Crayon joined the project for the use of AI in the healthcare system of the city of Moscow

2020: CT implementation Image Analytics for COVID-19

On July 23, 2020, the company Crayon announced that it had joined the project for application AI health care in the city's system. Moscow

According to the company, earlier the mayor of Moscow announced the launch of a "computer vision" system at the Moscow Reference Center for Radiation Diagnostics, where algorithms aimed at detecting coronavirus infection were tested. Computed tomography (CT) processing took up to 15 minutes, taking into account concomitant actions, with more 90% accuracy of results. The Moscow Government was faced with the task of introducing methods of high-quality and fast diagnostics based on the results of chest CT analysis using artificial intelligence (AI) technologies.

Crayon has acted as an integrator of the CT Image Analytics for COVID-19 solution, into the ERIS (Unified Radiological Information Service) system, which is deployed by the center of the NPCC DiT DZM and operates with the support of the Information Technology Department of the Moscow Government. Using digital images of CT images, as well as deep learning models, it determines the degree of lung damage in coronavirus pneumonia with an accuracy of 96%. As a result, it is possible to reduce the time for analyzing images to 10 seconds. At the same time, it becomes possible to more accurately diagnose, as well as prescribe and adjust treatment for patients with COVID-19. In this case, the virus detection procedure becomes more effective by reducing the influence of the human factor.

Crayon specialists have adapted the technology, ensuring the possibility of its further public use in the healthcare system of the city of Moscow. Taking into account all the requirements of the Moscow Government Information Technology Department, Crayon developers created an infrastructure that allows seamless integration of the CT image processing algorithm into the workflows of radiation diagnostics departments.

Since the end of 2019, an experiment has been carried out in Moscow on the use of various AI services for processing medical images from medical institutions in Moscow. As of July 2020, AI work already allows selecting studies with pathology for the priority work of a radiologist, designates pathological changes in the images, and also objectively calculates the volume of lesions in absolute values. As part of the Moscow experiment to introduce artificial intelligence (AI) technologies, in particular, computer vision, more than 120,000 studies were analyzed. In the Unified Radiological Information Service (ERIS) - a specialized system that unites doctors, laboratory assistants and diagnostic equipment - there are 7 services for analyzing CT, RG, FLG, MMG. noted Sergei Morozov, chief specialist in radiation and instrumental diagnostics of DZM and Ministry of Health in the Central Federal District, director of the Center for Diagnostics and Telemedicine