WASHINGTON, Feb. 22 (Xinhua) -- An international team has developed an artificial intelligence (AI) tool to screen patients with blinding eye diseases which are treatable if detected at early stages.
The paper, published on Thursday in the journal Cell, showed that researchers used the AI-based convolutional neural network to review more than 200,000 eye scans conducted with optical coherence tomography, a noninvasive technology that bounces light off the retina to create two- and three-dimensional representations of tissue.
Researchers then employed a technique called transfer learning in which knowledge gained in solving one problem is stored by a computer and applied to different but related problems.
For example, an AI neural network optimized to recognize the discrete anatomical structures of the eye, such as the retina, cornea or optic nerve, can identify and evaluate them when examining images of a whole eye.
It is more quickly and efficiently than previous tools which require using millions of images to train an AI system, researcher said.
This allows the AI system to learn effectively with a much smaller dataset than traditional methods.
The researchers also added the "occlusion testing" in which the computer identifies the areas in each image that are of greatest interest and the basis for its conclusions, the paper's senior author Zhang Kang told Xinhua.
"Machine learning is often like a black box where we don't know exactly what is happening," said Zhang, professor of ophthalmology at Shiley Eye Institute and University of California San Diego School of Medicine and Guangzhou Women and Children's Medical Center.
"With occlusion testing, the computer can tell us where it is looking in an image to arrive at a diagnosis, so we can figure out why the system got the result it did. This makes the system more transparent and increases our trust in the diagnosis."
The study focused on two common causes of irreversible blindness: macular degeneration and diabetic macular edema. Both conditions, however, are treatable if detected early.
Also, the AI platform is able to generates a treatment recommendation which is not done in previous studies.
According to Zhang, with simple training, the machine performed almost similar to a well-trained ophthalmologist, and could generate a decision on whether or not the patient should be referred for treatment within 30 seconds, with more than 95 percent accuracy.
The researchers also tested their tool in diagnosing childhood pneumonia, based on machine analyses of chest X-rays.
They found that the computer was able to differentiate between viral and bacterial pneumonia with greater than 90 percent accuracy.
"The future is more data, more computational power and more experience of the people using this system so that we can provide the best patient care possible, while still being cost-effective," Zhang said.