Protect the Brain When Treating the Heart: A Convolutional Neural Network for Detecting Emboli
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918465909030912 |
|---|---|
| author | Angino, Andrea Trotti, Ken Pizzagalli, Diego Ulisse Krause, Rolf Torre, Tiziano Demertzis, Stefanos |
| author_facet | Angino, Andrea Trotti, Ken Pizzagalli, Diego Ulisse Krause, Rolf Torre, Tiziano Demertzis, Stefanos |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_22258 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Protect the Brain When Treating the Heart: A Convolutional Neural Network for Detecting Emboli Angino, Andrea Trotti, Ken Pizzagalli, Diego Ulisse Krause, Rolf Torre, Tiziano Demertzis, Stefanos Machine Learning Artificial Intelligence 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. |
| title | Protect the Brain When Treating the Heart: A Convolutional Neural Network for Detecting Emboli |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2604.22258 |