Modeling global and local label correlation with graph convolutional networks for multi-label chest X-ray image classification

• Published in: Medical & biological engineering & computing Vol. 60; no. 9; pp. 2567 - 2588
• Main Authors: Li, Lanting, Cao, Peng, Yang, Jinzhu, Zaiane, Osmar R.
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.09.2022; Springer Nature B.V
• Subjects: Annotations; Artificial neural networks; Automation; Bioengineering; Biomedical and Life Sciences; Biomedical Engineering and Bioengineering; Biomedicine; Chest; Classification; Computer Applications; Correlation; Deep learning; Diagnosis; Disease; Engineering; Human Physiology; Image classification; Imaging; Medical diagnosis; Medical imaging; Modelling; Original Article; Patients; Pneumonia; Radiography; Radiology; Label correlation modeling; Chest X-ray interpretation; Graph convolutional networks; Multi-label classification
• ISSN: 0140-0118; 1741-0444; 1741-0444
• DOI: 10.1007/s11517-022-02604-1

The diagnosis of chest diseases is a challenging task for assessing thousands of radiology subjects. Their diagnosis decisions heavily rely on the expert radiologists’ manual annotations. It is important to develop automated analysis methods for the computer-aided diagnosis of chest diseases on chest radiography. To explore the label relationship and improve the diagnosis performance, we present an end-to-end multi-label learning framework for jointly modeling the global and local label correlation, called GL-MLL that (1) explores the label correlation from a globally static view and a locally adaptive view, (2) considers the imbalanced class distribution, and (3) focuses on capturing label-specific features in image-level representation. We validate the performance of the proposed framework on the CheXpert dataset. The results demonstrate that the proposed GL-MLL outperforms state-of-the-art approaches. The code is available at https://github.com/llt1836/GL-MLL. Graphical abstract