This is more than a thousand fully anonymised sets of computer tomograms. A unique resource for the diagnosis COVID-19 assembled in Moscow by CT-centers created on the basis of city polyclinics. The dataset used for developing different services based on artificial intelligence (AI).
“Moscow is fighting the epidemic of coronavirus for the fourth month. In this difficult time to help the doctors comes artificial intelligence – using technology, doctors can quickly and accurately determine the stage of development of pneumonia in lung CT. At the same time for effective learning artificial intelligence uses patient data in anonymised, collected in the period from 10 March to 25 April. This database has more than thousands of images and is the largest in the world. We hope that advanced technologies that we are now actively implemented at capital health system, will help us to deal more effectively with infection,” – said the Deputy mayor of Moscow on issues of social development Anastasia Rakova.
For the formation of a database of CT studies 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 CT performed in an outpatient CT centers patients with suspected viral pneumonia. Dataset available for developers of artificial intelligence. CT scan converted into a recognized among professionals machine learning NIfTI format.
“All artificial intelligence researchers are already widely used in the diagnosis of coronavirus infection. They are automatically entered into the unified radiological system (RICE). The AI processes the data and radiologist in the experiment receives the image labeling and text description. In the preparation of dataset 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,” explained the chief specialist on radiation and instrumental diagnostics Department of health of Moscow, Director of the Center for diagnostics and telemedicine Sergey Morozov.
This unique collection of Centre for diagnostics and telemedicine. For example, in the database of the University of California in San Diego is 349 two-dimensional CT images of 216 patients, while in dataset, assembled in Moscow, provides three-dimensional CT study. Database RAIOSS & Livon Saúde, formed in Brazil, while features ten computer tomograms, whereas the Italian radiological society she��refer to more than 70. A set of cases of new coronavirus infection of North American radiological society fragmented and is only suitable for review, and the British society of thoracic radiology it contains no more than hundreds of studies.
in the capital, there is another fundamental difference from abroad. All CT studies in the Center for diagnostics and telemedicine are marked according to the classification reflecting the amount of pathological changes in lung tissues COVID-19 the CT scan of the chest. The classification that formed the basis of markup that are published in the guidelines for the diagnosis of radiation coronavirus disease COVID-19.
let me Remind you, now established in Moscow and has 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.