Innovative Silicosis and Pneumonia Classification: Leveraging Graph Transformer Post-hoc Modeling and Ensemble Techniques

TL;DR

This study introduces a new dataset and a novel deep learning model combining graph transformer networks and ensemble techniques for accurate classification of silicosis and pneumonia from chest X-ray images, achieving high performance metrics.

Contribution

The paper presents a new curated dataset and a novel deep learning architecture that integrates graph transformers with ensemble methods for lung inflammation classification.

Findings

Achieved macro-F1 score of 0.9749

AUC ROC scores exceeding 0.99 for each class

Demonstrated significant improvements over baseline models

Abstract

This paper presents a comprehensive study on the classification and detection of Silicosis-related lung inflammation. Our main contributions include 1) the creation of a newly curated chest X-ray (CXR) image dataset named SVBCX that is tailored to the nuances of lung inflammation caused by distinct agents, providing a valuable resource for silicosis and pneumonia research community; and 2) we propose a novel deep-learning architecture that integrates graph transformer networks alongside a traditional deep neural network module for the effective classification of silicosis and pneumonia. Additionally, we employ the Balanced Cross-Entropy (BalCE) as a loss function to ensure more uniform learning across different classes, enhancing the model's ability to discern subtle differences in lung conditions. The proposed model architecture and loss function selection aim to improve the accuracy and reliability of inflammation detection, particularly in the context of Silicosis. Furthermore, our research explores the efficacy of an ensemble approach that combines the strengths of diverse model architectures. Experimental results on the constructed dataset demonstrate promising outcomes, showcasing substantial enhancements compared to baseline models. The ensemble of models achieves a macro-F1 score of 0.9749 and AUC ROC scores exceeding 0.99 for each class, underscoring the effectiveness of our approach in accurate and robust lung inflammation classification.