Automated Prediction of Paravalvular Regurgitation before Transcatheter Aortic Valve Implantation

2026-02-14

AI Summary

This study addresses the prediction of paravalvular regurgitation (PVR), a common complication following transcatheter aortic valve implantation (TAVI), to improve long-term patient outcomes. To this end, we propose the first application of a voxel-level 3D convolutional neural network to preoperative isotropic cardiac computed tomography (CT) images, enabling automatic extraction of subtle anatomical features for personalized PVR risk assessment. Our method operates directly on raw CT volumes without requiring manual annotation of anatomical landmarks, yet successfully identifies structural characteristics significantly associated with PVR. The approach demonstrates strong predictive performance and offers a novel AI-driven clinical decision-support tool for preoperative planning and precision interventional therapy.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Calibration & Uncertainty Quantification
• Humans and AI: Voting

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Severe aortic stenosis is a common and life-threatening condition in elderly patients, often treated with Transcatheter Aortic Valve Implantation (TAVI). Despite procedural advances, paravalvular aortic regurgitation (PVR) remains one of the most frequent post-TAVI complications, with a proven impact on long-term prognosis. In this work, we investigate the potential of deep learning to predict the occurrence of PVR from preoperative cardiac CT. To this end, a dataset of preoperative TAVI patients was collected, and 3D convolutional neural networks were trained on isotropic CT volumes. The results achieved suggest that volumetric deep learning can capture subtle anatomical features from pre-TAVI imaging, opening new perspectives for personalized risk assessment and procedural optimization. Source code is available at https://github.com/EIDOSLAB/tavi.

Problem

• Paravalvular Regurgitation
• Transcatheter Aortic Valve Implantation
• Aortic Stenosis
• Postoperative Complication
• Risk Prediction

Innovation

• 3D convolutional neural networks
• paravalvular regurgitation prediction
• preoperative CT
• deep learning
• TAVI