Automated Prediction of Paravalvular Regurgitation before Transcatheter Aortic Valve Implantation

TL;DR

This paper explores the use of 3D convolutional neural networks to predict paravalvular regurgitation risk from preoperative cardiac CT scans in TAVI patients, aiming to improve personalized treatment planning.

Contribution

It introduces a deep learning approach using volumetric CNNs to analyze preoperative CT images for PVR risk prediction, a novel application in this context.

Findings

Deep learning captures subtle anatomical features relevant to PVR.

Volumetric CNNs show promise for personalized risk assessment.

Source code availability promotes reproducibility.

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.