Chinese scientists have developed an artificial intelligence (AI) tool to screen patients with serious eye diseases that are treatable if detected in the early stages and the technology is expected to be applied to wider uses in medicine.
A paper, published on Thursday in the journal Cell, showed that researchers used an 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 with optimized recognition of discrete anatomical structures of the eye like the retina, cornea or optic nerve can identify and evaluate their condition when examining images of a whole eye.
It is quicker and more efficient than previous tools that took millions of images to train an AI system, a researcher said.
"Machine learning is often like a black box where we don't know exactly what is happening," said the paper's senior author Zhang Kang, professor of ophthalmology at Shiley Eye Institute, the University of California San Diego School of Medicine and Guangzhou Women and Children's Medical Center.
The study focused on two common causes of irreversible blindness: macular degeneration and diabetic macular edema. Both conditions are treatable if detected early.
The researchers also tested their tool for diagnosing childhood pneumonia, based on machine analyses of chest X-rays. They found 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," he said.
