Skip to main content
Dryad

Data and code from: Deep learning-based autonomous retinal vein cannulation in ex vivo porcine eyes

Zhang, Peiyao1; Gehlbach, Peter1; Taylor, Russell1; Iordachita, Iulian1; Kobilarov, Marin1

Published Dec 04, 2025 on Dryad. https://doi.org/10.5061/dryad.3ffbg79zd

Data files

Dec 04, 2025 version files 7.51 GB

Click names to download individual files

Abstract

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) control a 100-micrometer metal needle and a medical spatula to execute precise tasks. Three convolutional neural networks are trained to predict needle movement direction and identify contact and puncture events. A surgical microscope with an intraoperative Optical Coherence Tomography (iOCT) system captures the surgical field through a microscope and cross-sectional images. The goal is 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 are assigned to the user, who also supervises the robot during these steps. Our method is tested on 20 ex vivo porcine eyes, achieving a success rate of 90 %. Additionally, we simulate eye movements caused by breathing on six other ex vivo porcine eyes. With the eyes moving in a sinusoidal pattern, we achieve 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.