Guidance for Intra-cardiac Echocardiography Manipulation to Maintain Continuous Therapy Device Tip Visibility

2025-05-08

HSMR 2025

AI Summary

To address the clinical challenge of interrupted catheter-tip visibility during manual intracardiac echocardiography (ICE) navigation in electrophysiological and structural heart interventions, this paper proposes an AI-driven real-time tracking framework that accurately estimates the catheter tip’s incidence angle and the through-plane imaging point to enable robotic ICE catheter autonomy. Methodologically, we introduce a hybrid data generation strategy integrating electromagnetic-tracked real-world data with motion-continuous synthetic tip sequences. Furthermore, we pioneer the integration of an ultrasound foundation model—pretrained on 37.4M images—with a spatiotemporal Transformer to model dynamic geometric relationships in ICE sequences. Evaluated on 5,698 ICE-tip image pairs, our method achieves a mean incidence angle error of 3.32° and a rotation angle error of 12.76°, significantly enhancing tip visualization continuity and providing critical technical support for closed-loop robotic ICE control.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Machine Learning: Calibration & Uncertainty Quantification
• Humans and AI: Interaction Techniques and Devices

Application Category

• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Intra-cardiac Echocardiography (ICE) plays a critical role in Electrophysiology (EP) and Structural Heart Disease (SHD) interventions by providing real-time visualization of intracardiac structures. However, maintaining continuous visibility of the therapy device tip remains a challenge due to frequent adjustments required during manual ICE catheter manipulation. To address this, we propose an AI-driven tracking model that estimates the device tip incident angle and passing point within the ICE imaging plane, ensuring continuous visibility and facilitating robotic ICE catheter control. A key innovation of our approach is the hybrid dataset generation strategy, which combines clinical ICE sequences with synthetic data augmentation to enhance model robustness. We collected ICE images in a water chamber setup, equipping both the ICE catheter and device tip with electromagnetic (EM) sensors to establish precise ground-truth locations. Synthetic sequences were created by overlaying catheter tips onto real ICE images, preserving motion continuity while simulating diverse anatomical scenarios. The final dataset consists of 5,698 ICE-tip image pairs, ensuring comprehensive training coverage. Our model architecture integrates a pretrained ultrasound (US) foundation model, trained on 37.4M echocardiography images, for feature extraction. A transformer-based network processes sequential ICE frames, leveraging historical passing points and incident angles to improve prediction accuracy. Experimental results demonstrate that our method achieves 3.32 degree entry angle error, 12.76 degree rotation angle error. This AI-driven framework lays the foundation for real-time robotic ICE catheter adjustments, minimizing operator workload while ensuring consistent therapy device visibility. Future work will focus on expanding clinical datasets to further enhance model generalization.

Problem

• Maintaining continuous visibility of therapy device tip during ICE catheter manipulation
• Developing AI-driven tracking model for precise device tip localization
• Ensuring real-time robotic ICE catheter control with minimal operator workload

Innovation

• AI-driven tracking model for device tip visibility
• Hybrid dataset combining clinical and synthetic data
• Transformer-based network processing sequential ICE frames