In Moscow, assembled the world’s largest database of CT studies of the chest patients with signs COVID-19. It contains thousands of fully anonymised sets of computer tomograms. These data are used for developing different services based on artificial intelligence.
For formation of a base of more than thousands of impersonal and in a special way marked images on the basis of which it is possible to train artificial intelligence, we have analyzed about 80 thousand studies that did patients with suspected viral pneumonia in Moscow outpatient CT centers. This data is available to developers. Studies included in the database of the Scientific-practical center of clinical diagnosis and telemedicine technology, was assembled in Moscow for the period from 10 March to 25 April 2020 using a single radiology information service.
“artificial intelligence Technology already widely used in the diagnosis of coronavirus infection, — said Sergey Morozov, chief of radiation and instrumental diagnostics Department of health of Moscow, Director of the Scientific-practical center of clinical diagnosis and telemedicine technology. — All studies are automatically entered in a single of the radiological system. Artificial intelligence processes the data, radiologist in the experiment receives the image labeling and text description. In preparing the data set it is important that the layout of the data produced as a whole, the locations and the contours of pathology — areas in which artificial intelligence algorithms are able to identify pathology. In a tense epidemic situation this allows the doctor not to miss even the smallest details of the conducted research”.
the Assembled experts of the Center of diagnostics and telemedicine data set unique. For example, in the database of the University of California in San Diego is 349 two-dimensional CT images of 216 patients, whereas data obtained in Moscow, contain three-dimensional studies. Database RAIOSS & Livon Saúde, formed in Brazil, yet includes 10 computer tomograms, the Italian society of medical and interventional radiology more than 70. A set of cases of new coronavirus infection of the Radiological society of North America is fragmented and is only suitable for review, and the British society of thoracic radiology it contains no more than hundreds of studies.
Moscow database has one fundamental difference from abroad: all the pictures are marked according to the classification reflecting the amount of pathological changes in lung tissues COVID-19. Classification, which formed in about��Novo marking, was published in the guidelines for radiation diagnosis of coronavirus infection.
Today, the 48 outpatient CT centers for the diagnosis of patients with SARS, community-acquired pneumonia and suspected novel coronavirus infection. They are deployed on the basis of city outpatient clinics, having clinics CT. In addition to CT scan for patients with suspected COVID-19 in these centers have performed more tests: General blood analysis, ECG, intake strokes on novel coronavirus infection. This approach allows not only to diagnose the presence of pneumonia, but to determine its nature.
