A Comprehensive Analysis of COVID-19 Detection Using Bangladeshi Data and Explainable AI

2024-10-26

2024 International Conference on Innovations in Science, Engineering and Technology (ICISET)

AI Summary

In resource-constrained settings in Bangladesh, automated COVID-19 detection from chest X-ray (CXR) images suffers from low model trustworthiness and limited clinical interpretability. Method: We introduce the first multi-model comparative framework tailored to Bangladeshi CXR data—comprising 4,350 locally sourced, four-class images—integrating SMOTE-based oversampling to mitigate class imbalance and leveraging VGG19 with transfer learning, augmented by LIME for post-hoc interpretability. Results: The optimized VGG19 achieves 98% classification accuracy; LIME successfully identifies discriminative pulmonary regions, substantially enhancing model transparency and clinical interpretability. Contribution: This work establishes the first localized eXplainable AI (XAI)-enabled CXR diagnostic paradigm for Bangladesh, empirically validating the feasibility and efficacy of lightweight, interpretable AI solutions in low-resource healthcare environments—and providing a reproducible methodological foundation for AI-assisted diagnosis deployment in developing countries.

Technology Category

• Computer Vision: Interpretability, Explainability, and Transparency
• Humans and AI: Explainable AI (XAI) for Human Understanding
• Machine Learning: Transparent, Interpretable, Explainable ML

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

COVID-19 is a rapidly spreading and highly infectious virus which has triggered a global pandemic, profoundly affecting millions across the world. The pandemic has introduced unprecedented challenges in public health, economic stability, and societal structures, necessitating the implementation of extensive and multifaceted health interventions globally. It had a tremendous impact on Bangladesh by April 2024, with around 29,495 fatalities and more than 2 million confirmed cases. This study focuses on improving COVID-19 detection in CXR images by utilizing a dataset of $mathbf{4, 3 5 0}$ images from Bangladesh categorized into four classes: Normal, Lung-Opacity, COVID-19 and Viral-Pneumonia. ML, DL and TL models are employed with the VGG19 model achieving an impressive $mathbf{9 8 %}$ accuracy. LIME is used to explain model predictions, highlighting the regions and features influencing classification decisions. SMOTE is applied to address class imbalances. By providing insight into both correct and incorrect classifications, the study emphasizes the importance of XAI in enhancing the transparency and reliability of models, ultimately improving the effectiveness of detection from CXR images.

Problem

• Improving COVID-19 detection in CXR images using Bangladeshi data
• Utilizing Explainable AI (XAI) to enhance model transparency and reliability
• Addressing class imbalances in COVID-19 CXR image datasets

Innovation

• Uses VGG19 model for 98% accuracy
• Applies LIME for explainable AI insights
• Employs SMOTE to balance class data