Another model of interaction between specialists of the Reference Center and radiologists of medical facilities is called "competitive reporting". In the case when a radiologist at one of the medical facilities needs help because the number of studies is overwhelmingly high, the primary reporting is done by radiologists of the Reference Center and other medical institutions.

The third model is called "secondary reporting." It is structured as follows: when doctors at medical facilities assume a high probability of COVID-19, they add a special tag to URIS, and those studies will be placed at the top of the Reference Center's worklist. The Center's experts report these studies in the first place. Thus, a secondary review is performed.


For those doctors who cannot use URIS, the Reference Center provides a unique opportunity to consult with specialists of the CDT in the "Radiology of Moscow" telegram channel, in regard to complicated cases of COVID-19 diagnostics.

Statistics of the Reference Center operation as of June 20, 2020 are as follows:

- over 300 online consultations on COVID-19;
- over 2,000 primary reports in URIS;

- over 23,800 secondary reports in URIS.

Implementation of artificial intelligence

As part of a large-scale experiment, more than 80,000 studies were conducted with application of artificial intelligence (AI) based on computer-vision technologies. This technology allows to draw an expert conclusion on the computed tomography study to determine whether a patient has COVID-19 features with accuracy over 90%. How does this happen in practice? The study from the scanner is transferred to URIS right away and processed by algorithms. Then a radiologist receives both the original image and the image processed by artificial intelligence. The doctor opens a worklist of studies on his/her computer which need to be interpreted. Preliminary study markings of suspected pathology made by AI services are available to a specialist. When a radiologist opens CT scan images, he/she sees a copy of the original image, on which artificial intelligence has highlighted pathological findings in red. This is how the algorithm draws the doctor's attention to the lung areas with a probable lesion. To help with interpretation, AI can generate a report where it indicates the probability of viral pneumonia. The final conclusion, diagnosis and further treatment, remain the sole responsibility of the doctor.

Educational materials

Risk Management Homepage