Chinese and American researchers have developed artificial intelligence that can examine retinal diseases

recently, Chinese and American researchers developed a platform that uses big data and artificial intelligence to not only identify the two most common retinal diseases, but also assess their severity. It can also distinguish between bacterial pneumonia and viral pneumonia in children based on chest x-ray images. The paper was published in the journal Cell.
researchers at Guangzhou Women's and Children's Medical Center and the University of California, San Diego and others studied more than 200,000 eye optically relevant fault scans using reel neural networks based on artificial intelligence technology. The "migration learning" technique is then used to enable computer learning to use the knowledge gained to solve other related problems. The researchers also used masking tests to mask hundreds of areas of the image and determine whether accuracy was affected, identifying the areas of the lesions in each image that are most important for the computer to diagnose.
researchers analyzed the AI platform's diagnosis of macular degeneration and diabetic retinal disease. The results showed that the new technology can determine whether the examiner needs treatment in 30 seconds, with an accuracy of more than 95%. The researchers also applied the tool to the diagnosis of pneumonia in children. By examining chest x-rays, the computer was able to determine the difference between the virus and bacterial pneumonia with an accuracy rate of more than 90%.
in addition to medical diagnosis, the AI platform can also provide referrals and treatment advice, beyond previous research. In addition, there are many other potential applications for this technology, such as distinguishing between cancer and non-cancer lesions in CT scans and MRIs. (Source: Science Network Tang Feng)