While diagnosing multiple lesion regions in chest X-ray (CXR) images, radiologists usually apply pathological relationships in medicine before making decisions. Therefore, a comprehensive analysis of labeling relationships in different data modes is essential to improve the recognition performance of the model. However, most automated CXR diagnostic methods that consider pathological relationships treat different data modalities as independent learning objects, ignoring the alignment of pathological relationships among different data modalities. In addition, some methods that use undirected graphs to model pathological relationships ignore the directed information, making it difficult to model all pathological relationships accurately. In this paper, we propose a novel multi-label CXR classification model called MRChexNet that consists of three modules: a representation learning module (RLM), a multi-modal bridge module (MBM) and a pathology graph learning module (PGL). RLM captures specific pathological features at the image level. MBM performs cross-modal alignment of pathology relationships in different data modalities. PGL models directed relationships between disease occurrences as directed graphs. Finally, the designed graph learning block in PGL performs the integrated learning of pathology relationships in different data modalities. We evaluated MRChexNet on two large-scale CXR datasets (ChestX-Ray14 and CheXpert) and achieved state-of-the-art performance. The mean area under the curve (AUC) scores for the 14 pathologies were 0.8503 (ChestX-Ray14) and 0.8649 (CheXpert). MRChexNet effectively aligns pathology relationships in different modalities and learns more detailed correlations between pathologies. It demonstrates high accuracy and generalization compared to competing approaches. MRChexNet can contribute to thoracic disease recognition in CXR.
Keywords: cross-modal fusion; multi-label chest X-ray recognition; pathology correlation; relational learning.