Діагностика патології легень з використанням гібридної нейромережевої моделі

Abstract

The paper considers the construction of a hybrid neural network model for diagnosing lung pathology, which uses a dendritic artificial immune network (DaiNet) to segment all cell nuclei in a histopathological image, a graph convolutional neural network (GCN) to extract features of the spatial structure of cells, and a convolutional neural network (CNN) to extract semantic features