Accuracy of cardiac magnetic resonance generated 3D models of the aortic annulus compared to cardiovascular computed tomography generated 3D models

Latest Developments in Adapting Deep Learning for Assessing TAVR Procedures and Outcomes

Aortic valve defects are among the most prevalent clinical conditions. A severely damaged or non-functioning aortic valve is commonly replaced with a bioprosthetic heart valve (BHV) via the transcatheter aortic valve replacement (TAVR) procedure. Accurate pre-operative planning is crucial for a successful TAVR outcome. Assessment of computational fluid dynamics (CFD), finite element analysis (FEA), and fluid-solid interaction (FSI) analysis offer a solution that has been increasingly utilized to evaluate BHV mechanics and dynamics. However, the high computational costs and the complex operation of computational modeling hinder its application. Recent advancements in the deep learning (DL) domain can offer a real-time surrogate that can render hemodynamic parameters in a few seconds, thus guiding clinicians to select the optimal treatment option. Herein, we provide a comprehensive review of classical computational modeling approaches, medical imaging, and DL approaches for planning and outcome assessment of TAVR. Particularly, we focus on DL approaches in previous studies, highlighting the utilized datasets, deployed DL models, and achieved results. We emphasize the critical challenges and recommend several future directions for innovative researchers to tackle. Finally, an end-to-end smart DL framework is outlined for real-time assessment and recommendation of the best BHV design for TAVR. Ultimately, deploying such a framework in future studies will support clinicians in minimizing risks during TAVR therapy planning and will help in improving patient care.

Translating Imaging Into 3D Printed Cardiovascular Phantoms

•

3D printed patient specific phantoms can visualize complex cardiovascular anatomy

•

Common imaging modalities for 3D printing are CCT and CMR

•

Material jetting/PolyJet and stereolithography are widely used printing techniques

•

Standardized validation is warranted to compare different 3D printing technologies

Translation of imaging into 3-dimensional (3D) printed patient-specific phantoms (3DPSPs) can help visualize complex cardiovascular anatomy and enable tailoring of therapy. The aim of this paper is to review the entire process of phantom production, including imaging, materials, 3D printing technologies, and the validation of 3DPSPs. A systematic review of published research was conducted using Embase and MEDLINE, including studies that investigated 3DPSPs in cardiovascular medicine. Among 2,534 screened papers, 212 fulfilled inclusion criteria and described 3DPSPs as a valuable adjunct for planning and guiding interventions (n = 108 [51%]), simulation of physiological or pathological conditions (n = 19 [9%]), teaching of health care professionals (n = 23 [11%]), patient education (n = 3 [1.4%]), outcome prediction (n = 6 [2.8%]), or other purposes (n = 53 [25%]). The most common imaging modalities to enable 3D printing were cardiac computed tomography (n = 131 [61.8%]) and cardiac magnetic resonance (n = 26 [12.3%]). The printing process was conducted mostly by material jetting (n = 54 [25.5%]) or stereolithography (n = 43 [20.3%]). The 10 largest studies that evaluated the geometric accuracy of 3DPSPs described a mean bias <±1 mm; however, the validation process was very heterogeneous among the studies. Three-dimensional printed patient-specific phantoms are highly accurate, used for teaching, and applied to guide cardiovascular therapy. Systematic comparison of imaging and printing modalities following a standardized validation process is warranted to allow conclusions on the optimal production process of 3DPSPs in the field of cardiovascular medicine.