A serious eye disease called retinal vein occlusion (RVO) happens when a vein in the retina—the light-sensitive layer at the back of the eye—gets blocked. This can lead to sudden or gradual loss of vision.
Right now, doctors treat RVO using eye injections to reduce swelling and stop the growth of abnormal blood vessels. But these treatments need to be repeated often and don’t always work well for everyone.
A more direct way to treat RVO is a delicate surgery called retinal vein cannulation (RVC). In this procedure, a surgeon carefully inserts a very thin needle into the blocked vein and delivers medicine to break up the clot. However, the veins in the retina are about as thin as a human hair, making this task extremely difficult to perform by hand.
Now, scientists at Johns Hopkins University have created a new robotic system that can help surgeons perform this very tricky procedure with great accuracy. Their study, published in the journal Science Robotics, shows how this robot can be guided by artificial intelligence and advanced imaging tools to insert the needle safely and correctly into the tiny veins.
The robot works with the help of deep learning algorithms. These are computer programs trained to learn from images and improve over time.
In this case, the robot watches through a surgical microscope and uses a special scan called optical coherence tomography (OCT) to see inside the eye. The robot then plans how to move the needle and inserts it with great precision—within less than 100 microns, or thinner than a strand of hair.
According to lead researcher Peiyao Zhang, this level of accuracy is very hard for a human hand to achieve. Their goal was to prove that a robot, guided by deep learning, can perform this surgery safely and consistently.
The robot includes two small machines called steady-hand eye robots. One holds the needle, and the other holds a tool used during surgery. The system also includes three deep learning programs. These programs help track the needle’s movement and decide how and where it should move to enter the blocked vein.
The researchers tested the system using pig eyes, both still and moving to mimic the way human eyes shift slightly during breathing. The robot successfully performed the surgery in 90% of the still eyes and 83% of the moving ones. It could even tell when the needle touched or entered the vein, which is a critical part of doing the surgery right.
Zhang says this system could help doctors without special eye surgery training perform these complex procedures with help from the robot. It might also reduce the strain on experienced surgeons and make the results more consistent.
The next step for the research team is to test the robot in live animals and eventually in human trials. Their hope is to bring this technology into hospitals to help treat people with vision problems caused by RVO.
In summary, this new robot could one day make it safer and easier to perform a very precise eye surgery that could save or improve the sight of many patients. It shows how combining robotics with artificial intelligence can lead to breakthroughs in medical care, especially for delicate operations like those involving the eyes.
If you care about eye health, please read studies about how vitamin B may help fight vision loss, and MIND diet may reduce risk of vision loss disease.
For more information about eye disease, please see recent studies about how to protect your eyes from glaucoma, and results showing this eye surgery may reduce dementia risk.
Copyright © 2025 Knowridge Science Report. All rights reserved.
