Artificial intelligence helps radiologists to process more than two million studies

June 10

More than two million studies since the services operation start were analyzed by Moscow radiologists using computer vision algorithms based on artificial intelligence. New technologies have become part of the Moscow unified digital platform and have helped to reduce the time for describing images by an average of 30 percent. This was reported in the press service of the Moscow Social Development Complex.

"The neural network started processing medical images more than a year ago. They helped Moscow radiologists to analyze more than two million studies. Thanks to the creation of a unified digital platform and the artificial intelligence services integration, the time for image description was reduced by an average of 30 percent. In emergency situations, the sending doctor can receive the radiologist's report within five minutes after the study and quickly make the correct diagnosis," in the press service of the department was said.

Artificial intelligence services are integrated into the unified radiological information service (URIS) of the Unified Medical Information and Analytical System (UMIAS). They can be used by radiologists of all healthcare institutions connected to the URIS. The cloud storage of medical images contains data from more than 1,300 radiodiagnosis devices.

Artificial intelligence works in real time mode. Immediately after the studies are uploaded to the general system, the neural networks apply preliminary markup to them and group them. First of all, images on which pathological changes are more likely to be detected are sent to radiologists. When describing, both the original study and the image with the results of its processing by artificial intelligence services are available for doctor. The algorithms application improves the quality and speed of radiation diagnostics, helps doctors to track pathologies and identify groups of patients with a high risk of developing diseases.

"At the moment, artificial intelligence-based algorithms are available for doctors to work with, which can help to detect lung cancer, COVID-19, breast cancer and various lung pathologies. Services for detecting other pathologies are currently being prepared and tested," Sergey Morozov, MD, Director of the Center for Diagnostics and Telemedicine, said.

The implementation of such solutions was made possible due to the unified digital healthcare platform, which was developed and is developing by the Moscow Social Development Complex and the Moscow Department of Information Technologies. This helped the capital to cope with the challenges of the COVID-19 pandemic.

This month, Moscow radiologists will start using artificial intelligence algorithms to recognize osteoporosis and signs of coronary heart disease on computed tomography. And during the year, new technologies will be used in 13 fields of study.


If you continue to use our website, you are agreeing to accept the use of cookies on your device. Cookie files ensure the website’s efficiency and help us provide you with the most interesting and relevant information. Read more about cookie files.
Accept ccokies