Adversarial and Correlation-Aware Data Augmentation Framework for Multi-Label Chest X-Ray Image Classification

Deep learning-based methods have shown promising results in multi-label chest X-ray (CXR) image classification. However, most existing methods rely on large-scale fully-annotated datasets, which are costly and laborious to obtain. Therefore, training a high-performance model with limited annotation remains a significant challenge in practice. To address this issue, we propose an Adversarial and Correlation-Aware Data Augmentation (ACAA) framework for multi-label CXR image classification. First, we generate pseudo labels based on the model predictions on weakly-augmented images. Next, we propose a Generalized Nesterov Iterative Fast Gradient Sign Method (GNI-FGSM) to generate effective adversarial examples as image-level strongly-augmented data. Then, we introduce an image-level adversarial-augmentation-based consistency regularization to perform supervision of model predictions on the above image-level adversarial examples. To explore more diverse data transformations, we further perform adversarial augmentation in the feature space by imposing perturbations on the extracted features of each image and introduce a feature-level adversarialaugmentation- based consistency regularization. Furthermore, we propose a Batch-level Mamba module (Batch- Mamba) coupled with a batch-level Mamba-based correlation regularization to explore inter-sample correlations along batch dimension. Extensive experiments on two large CXR datasets (CheXpert and MIMIC-CXR) demonstrate the effectiveness of the proposed ACAA framework for multilabel CXR image classification under limited-annotation scenario.

Authors

• Zhanbo Liang
• Si Li Beijing University of Posts and Telecommunications
• Jian Zhu JD.com

Keywords

• Data augmentation
• Feature extraction
• Training
• Correlation
• Image classification
• Predictive models
• Pathology
• Iterative methods
• X-ray imaging
• Transformers
• Chest X-ray
• Classification Framework
• Chest X-ray Images
• Augmented Framework
• Adversarial Data
• Classification Of X-ray Images
• Chest X-ray Image Classification
• Data Augmentation Framework
• Adversarial Data Augmentation
• Multi-label Chest X-ray
• Prediction Model
• Feature Space
• Fast Method
• Deep Learning-based Methods
• Pseudo Labels
• Adversarial Examples
• Consistency Regularization
• Fast Gradient Sign Method
• Adversarial Perturbations
• Batch Of Images
• Image X
• Regularization Loss
• Semi-supervised Learning
• Patient-Centered Outcomes Research Institute
• Augmentation Strategy
• Medical Image Analysis
• Classification Performance
• Positive Labels
• Multi-label chest X-ray image classification
• Mamba