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.
@article{arxiv.2604.22258,
title = {Protect the Brain When Treating the Heart: A Convolutional Neural Network for Detecting Emboli},
author = {Andrea Angino and Ken Trotti and Diego Ulisse Pizzagalli and Rolf Krause and Tiziano Torre and Stefanos Demertzis},
journal= {arXiv preprint arXiv:2604.22258},
year = {2026}
}
Comments
Corresponding authors: Andrea Angino and Diego Ulisse Pizzagalli