Processing and Visualization of Tomography Signal with AI: Decision Making on COVID-19

The coronavirus COVID-19 is an infectious disease caused by the SARS-CoV-2 virus. As the name suggests, the virus is characterized by SARS (Severe acute respiratory syndrome). Five times more deadly than the influenza virus, COVID-19 infects the respiratory system, causing coughing, shortness of breath and death in severe cases. One of the most effective ways to diagnose the form and severity of the disease is X-ray images and computed tomography (CT) of the chest. To improve the efficiency of diagnosing infection with high accuracy, a method based on artificial intelligence is necessary. Gradient Weighted Class Activation Mapping (Grad-CAM) highlights important areas in images using deep learning heat map models. The dynamic anamorphosis method is considered as a promising tool for decision support. The method helps to activate the visual-figurative mechanisms of thinking of a decision-maker and to simplify the study of information. The article describes an algorithm for cognitive visualization of a two-dimensional image of the lungs by anamorphosis of the Grad-CAM heat map. Directions for further research are outlined.