Abstract Funding Acknowledgements Type of funding sources: None. Introduction The creation of an artificial intelligence imaging algorithm, the CARTOSOUND FAM Module, shows promise in enhancing current intracardiac echocardiography (ICE) practices, particular in atrial fibrillation (AF) ablation. However, there is a gap of knowledge associated with how to best optimize current practices. This study aims to provide workflow recommendations based on a high-volume US center. Methods The CARTOSOUND FAM Module is an automated version of the legacy CARTOSOUND Module. It incorporates an automatic algorithm that enables automatic detection of cardiac anatomy using a series of 2D ultrasound views. The left atrial (LA) algorithm uses a series of 2D ultrasound frames acquired from the right atrium (RA)/fossa ovalis and the RVOT to: create a 3D volume reconstruction of the LA anatomies (LA Body, LAA, LSPV, LIPV, RSPV, and RIPV), provide 3D auto-segmentation for the relevant anatomical structures, generate 2D auto-contours that are overlaid on the corresponding 2D ultrasound frames, and demonstrate 2D auto-tagging for the relevant anatomical structures. Best practice recommendations have been collected and summarized. Results The required input for the CARTOSOUND FAM algorithm: 2D ULS distinct frames, with full spatial coverage of the LA body and its adjacent key anatomical structures (LAA and PVs), with at least 2 different views for each structure, and preferably clearly visualizing the ostium of the PV’s and LAA. The 2D clips should be acquired while the SOUNDSTAR® catheter is positioned in the RA and/or the RVOT. The selected frames within the ULS clip should be gated at the end-expiration phase and to the LA max volume (). LA frames with a temporal resolution of ~20 msec just before the opening of the mitral valve at the time of maximal atrial volume (end atrial diastole). The selected frames within the ULS clip should be with depth 90-140mm. The LA anatomy shall not have uncommon anatomical variation (e.g. 5th PV). There shall be no map shift between the ULS data (frames) and the magnetic data (FAM, VISITAGs, EA points, etc.) in the CARTOSOUND® clinical procedure. Conclusion This study successfully reports on best workflow practices in using the CARTOSOUND FAM Module in conjunction with ICE. Further studies evaluating the safety and efficiency are required to validate reproducibility these recommendations.
Read full abstract