Eyes are one of the most important organs of our body. In our population, there are more than 39 million people as being truly blind and246 million have low vision. What if there will be something that will tell whether you will go blind or not?
Dr. Ramasamy Kim the head of retina services at an eye hospital in southern India and his team has created an amazing machine learning algorithm that helps in diagnosing eye problem caused by diabetes and tells whether you will go blind or not?
Over the past few years, Kim and his team at the Aravind eye hospital have studied and worked over thousands of images of the retina. In total the team has examined about 15,000 images.
All these images were collected across the country, showing the interior surface of the eyeball, known as the fundu. With this huge dataset, the researchers identified the very first condition that leads to diabetes that can lead to blindness.
After finding this important spot, the team starts grading each image, marking abnormal spots, lesions, and indications of bleeding. They have created a complete database of retinal images from all over the world, compiled by Google and its health-tech subsidiary, Verily.
The data then put into the machine learning algorithm created by the team with a set of instructions built into a computer program to identify eye complications arising from diabetes.
Kim’s machine learning points toward several yellow spots that look like pinpricks of light emerging from the reddish-brown orb. In diabetes, the tiny blood vessels of the retina heavily get damage.
That’s what causes these tiny blood vessels to leak blood and cholesterol. In many cases, the patient does not even feel this. There is ultimately no symptoms until the patience retinal tissue begins to swell.
After a few days, the patients start noticing dullness in vision and eyesight begins to fail. At this point, it gets completely difficult to treat and in some cases, irreversible.
Kim says, it is remarkable that a machine can be trained to identify even the earliest stages of the diabetic retinopathy and grade it with as much accuracy as a human doctor.
“It’s been very exciting to watch this take shape,” says Dr. Renu Rajan, a retinal surgeon involved in the project.
Recommended: Autoblow World’s first AI sex toy
“When a machine is trained to be capable of identifying abnormal patterns in this way, it saves a doctor so much time in diagnosis; time that could be better spent helping the patient manage the condition and in aftercare.”
“Big data” and artificial intelligence has come in for stinging criticism in recent years, over issues of privacy, fairness, accountability, and transparency.”
Kim and his team have been involved in a pilot project to test the algorithm from the starting of 2016.
The machine-learning algorithm created by the team is at its early stage and the results it generates is being checked against a manual grading process.
“If there is a big difference between the results generated from the AI software and the manual diagnosis by an ophthalmologist, a senior retina specialist will make the final decision on the grading,” says Kim.
“These discrepancies are analyzed, helping to improve and fine-tune the data that will be fed into it.”
Kim hopes that in the near future India’s remotest villages will mostly get benefited by AI-powered machines set up like vending booths, the villagers will be capable of taking photographs of people’s inner eye and offering a digital diagnosis.
“Think of it as a screening and referral tool, that could tell you with a great deal of precision whether you needed to see a specialist or not and if so, how urgently you needed to see one,” says Dr. H Parida, a retina specialist.”
Google and Verily have been working with well-established eye care centers in order to build the raw data that their algorithm needs.
“By partnering with well-known institutions like Aravind eye hospital and Shankara Nethralaya, we can continue our research and pilot studies in implementing AI-powered screening technology, and then extend it to clinical practice,” says Dr. Lily Peng, a Google product manager.
More in AI :