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

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 2..., , , # Deep Learning-Based Autonomous Retinal Vein Cannulation in ex vivo Porcine Eyes

# Introduction

This repository contains all necessary code and data for reproducing the training results and control algorithms for the paper titled \"Deep Learning-Based Autonomous Retinal Vein Cannulation in ex vivo Porcine Eyes\". Please unzip contact_network.zip, dataset_for_all.zip, navigation_network.zip, puncture_network.zip, and SHER_visualiaztion_and_control.zip first.

# Installation

We recommend running this in a virtual environment:

```
# generate a virtual environment with name test_env and Python 3.8.16 installed
conda create -n test_env python=3.8.16
# activate the environment
conda activate test_env
# deactivate the environment
conda deactivate
# delete the virtual environment and all its packages
conda remove -n test_env --all
```

To install all necessary packages, please navigate to the cloned directory and run the following code in the terminal:

```
pip install -r requirements.txt
``...