Artificial Intelligence in Structural Heart Disease
1University Hospital Düsseldorf, Düsseldorf, Germany
2University Hospital Cologne, Cologne, Germany
3Erasmus University Rotterdam, Rotterdam, Netherlands
4Rigshospitalet, Copenhagen University Hospital, Copenhagen, Denmark
Artificial Intelligence in Structural Heart Disease
Description
Structural heart disease (SHD) has developed into a fast-growing and important field in cardiovascular medicine. Interventional SHD procedures such as transcatheter valve interventions, among others, have increased rapidly over recent years, increasing the need for in-depth knowledge about an optimal anatomical spatial orientation during these interventions. This need had led to the development of new procedural skills and technologies in periprocedural planning.
Hybrid fusion imaging (FI) is a combined procedure of several imaging modalities, mainly based on MSCT and echocardiography with fluoroscopy. This procedure promises increased safety, accuracy, and periprocedural effectiveness through heart model-derived re-constructions and the possibility for simulation of individual anatomic conformations. Ongoing developments in machine learning and artificial intelligence (AI) facilitate the routine use of individualized segmented three-dimensional (3D) heart models allowing multiple combinations of distinct imaging modalities. Furthermore, the integration of knowledge about potentially outcome-relevant patient-specific risk factors may lead to a patient-tailored device and implantation strategy. As AI enables computers to perform tasks faster and potentially with more precision than humans, risk stratification and outcome aspects may be optimized in the future. The application of computational modeling, 3D printing, and AI has already changed the landscape of procedural planning and physician training in SHD, promising unlimited options in the near future.
The scope of this Special Issue includes original studies and reviews on FI and AI in Structural heart disease and related interventions. The aims of this Special Issue include the dispersion of knowledge regarding different 3D heart models, functioning of deep learning/machine learning algorithm and their impact on patient selection, periprocedural planning and guidance, education, costs, and patient outcomes.
Potential topics include but are not limited to the following:
- Current and future trends of FI and/or AI in SHD and interventions
- Challenges in applying FI and/or AI in clinical practice
- Use of computational modelling, fusion imaging, and artificial intelligence in TAVR
- Use of computational modelling, fusion imaging, and artificial intelligence in transcatheter mitral and tricuspid interventions
- Use of computational modelling, fusion imaging, and artificial intelligence in percutaneous LAA closure
- Functioning of deep learning/machine learning in SHD
- Controversies of human knowledge and AI in SHD and interventions
- The potential impact of FI/AI on patient selection, device selection, medication, outcome, and out-patient care/follow-up