TAVI-TEC: an AI-based tool for procedural planning of transcatheter aortic valve implantation

Computed tomography angiography (CTA) is crucial for preprocedural TAVI planning, providing the anatomical information required for prosthesis sizing and vascular access assessment. As the volume of TAVI procedure increases, improving efficiency and standardizing annotations is becoming essential in clinical practice. This study presents TAVI-TEC, a fully automated artificial intelligence-based framework integrated into a web-based DICOM viewer for routine preoperative TAVI planning. Pre-procedural CTA scans from patients undergoing TAVI with SAPIEN 3 Ultra (S3U) prostheses were processed using a fully automated pipeline. Deep learning-based segmentation of cardiovascular structures, calcification detection, centerline extraction, landmark identification, and annular plane definition was implemented to quantify key annular and aortic root measurements and color-coded maps of lumen reduction and vessel diameter for vascular access. A multilayer perceptron classifier was trained to predict prosthesis size prior to the TAVI procedure. Results revealed that TAVI-TEC enabled pre-procedural measurements in approximately 2–6 min. Strong agreement with clinician-derived measurements was observed for annular area (coefficient of concordance, CCC = 0.934; interclass correlation coefficient, ICC = 0.935; R² = 0.881) and perimeter (CCC = 0.909; ICC = 0.909; R² = 0.854). The valve-size prediction model achieved a classification accuracy of 77.1% (95% CI: 70.1–83.9%) with the clinically selected and implanted valve size, with most discordances occurring between adjacent prosthesis sizes. These findings support the technical feasibility and promising initial performance of TAVI-TEC. Prospective multicenter and external validation, including additional valve platforms, will be required before routine clinical implementation and before its effects on operator variability and clinical workflow can be established.