Feasibility of three-dimensional artificial intelligence algorithm integration with intracardiac echocardiography for left atrial imaging during atrial fibrillation catheter ablation

Abstract

Aims: Intracardiac echocardiography (ICE) is a useful but operator-dependent tool for left atrial (LA) anatomical rendering during atrial fibrillation (AF) ablation. The CARTOSOUND FAM Module, a new deep learning (DL) imaging algorithm, has the potential to overcome this limitation. This study aims to evaluate feasibility of the algorithm compared to cardiac computed tomography (CT) in patients undergoing AF ablation.

Methods and results: In 28 patients undergoing AF ablation, baseline patient information was recorded, and three-dimensional (3D) shells of LA body and anatomical structures [LA appendage/left superior pulmonary vein/left inferior pulmonary vein/right superior pulmonary vein/right inferior pulmonary vein (RIPV)] were reconstructed using the DL algorithm. The selected ultrasound frames were gated to end-expiration and max LA volume. Ostial diameters of these structures and carina-to-carina distance between left and right pulmonary veins were measured and compared with CT measurements. Anatomical accuracy of the DL algorithm was evaluated by three independent electrophysiologists using a three-anchor scale for LA anatomical structures and a five-anchor scale for LA body. Ablation-related characteristics were summarized. The algorithm generated 3D reconstruction of LA anatomies, and two-dimensional contours overlaid on ultrasound input frames. Average calculation time for LA reconstruction was 65 s. Mean ostial diameters and carina-to-carina distance were all comparable to CT without statistical significance. Ostial diameters and carina-to-carina distance also showed moderate to high correlation (r = 0.52-0.75) except for RIPV (r = 0.20). Qualitative ratings showed good agreement without between-rater differences. Average procedure time was 143.7 ± 43.7 min, with average radiofrequency time 31.6 ± 10.2 min. All patients achieved ablation success, and no immediate complications were observed.

Conclusion: DL algorithm integration with ICE demonstrated considerable accuracy compared to CT and qualitative physician assessment. The feasibility of ICE with this algorithm can potentially further streamline AF ablation workflow.

Keywords: Artificial intelligence; Atrial fibrillation; Catheter ablation; Deep learning; Intracardiac echocardiography.

Graphical abstract

Figure 1

Deep learning algorithm data input flow diagram. Batches of two-dimensional (2D) ultrasounds gated frames covering the full left atrial (LA) anatomy and spatially organized using the intracardiac echocardiography (ICE) catheter position were imported into the deep learning algorithm. Automatic detection of the three-dimensional (3D) LA body and the adjacent anatomical structures [LA appendage (LAA), left superior pulmonary vein (LSPV), left inferior pulmonary vein (LIPV), right superior pulmonary vein (RSPV), and right inferior pulmonary vein (RIPV)] were performed along with the ostia, and the 2D contours were constructed. Fast anatomical mapping (FAM) of the 3D LA anatomy with 3D auto-segmentation, the 2D overlaying contours, and the 2D auto-taggings were shown as the final output on the mapping workstation.

Figure 2

Three-dimensional (3D) reconstruction of left atrium (LA) and adjacent anatomies and automatic two-dimensional (2D) contour detection. (A) 3D reconstruction and auto-segmentation of overall LA shell and its adjacent structures including LA appendage (LAA) and pulmonary veins (PVs). (B) Automatic artificial intelligence (AI) 2D contour detection of the LA shell (yellow lines) and the LAA (purple line) and the 2D auto-tagging indicated on the right list.