1 Kasım 2019 Cuma

Google Engineers Developed Artificial Intelligence Which Determine Better Than Human, In Lung Disorders


Google, one of the leading companies in the healthcare field of artificial intelligence (AI) and machine learning technology, has collaborated with the Indian hospital chain Apollo Hospitals to develop an artificial intelligence algorithm that analyzes chest X-ray images.

Artificial intelligence (AI), which gives life to many sectors from smart phone to automotive, from military to health, has the potential to overcome many obstacles in front of humanity. One of the companies that are aware of this potential, Google has added a new one to its studies in artificial intelligence. The US technology giant has developed an artificial intelligence algorithm to detect four important findings in people's chest X-rays.

Designed by Google researchers, the model can detect four major lung disorders: pneumothorax, mass, fracture, and opacity. According to research published in the world-famous science journal Nature, the AI algorithm, which is trained using thousands of x-ray images, performs at the radiologist level.


More than 600,000 X-rays were obtained from the India-based hospital chain Apollo Hospitals, which was also supported by Google's umbrella company, Alphabet's artificial intelligence initiative DeepMind. Researchers developed a text-based system using radiology reports associated with each X-ray, and then analyzed more than 560,000 images from the data set provided by Apollo Hospitals.

Google researchers, the artificial intelligence algorithm they developed, doctors can easily see the x-ray images can be detected quickly, he says. Stating that the models determine the findings frequently missed by radiologists, the company said that in some cases, doctors made much better detection than artificial intelligence. Therefore, researchers expressed the need to develop models combining the skills of both AI systems and doctors, and stated that AI applications have tremendous potential in medical image interpretation.


Hiç yorum yok:

Yorum Gönder