Automated thorax disease diagnosis using multi-branch residual attention network

• Published in: Scientific reports Vol. 14; no. 1; p. 11865
• Main Authors: Li, Dongfang, Huo, Hua, Jiao, Shupei, Sun, Xiaowei, Chen, Shuya
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 24.05.2024; Nature Publishing Group; Nature Portfolio
• Subjects: 631/114/1305; 631/114/1564; 631/114/2413; Algorithms; Attention mechanism; BCE Loss; Chest; Convolutional neural network; Datasets; Diagnosis; Diagnosis, Computer-Assisted - methods; Humanities and Social Sciences; Humans; Label smoothing; Medical diagnosis; multidisciplinary; Neural Networks, Computer; Radiography, Thoracic - methods; Science; Science (multidisciplinary); Thoracic disease diagnosis; Thoracic Diseases - diagnosis; Thoracic Diseases - diagnostic imaging; Thorax; Attention mechanism; Thoracic disease diagnosis; BCE Loss; Label smoothing; Convolutional neural network
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-024-62813-6

Chest X-ray (CXR) is an extensively utilized radiological modality for supporting the diagnosis of chest diseases. However, existing research approaches suffer from limitations in effectively integrating multi-scale CXR image features and are also hindered by imbalanced datasets. Therefore, there is a pressing need for further advancement in computer-aided diagnosis (CAD) of thoracic diseases. To tackle these challenges, we propose a multi-branch residual attention network (MBRANet) for thoracic disease diagnosis. MBRANet comprises three components. Firstly, to address the issue of inadequate extraction of spatial and positional information by the convolutional layer, a novel residual structure incorporating a coordinate attention (CA) module is proposed to extract features at multiple scales. Next, based on the concept of a Feature Pyramid Network (FPN), we perform multi-scale feature fusion in the following manner. Thirdly, we propose a novel Multi-Branch Feature Classifier (MFC) approach, which leverages the class-specific residual attention (CSRA) module for classification instead of relying solely on the fully connected layer. In addition, the designed BCEWithLabelSmoothing loss function improves the generalization ability and mitigates the problem of class imbalance by introducing a smoothing factor. We evaluated MBRANet on the ChestX-Ray14, CheXpert, MIMIC-CXR, and IU X-Ray datasets and achieved average AUCs of 0.841, 0.895, 0.805, and 0.745, respectively. Our method outperformed state-of-the-art baselines on these benchmark datasets.