An Efficient Lung Disease Classification from X-ray Image Using Graph Neural Network and Transformer

This research addresses the need for improved accuracy and efficiency in lung disease classification from X-ray images by developing a novel approach that integrates Graph Neural Networks (GNNs) with Transformer models. Using the extensive ChestX-ray14 dataset, which includes a wide array of lung disease cases, this study introduces and validates the TransGNN model. TransGNN harnesses the complementary strengths of GNNs and Transformers through advanced attention mechanisms and a dual-branch architecture, effectively capturing the complex and variable characteristics inherent in medical imaging data. The methodological framework includes rigorous data preprocessing, the application of weighted focus loss functions to address significant class imbalances, and extensive data augmentation techniques to bolster the model’s robustness during testing. Results show that TransGNN surpasses conventional models by achieving superior classification accuracy across multiple lung diseases, demonstrating substantial improvements in diagnostic precision and reliability. Furthermore, the model’s continuous learning mechanisms enable it to adapt seamlessly to new data and advances in medical imaging technology, making it highly versatile. This study highlights the potential of GNNs and Transformers to revolutionize the diagnostic landscape, offering a powerful, precise, and efficient tool for lung disease diagnosis. Future research should aim to incorporate additional patient-specific data, explore more advanced neural network architectures, and validate the model across diverse patient populations to enhance diagnostic accuracy further and expand its practical applicability in clinical settings, paving the way for a new standard in AI-driven medical diagnostics.