Sber CT Lungs

Main articles:

• Computed tomography
• Artificial Intelligence in Medicine
• Artificial intelligence in radiology
• Cancer diagnosis

KT The "Lungs" service from the company, SberMedIya developed in collaboration with the Laboratory on, artificial intelligence Sbera aims to search for pathologies, including those caused, COVID-19 as well as segmentation of areas of affected lung tissue indicating the volume of damage. It makes it possible computed tomography to identify patients with lung changes in viral pneumonia on a basis, allows you to evaluate the volume and degree of these changes in a few seconds.

History

2021: Early detection of lung cancer

The company SberMedAI on October 22, 2021 announced the improvement of the service "KT Lightweight." Now artificial intelligence has learned to detect cancer at an early stage when analyzing chest CT scans and can help doctors with diagnostics.

Early lung cancer looks like a small tissue change of a few millimeters. Now the algorithm is able to find minimal nodular growths in the lungs, as well as highlight potentially dangerous areas. For example, if the size of at least one of the detected neoplasms exceeds the threshold value of four millimeters, then the service allocates all the detected nodular neoplasms regardless of their size, thereby indicating to the doctor the areas to be paid attention to when analyzing and deciding on further actions to determine the nature of neoplasms.

The system was trained on impersonal images from open sources of medical data. Specifically for improving the CT Lung model, hand-marked radiologists marked more than 12 thousand pictures, which became the basis for training artificial intelligence algorithms. As of October 2021, a decision is piloted in the oncological dispensary of one of the constituent entities of the Russian Federation.

{{quote 'author = said Yuri Krestinsky, vice president, health care Sberbank industry manager. |

The CT image analysis service showed its effectiveness during the pandemic, when the number of studies requiring interpretation increased many times. AI processed each picture for several minutes, and in addition, provided prioritization for doctors: they were primarily provided with images of patients with suspected pathology. Thus, it was possible to quickly begin treatment in those patients who most needed it, that is, from "risk groups." Connecting "CT Lungs" to the search for signs of cancer can improve the quality of medical care, and timely diagnosis can save the lives of many people,}}

Lung cancer is the most common malignant formation in the world, as well as the most common cause of death among oncological pathologies. According to the National Strategy for the Development of Artificial Intelligence for the Period until 2030, one of the priorities to support the health sector is the accelerated introduction of digital technologies. The use of the updated service "CT Lungs" can help doctors in detecting neoplasms on CT images, contribute to improving the quality of diagnosis of cancer in the early stages.

The KT Lung service for October 2021 is used in 30 clinics in 19 regions of Russia for the diagnosis of viral pneumonia, including COVID-19. Artificial intelligence marks places and indicates the percentage of affected tissues, helping doctors in the fight against coronavirus infection. It is part of the system solution of SberMedAI, a medical digital diagnostic center (MDDC) that combines more than 50 products and solutions of SberMedAI, as well as other companies of the Sber ecosystem and partners.