Deep learning–based autonomous retinal vein cannulation in ex vivo porcine eyes
Science Robotics · 2025
DOI: 10.1126/scirobotics.adw2969 ↗Kurz gefasst
Fachartikel in der Zeitschrift Science Robotics, 2025. Verfasst von Peiyao Zhang und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mechanical Engineering, Johns Hopkins University, Baltimore, MD 21211, USA. Hauptthemen laut MEDLINE: Deep Learning, Catheterization, Retinal Vein, Robotic Surgical Procedures. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 59 Literaturangaben. Gefördert von: National Institutes of Health, Johns Hopkins University.
Abstract (Originalsprache)
Retinal vein cannulation (RVC) is an emerging method for treating retinal vein occlusion (RVO). The success of this procedure depends on surgeon expertise and, recently, robotic assistance. This paper proposes an autonomous RVC workflow leveraging deep learning and computer vision. Two Steady-Hand Eye Robots (SHERs) controlled a 100-micrometer metal needle and a medical spatula to execute precise tasks. Three convolutional neural networks were trained to predict needle movement direction and identify contact and puncture events. A surgical microscope with an intraoperative optical coherence tomography (iOCT) system captured the surgical field through a microscope and cross-sectional images (B-scans). The goal was to enable the robot to autonomously carry out the critical steps of the RVC procedure, especially those that are challenging and require expert knowledge. The less technically demanding tasks were assigned to the user, who also supervised the robot during these steps. Our method was tested on 20 ex vivo porcine eyes, achieving a success rate of 90%. In addition, we simulated eye movements caused by breathing on six other ex vivo porcine eyes. With the eyes moving in a sinusoidal pattern, we achieved a success rate of 83%, demonstrating the robustness and stability of the proposed workflow. Our results demonstrate that the autonomous RVC workflow, incorporating deep learning and robotic assistance, achieves high success rates in both static and dynamic conditions, indicating its potential to enhance the precision and reliability of RVO treatment.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Mechanical Engineering, Johns Hopkins University, Baltimore, MD 21211, USA.
- Laboratory for Computational Sensing and Robotics, Johns Hopkins University, Baltimore, MD 21211, USA.
- Wilmer Eye Institute, Johns Hopkins University, Baltimore, MD 21211, USA.
- Department of Computer Science, Johns Hopkins University, Baltimore, MD 21211, USA.
ORCID-Profile: Peiyao Zhang, Peter Gehlbach, Russell H Taylor, Iulian Iordachita, Marin Kobilarov
Förderung
- National Institutes of Health
- Johns Hopkins University
Zitieren
APA
Zhang, P., Gehlbach, P., Taylor, R. H., Iordachita, I., & Kobilarov, M. (2025). Deep learning–based autonomous retinal vein cannulation in ex vivo porcine eyes. Science Robotics. https://doi.org/10.1126/scirobotics.adw2969
Vancouver
Zhang P, Gehlbach P, Taylor RH, Iordachita I, Kobilarov M. Deep learning–based autonomous retinal vein cannulation in ex vivo porcine eyes. Science Robotics. 2025. doi:10.1126/scirobotics.adw2969
BibTeX
@article{Zhang2025,
author = {Zhang, Peiyao and Gehlbach, Peter and Taylor, Russell H and Iordachita, Iulian and Kobilarov, Marin},
title = {Deep learning–based autonomous retinal vein cannulation in ex vivo porcine eyes},
journal = {Science Robotics},
year = {2025},
doi = {10.1126/scirobotics.adw2969}
}
EUVIMED