About this Research Topic
We are witnessing a rapid advance of artificial intelligence (AI) developments in different fields such as medicine. Researchers from different disciplines, including cardiac modelers, are aware of the advantages of combining machine learning and deep learning techniques with classical modeling tools to improve image segmentation outcomes, model parameter estimation, perform data-driven reduction models, or predict the outcome of complex cardiac therapies.
Modeling and simulation of cardiac function is a very challenging area that can benefit from modern AI technologies, which will enable its translation into clinical environments by improving the accuracy or reducing the cost of biophysical computer simulations.
In this Research Topic we would like to explore the potential benefits of combining AI with traditional physics-based mechanistic modeling techniques employed by cardiac modelers. Cardiac modeling and simulation has become increasingly complex with challenges ranging from the need to integrate experimental and clinical imaging and recording data into the model, to properly address and understand the uncertainty within these models, and to employ them in clinical workflows for fast calibration and prediction. The goal of this Research Topic is to sample and showcase the collective efforts of using AI to address these emerging challenges, covering potential topics from the construction of the computational model that will involve the segmentation of the heart and great vessels or its geometrical characterization, to the personalization of the model parameters or the prediction of the heart function, e.g. activation sequences, from a reduced set of parameters.
It is also of special interest the use of AI techniques to help in diagnosis and therapy planning of therapies such as cardiac resynchronization therapy or radiofrequency ablation.
This Research Topic welcomes review papers and original research on the following themes but is not limited to them:
• Image-based cardiac segmentation and anatomical parameterization
• Parameter estimation and model personalization
• AI-assisted reduced modeling
• Diagnosis, prediction, and therapy planning
• Uncertainty quantification and reduction
Keywords: Cardiac Imaging Analysis and Segmentation, Model Parameter Personalization, Diagnosis and Prediction, AI-based Cardiac Therapy Planning, Multi-Scale and Multi-Physics Simulation, Drug Screening for Cardiotoxicity
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.