Diagnosing tuberculosis using graph neural network

Abstract

According to the World Health organization (WHO), tuberculosis (TB) is the top disease deadly worldwide, especially in developing and underdeveloped countries, due to poverty and limited health resources. Early screening for TB is a highly urgent task because of the severe effects on patient health and the rapid spread of the disease. Among the methods of diagnosing tuberculosis, chest X-ray images are often used as resources for clinical diagnosis because of their convenience and optimal cost. Currently, research on Computer-Aided Diagnosis (CAD) systems uses machine learning to provide doctors with diagnostic, analytical, and disease-monitoring techniques. Graph neural networks (GNN) have recently emerged as a research trend; works using GNN achieve perfect accuracy in many fields. In this paper, a study is presented on a solution to automatically diagnose tuberculosis on X-ray images (CXR) using the graph neural network method. We classify the CRX dataset into two classes (TB and non-TB). We achieve encouraging results with the proposed model: accuracy 99.33%, recall 99.07%, precision 99.63%, f1-score 99.35%, AUC 99.97%.