19 METHOD AND APPARATUS FOR DIAGNOSING COVID-19 USING ARTIFICIAL NEURAL NETWORK

摘要

A method and apparatus for diagnosing COVID-19 using an artificial neural network are provided. In an embodiment of the present invention, the method for diagnosing COVID-19 includes performing learning of a first neural network including a first feature extraction layer and a lung anomaly classification layer, and a second neural network based on the learned first feature extraction layer. Performing transfer learning of the included second feature extraction layer Generating a synthetic Corona 19 chest image based on the Corona 19 chest image Inputs the target chest image to the second neural network, and based on the output data of the second neural network and estimating whether or not the target chest image is infected with COVID-19.