Related Experiment Video
Updated: Jun 18, 2026
Improved Registration of 3D CT Angiography with X-ray Fluoroscopy for Image Fusion During Transcatheter Aortic Valve Implantation
Published on: June 3, 2018
A novel computational method to predict hypoattenuated leaflet thickening post-transcatheter aortic valve replacement
Aniket Venkatesh1,2, Fateme Esmailie3, Noah Tregobov4,5
1Parker H. Petit Institute for Bioengineering and Bioscience, Georgia Institute of Technology, Atlanta, Ga.
Insights
A new AI pipeline predicts hypoattenuated leaflet thickening (HALT), a sign of blood clots after TAVR valve replacement, using pre-procedure CT scans. This tool aids in preventing valve dysfunction and improving patient outcomes.
Area of Science:
- Cardiovascular Imaging and Interventions
- Artificial Intelligence in Medicine
- Biomedical Engineering
Background:
- Hypoattenuated leaflet thickening (HALT) is a computed tomography (CT) finding post-transcatheter aortic valve replacement (TAVR) indicating bioprosthetic valvular thrombosis.
- Current methods for predicting HALT are not standardized or validated, posing risks for bioprosthetic valve dysfunction and adverse patient outcomes.
Purpose of the Study:
- To develop a novel, rapid, artificial intelligence (AI) and machine learning (ML)-driven computational pipeline for predicting HALT using preprocedural CT scans.
Main Methods:
- The pipeline integrated pre-TAVR CT reconstruction and reduced order modeling for predicting postprocedural geometric parameters.
- Automated left ventricle segmentation was employed to predict hemodynamic parameters.
- Statistical and ML analyses were performed to derive HALT predictive metrics.
Main Results:
- The pipeline achieved 84.40% accuracy and an AUC of 0.87 in predicting HALT.
- Statistically significant relationships were found between HALT and peak systolic blood velocity, peak systolic blood flow, left ventricular ejection time, ejection volume, and right coronary height.
- ML-derived metrics of neosinus circulation strongly correlated with HALT occurrence.
Conclusions:
- A computational pipeline utilizing pre-TAVR CT scans can predict post-TAVR geometric and hemodynamic measurements indicative of HALT risk.
- This predictive tool may enhance clinical decision-making and understanding of postprocedural thrombosis prevention.
Objective:
Hypoattenuated leaflet thickening (HALT) is a computed tomography (CT) finding after transcatheter aortic valve replacement (TAVR) that is indicative of bioprosthetic valvular thrombosis. There are currently no standardized or validated methods for predicting HALT, which can cause bioprosthetic valve dysfunction and has been associated with adverse patient outcomes. The objective was to develop a novel fast-response, artificial intelligence, and machine learning (ML)-driven computational pipeline to predict HALT using preprocedural CT scans.
Methods:
The pipeline consisted of (1) pre-TAVR CT reconstruction and reduced order modeling simulations to automatically predict postprocedural geometric parameters, (2) a landmark-guided automated left ventricle segmentation method to predict hemodynamic parameters, and (3) statistical and ML analyses to develop HALT predictive metrics.
Results:
Pre- and postprocedural scans from 45 patients (21 with HALT, 24 without) were used as inputs for the pipeline. We identified statistically significant relationships between HALT and peak systolic blood velocity (P < .01) and peak systolic blood flow through the bioprosthetic valve (P < .01), left ventricular ejection time (P < .01), ejection volume (P < .05), and right coronary height (P < .05). ML-yielded metrics related to circulation in the neosinuses correlated strongly with HALT occurrence (P < .001) along with the greatest accuracy of 84.40% and area under receiver operating characteristic curve of 0.87.
Conclusions:
A computational pipeline using pre-procedural CT scans as inputs that outputs post-TAVR geometric and hemodynamic measurements was developed to assess metrics with the potential to predict the risk of HALT. Such a tool may help guide decision-making and understanding of prevention of postprocedural thrombosis.
