Aren’t optical coherence tomography (OCT) machines great? The machine uses light waves to take a cross-section of the retina and this allows the eye doctor to map and measure its thickness. These measurements help with the diagnosis and treatment of glaucoma, age-related macular degeneration (AMD) and diabetic eye disease.
As great as an OCT machine is, it needs a trained technician to operate it. So, these machines are usually found in specialized eye care practices. Researchers at Duke University have developed a robotic OCT machine that can automatically detect and scan a patient’s eyes for markers of different eye diseases.
Yes, you read correctly, a robotic OCT machine. This device combines an imaging scanner with a robotic arm and can track and image a patient’s eyes in under 60 seconds. The images produced are as clear as those produced by traditional OCT machines in an eye doctor office. In addition, the traditional OCT machines are large tabletop systems where a patient has to sit in a certain way, so that his or her head and chin fits into the head and chin rest. This can be both uncomfortable and difficult for scans to be completed since the patient has to sit still in order for proper imaging to take place.
The robotic OCT machine works to eliminate both the awkwardness of fitting into the head and chin rest and need to have a specialized technician operating it. The robotic OCT machine is easier for patients to have a scan done. The person approaches the machine, stands in front of the robotic arm. 3D cameras placed at the right and left of the robot locate the patient in space. Smaller cameras in the robotic arm search for landmarks on the eye, in order to position the scanner correctly. The need for a head and chin rest is eliminated since this device corrects for a patient’s movements. It also isn’t as bulky as a traditional OCT machine, so it can be brought to a patient, such in a general practitioner’s office or optometric practice.
Another great thing about this device is that the patient is not in physical contact with it, so there isn’t an issue with either hygiene or infectious diseases, like the coronavirus. Also, the device itself is safe since it continuously tracks the patient. This keeps the robot at a safe distance from the patient. The only problems that arise are when a few patients have bumped into the robot when the imaging is complete.
As great as this robotic OCT machine is, the images it captures still need to be analyzed by an ophthalmologist. Researchers feel that machine learning techniques for ophthalmic OCT analysis could one day automate the interpretation of the images. Scientists are working on the next phase of research where they are imaging the eyes of volunteers in order to refine the robots targeting. After this, they hope to image patients with retinal or corneal disease to see how well the device can capture irregularities in the eye. They also want to improve the field of view for the retinal scanner, since the first version of their device was able capture key features, but multiple images were needed in order to get a full view of the retina.
“While this is a solution for image collection issues, we think it will pair incredibly well with recent advances in machine learning for OCT image interpretation,” said Ryan McNabb, a research scientist in the Department of Ophthalmology at the Duke University Medical Center. “We’re optimistic that something like this could easily be used in places like optometrist offices, primary-care clinics, or even emergency departments. OCT is a useful diagnostic tool, and these kinds of advances help make it easier for wider communities to access it.”