A Deep Learning-Driven Autonomous System for Retinal Vein Cannulation: Validation Using a Chicken Embryo Model

-- Retinal vein cannulation (RVC) is a minimally invasive microsurgical procedure for treating retinal vein occlusion (RVO), a leading cause of vision impairment. However, the small size and fragility of retinal veins, coupled with the need for high-precision, tremor-free needle manipulation, create significant technical challenges. These limitations highlight the need for robotic assistance to improve accuracy and stability. This study presents an automated robotic system with a top-down microscope and B-scan optical coherence tomography (OCT) imaging for precise depth sensing. Deep learning-based models enable real-time needle navigation, contact detection, and vein puncture recognition, using a chicken embryo model as a surrogate for human retinal veins. The experiments demonstrate notable reductions in navigation and puncture times compared to manual methods. Our results demonstrate the potential of integrating advanced imaging and deep learning to automate microsurgical tasks, providing a pathway for safer and more reliable RVC procedures with enhanced precision and reproducibility. I. INTRODUCTION Retinal vein occlusion (RVO) occurs due to the blockage of a retinal vein by a thrombus, leading to transient or permanent vision loss [1]. Current treatments focus on managing complications, but no standardized surgical approach exists for thrombus removal. A 2015 meta-analysis identified RVO as the second most prevalent retinal vascular disease globally, affecting 28.06 million people aged 30-89, including 23.38 million branch RVO (BRVO) and 4.67 million central RVO (CRVO) [2]. Retinal vein cannulation (RVC) involves inserting a micro-needle into the occluded retinal vein, followed by injecting a thrombolytic agent to dissolve the clot [3].