Protect the Brain When Treating the Heart: A Convolutional Neural Network for Detecting Emboli

2026-04-24

AI Summary

This study addresses the challenge of accurately detecting and quantifying gaseous microemboli (GME) in intracardiac ultrasound images during interventional procedures, where high-speed motion, view dependency, and background clutter severely hinder reliable analysis. To overcome these limitations, this work proposes the first application of a 2.5D U-Net architecture to spatiotemporally continuous ultrasound data, enabling robust GME segmentation and real-time monitoring. By effectively integrating spatiotemporal contextual information, the method achieves high segmentation accuracy and strong resilience to interference while meeting the stringent latency requirements of intraoperative processing. The system has been successfully integrated into clinical procedural monitoring workflows, providing dynamic quantification of GME area to support timely and informed surgical decision-making.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Web Mining and Content Analysis: Web data integration and cleaning
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

Gaseous microemboli (GME) represent a common complication of cardiac structural interventions across both surgical and transcatheter approaches. Transthoracic cardiac ultrasound imaging represents a convenient methodology to visualize the presence of circulating GME. However, their detection and quantification are far from trivial due to operator-dependent view, high velocity, and objects with similar structure in the background. Here, we propose an approach based on a 2.5D U-Net architecture to segment GME in space-time connected data. Such an approach yields robust detection against the background and high segmentation accuracy while retaining real-time execution speed. These properties facilitated the integration of the proposed pipeline into patient-monitoring surgical protocols, providing the quantification of GME area over time.

Problem

• gaseous microemboli
• cardiac interventions
• ultrasound imaging
• emboli detection
• microemboli quantification

Innovation

• 2.5D U-Net
• gaseous microemboli detection
• real-time segmentation
• cardiac ultrasound
• deep learning