Cardiovascular disease remains the most common cause of morbidity and mortality worldwide, and thus an important focus for medical research and medical imaging. Despite continuous advances in cardiac imaging modalities, including echocardiography, cardiovascular magnetic resonance and cardiac computed tomography, the heart remains a challenging organ to image, in particular due to its perpetual motion. Other challenges faced by cardiac imaging include respiratory motion, complex geometry of the ventricles and atria, variability in imaging conditions and protocols, oblique orientation of the heart with respect to the body, and the small size of some of the cardiac structures, including the coronary arteries, trabeculae and papillary muscles.
In the last decade, several initiatives have been established to collect large-scale databases of cardiac images, such as the Framingham Heart Study, the Multi-Ethnic Study of Atherosclerosis and the UK Biobank. In this context, artificial intelligence (AI), particularly machine learning for artificial neural networks and computer vision, has emerged as one of the most promising topics in cardiac imaging research. Combined with the exponential increase in computing power, AI provides unprecedented opportunities to leverage the available large collections of cardiac imaging data for developing more robust cardiac image analysis algorithms, to uncover currently unknown clinical knowledge on cardiac health and disease, and to build novel software tools that will impact clinical cardiology.
This Research Topic will provide comprehensive reviews of the recent advances and potential impact of AI for a range of cardiac imaging applications, particularly cardiac image acquisition, automated cardiac quantification, cardiac tissue characterization, imaging biomarker discovery, and clinical decision support in cardiology. These papers will also be aimed at discussing current challenges and future opportunities of AI in cardiac imaging, and to promote new cutting-edge research in the field.
Cardiovascular disease remains the most common cause of morbidity and mortality worldwide, and thus an important focus for medical research and medical imaging. Despite continuous advances in cardiac imaging modalities, including echocardiography, cardiovascular magnetic resonance and cardiac computed tomography, the heart remains a challenging organ to image, in particular due to its perpetual motion. Other challenges faced by cardiac imaging include respiratory motion, complex geometry of the ventricles and atria, variability in imaging conditions and protocols, oblique orientation of the heart with respect to the body, and the small size of some of the cardiac structures, including the coronary arteries, trabeculae and papillary muscles.
In the last decade, several initiatives have been established to collect large-scale databases of cardiac images, such as the Framingham Heart Study, the Multi-Ethnic Study of Atherosclerosis and the UK Biobank. In this context, artificial intelligence (AI), particularly machine learning for artificial neural networks and computer vision, has emerged as one of the most promising topics in cardiac imaging research. Combined with the exponential increase in computing power, AI provides unprecedented opportunities to leverage the available large collections of cardiac imaging data for developing more robust cardiac image analysis algorithms, to uncover currently unknown clinical knowledge on cardiac health and disease, and to build novel software tools that will impact clinical cardiology.
This Research Topic will provide comprehensive reviews of the recent advances and potential impact of AI for a range of cardiac imaging applications, particularly cardiac image acquisition, automated cardiac quantification, cardiac tissue characterization, imaging biomarker discovery, and clinical decision support in cardiology. These papers will also be aimed at discussing current challenges and future opportunities of AI in cardiac imaging, and to promote new cutting-edge research in the field.