Revolutionary Robotic System Enhances Delicate Eye Surgery

Retinal vein occlusion (RVO) is a severe disease that occurs when a vein in the light-sensitive layer at the back of the eye (i.e., the retina) becomes blocked, which results in a loss of vision. There are currently a few medical interventions that address RVO, including the periodic injection of medications that block the abnormal growth of blood vessels or of steroids, which reduce swelling and inflammation. A promising procedure for the treatment of RVO is retinal vein cannulation (RVC). This is a very delicate surgical intervention that requires surgeons to insert a tiny needle into the blocked vein with high precision, delivering clot-dissolving drugs or medications that control the abnormal growth of blood vessels. Given that retinal veins targeted for cannulation are similar in thickness to a human hair, manually inserting a needle inside them with high precision is very challenging. Robots could potentially assist surgeons in performing RVO procedures, ensuring that needles are inserted correctly and without damaging the patients' retina. Researchers at Johns Hopkins University have recently developed a new autonomous robotic system that could reliably perform these procedures. This system, introduced in a paper published in Science Robotics, is guided by deep learning algorithms that analyze images collected by a surgical microscope, as well as eye tissue cross-sectional scans collected using an imaging method called optical coherence tomography (OCT). "This work builds on our long-standing interest in addressing the extreme precision and stability challenges of retinal microsurgery," Peiyao Zhang, first author of the paper, told Medical Xpress. "In particular, retinal vein cannulation requires less than 100-micron accuracy, which exceeds normal human physiological limitations. The main objective of this paper was to show that by combining robotic assistance with deep learning, it is possible to achieve an autonomous surgical workflow with a level of precision and repeatability that is difficult to obtain manually." An approach to automate retinal vein cannulation procedures The robotic system created by Zhang and his colleagues combines computational techniques for controlling robots with high-resolution imaging and deep learning algorithms. The team's system consists of two robots designed to perform retinal microsurgeries, called steady-hand eye robots, which hold a tiny needle and a surgical tool. This hardware is combined with three deep learning algorithms that were trained to track the movement of the needle and plan the robot's actions to ensure the correct insertion of the needle into affected retinal veins. The researchers have so far tested their proposed system on pig eyes that were either still or periodically moved in ways that emulated the motions that breathing would produce in live pigs or humans. "We believe that expert surgical knowledge such as the principles required for successful retinal vein cannulation can be embedded into deep learning models, enabling clinicians without specialized training to perform robot-assisted autonomous procedures and achieve outcomes comparable to those of experienced surgeons," explained Zhang. "We validated the workflow through controlled experiments, demonstrating consistent and accurate cannulation in both static and vertically moving pig eyes." In the team's experiments, their robotic system was found to successfully complete RVC in 90% of still pig eyes and in 83% of moving eyes. Notably, the team's system could also reliably detect when the needle touched and entered a retinal vein. Next steps and possible implications for eye care The findings of this recent paper suggest that robotic systems could effectively perform RVC procedures. Before it can be introduced in clinical settings, however, the team's system will need to be further assessed in experiments involving live animals and in human clinical trials. "Our paper shows that a highly delicate retinal surgical procedure can be partially automated in a safe, accurate, and repeatable manner using robotic assistance and deep learning," said Zhang. "The results represent a concrete step toward reducing surgeon workload and variability while improving precision. In practice, this approach could support future clinical systems that assist ophthalmic surgeons during challenging microsurgical tasks." In the future, the new robotic system introduced by Zhang and his colleagues could prove to be a valuable tool for eye surgeons, potentially broadening treatment options for patients with RVO. Meanwhile, the researchers are planning additional studies aimed at validating their system's potential. "Our next step will be to evaluate this workflow in live animal studies," added Zhang. "Ultimately, our goal is to translate robot-assisted autonomous retinal vein cannulation into real-world surgical settings." © 2026 Science X Network