Multi-Label Chest X-Ray Image Classification via Semantic Similarity Graph Embedding

• Published in: IEEE transactions on circuits and systems for video technology Vol. 32; no. 4; pp. 2455 - 2468
• Main Authors: Chen, Bingzhi, Zhang, Zheng, Li, Yingjian, Lu, Guangming, Zhang, David
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.04.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Chest; Correlation; Deep learning; Diagnosis; Embedding; Feature extraction; graph convolutional network; graph embedding; Image classification; Image contrast; Lesions; Machine learning; Medical imaging; Modules; Multi-label CXR image classification; Optimization; Pathology; semantic similarity; Semantics; Similarity; teacher-student; Visualization; X-ray imaging
• ISSN: 1051-8215; 1558-2205
• DOI: 10.1109/TCSVT.2021.3079900

Automated multi-label chest X-ray (CXR) image classification has recently made significant progress in clinical diagnosis based on the advanced deep learning techniques. However, most existing methods mainly focus on analyzing locality visual cues from a single image but fail to leverage the underlying explicit correlations among different images for precise disease diagnosis. By contrast, an experienced radiologist expertizes in transferring knowledge from previous tasks to diagnose the present radiograph. To enable the machine like a radiologist, this paper proposes a novel Semantic Similarity Graph Embedding (SSGE) framework, which explicitly explores the semantic similarities among images to optimize the visual feature embedding for improving the performance of multi-label CXR images classification. Specifically, the proposed SSGE framework contains three main components: the image feature embedding (IFE) module, similarity graph construction (SGC) module, and semantic similarity learning (SSL) module. To realize interactive teaching and learning between visual and semantic information, the proposed SSGE framework is built on the "Teacher-Student" (semantic-visual) learning mechanism. With the guidance and supervision of the cross-image similarity graph generated by the SGC module, the SSL module leverages Graph Convolutional Network (GCN) to adaptively recalibrate the multi-image feature representations extracted from the IFE module, which guarantees their semantic consistency. Furthermore, we propose a novel re-weighting strategy to learn a more optimal semantic-similarity graph for the information propagation of the GCN layers. Extensive experiments on two benchmark datasets demonstrate the effectiveness of the proposed method in comparison with some state-of-the-art baselines.