CoRSAI: A System for Robust Interpretation of CT Scans of COVID-19 Patients Using Deep Learning

Analysis of chest CT scans can be used in detecting parts lungs that are affected by infectious diseases such as COVID-19. Determining the volume lesions is essential for formulating treatment recommendations and prioritizing patients severity disease. In this article we adopted an approach based on using ensemble deep convolutional neural networks segmentation slices lung scans. Using our models, able to segment lesions, evaluate patients’ dynamics, estimate relative damage stage. Our models were trained data from different medical centers. We compared predictions with those six experienced radiologists, model outperformed most them. On task classification disease severity, all radiologists.