prompt diagnoses, but it can also identify hidden opportunities to improve patient management and avoid unnecessary spending.…”