A Dual-Branch Network for Diagnosis of Thorax Diseases From Chest X-Rays

Chowdary, G. Jignesh; Kanhangad, Vivek

doi:10.1109/jbhi.2022.3215694

Cited by 2 publications

(1 citation statement)

References 44 publications

(59 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method is able to find the reasonable spatial location of the disease. Chowdary et al 14 designed a two-branch network that firstly segmented the input CXR image by R-I UNet, and then used two fine-tuned AlexNet models to extract features from the original CXR image and the segmented image respectively. Hashmi et al 15 fine-tuned five classical CNN models using transfer learning and achieved good improvements in CXR classification.…”

mentioning

confidence: 99%

Automated thorax disease diagnosis using multi-branch residual attention network

Li,

Huo,

Jiao

et al. 2024

Sci Rep

View full text Add to dashboard Cite

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.

show abstract

mentioning

confidence: 99%