We performed experiments on the NIH Chest X-ray14 dataset, which contains 112,120 frontal-view radiographs each image has multiple thorax disease labels. After end-to-end training, the GRL module enhances the correlation between thorax diseases to improve diagnosis performance. We adopted a data-driven method to create a disease correlation matrix that works on the message passing and aggregation process for the nodes in the GRL module.
From the GRL module, the self-attention mechanism aggregates neighborhood features from the graphic structure to enhance the implicit correlation between thorax diseases. We employ the IRL module to learn high-level visual representation features from the CXR image. Specifically, the proposed CheXGAT framework comprises two main modules: an image representation learning (IRL) module and a graph representation learning (GRL) module. The system is intended to explore implicit correlations between thorax diseases to aid in the multilabel chest X-ray image classification task, which we term ‶CheXGAT‶. In this paper, we propose a novel computer-aided diagnosis (CAD) system based on a hybrid deep learning model composed of a convolutional neural network (CNN) and a graph neural network (GNN). Chest X-ray (CXR) imaging is one of the most common diagnostic imaging techniques in clinical diagnosis and is usually used for radiological examinations to screen for thorax diseases.
0 kommentar(er)
