A fully automated artificial intelligence-driven software for planning of transcatheter aortic valve replacement

BACKGROUND

Transcatheter aortic valve replacement (TAVR) is increasingly performed for the treatment of aortic stenosis. Computed tomography (CT) analysis is essential for pre-procedural planning. Currently available software packages for TAVR planning require substantial human interaction. We describe development and validation of an artificial intelligence (AI) powered software to automatically rend anatomical measurements and other information required for TAVR planning and implantation.

METHODS

Automated measurements from 100 CTs were compared to measurements from three expert clinicians and TAVR operators using commercially available software packages. Correlation coefficients and mean differences were calculated to assess precision and accuracy.

RESULTS

AI-generated annular measurements had excellent agreements with manual measurements by expert operators yielding correlation coefficients of 0.97 for both perimeter and area. There was no relevant bias with a mean difference of -0.07 mm and - 1.4 mm2 for perimeter and area, respectively. For the ascending aorta measured 5 cm above the annular plane, correlation coefficient was 0.95 and mean difference was 1.4 mm. Instruction for use-based sizing yielded agreement with the effective implant size in 87-88 % of patients for self-expanding valves (perimeter-based sizing) and in 88 % for balloon-expandable valves (area-based sizing).

CONCLUSIONS

A fully automated software enables accurate and precise anatomical segmentation and measurements required for TAVR planning without human interaction and with high reliability.

Pre-procedural planning of coronary revascularization by cardiac computed tomography: An expert consensus document of the Society of Cardiovascular Computed Tomography

Coronary CT angiography (CCTA) demonstrated high diagnostic accuracy for detecting coronary artery disease (CAD) and a key role in the management of patients with low-to-intermediate pretest likelihood of CAD. However, the clinical information provided by this noninvasive method is still regarded insufficient in patients with diffuse and complex CAD and for planning percutaneous coronary intervention (PCI) and surgical revascularization procedures. On the other hand, technology advancements have recently shown to improve CCTA diagnostic accuracy in patients with diffuse and calcific stenoses. Moreover, stress CT myocardial perfusion imaging (CT-MPI) and fractional flow reserve derived from CCTA (CT-FFR) have been introduced in clinical practice as new tools for evaluating the functional relevance of coronary stenoses, with the possibility to overcome the main CCTA drawback, i.e. anatomical assessment only. The potential value of CCTA to plan and guide interventional procedures lies in the wide range of information it can provide: a) detailed evaluation of plaque extension, volume and composition; b) prediction of procedural success of CTO PCI using scores derived from CCTA; c) identification of coronary lesions requiring additional techniques (e.g., atherectomy and lithotripsy) to improve stent implantation success by assessing calcium score and calcific plaque distribution; d) assessment of CCTA-derived Syntax Score and Syntax Score II, which allows to select the mode of revascularization (PCI or CABG) in patients with complex and multivessel CAD. The aim of this Consensus Document is to review and discuss the available data supporting the role of CCTA, CT-FFR and stress CT-MPI in the preprocedural and possibly intraprocedural planning and guidance of myocardial revascularization interventions.

Pre-procedural planning of transcatheter mitral valve replacement in mitral stenosis with multi-detector tomography-derived 3D modeling and printing: a case report

Background

Transcatheter mitral valve replacement (TMVR) may be a valuable treatment option for mitral annular calcification and severe mitral stenosis (MS) in patients at high operative risk. Pre-procedural virtual and printed simulations may aid in procedure planning, device sizing, and mitigate complications such as valve embolization or left ventricular outflow tract (LVOT) obstruction.

Case summary

We describe a case of TMVR in which multi-detector computed tomography (MDCT) derived, three-dimensional virtual planning and a 3D-printed model of the patients’ left heart provided enhanced understanding of an individual patient’s unique anatomy to determine feasibility, device sizing, and risk stratification. This resulted in deployment of an adequately sized valve. Post-TMVR LVOT obstruction was treated with LVOT balloon dilatation and percutaneous transluminal septal myocardial ablation.

Discussion

Advanced MDCT-derived planning techniques introduce consistent 3D modeling and printing to enhance understanding of intracardiac anatomical relationships and test device implantation. Still, static measurements do not feature haemodynamic factors, tissue, or device characteristics and do not predict device host interaction. Transcatheter mitral valve replacement is feasible in MS when adequately pre-procedurally planned. Multi-detector computed tomography-derived, 3D, virtual and printed models contribute to adequate planning in terms of determining patient eligibility, procedure feasibility, and device sizing. However, static 3D modeling cannot completely eliminate the risk of peri-procedural complications.