Explainable Deep Learning for Pediatric Pneumonia Detection in Chest X-Ray Images

2026-01-14

AI Summary

This study addresses the challenge of achieving both high accuracy and clinical trustworthiness in the automatic detection of pediatric pneumonia from chest X-ray images. By integrating EfficientNet-B0 and DenseNet121 architectures with transfer learning and data augmentation strategies, the proposed approach achieves high classification performance on a publicly available pediatric X-ray dataset. To enhance interpretability and clinical relevance, Grad-CAM and LIME techniques are employed to visualize the model’s decision-making process, confirming that predictions are grounded in clinically meaningful pulmonary regions. Experimental results demonstrate that EfficientNet-B0 yields the best performance, attaining an accuracy of 84.6%, an F1-score of 0.8899, a Matthews correlation coefficient (MCC) of 0.6849, and a recall exceeding 0.99. These findings underscore the model’s strong diagnostic capability and transparency, offering a reliable AI-assisted solution for pediatric pneumonia diagnosis.

Technology Category

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

Application Category

• Responsible Web: Algorithmic accountability and transparency on the web
• Web Mining and Content Analysis: Large pretrained models with web data
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Background: Pneumonia remains a leading cause of morbidity and mortality among children worldwide, emphasizing the need for accurate and efficient diagnostic support tools. Deep learning has shown strong potential in medical image analysis, particularly for chest X-ray interpretation. This study compares two state-of-the-art convolutional neural network (CNN) architectures for automated pediatric pneumonia detection. Methods: A publicly available dataset of 5,863 pediatric chest X-ray images was used. Images were preprocessed through normalization, resizing, and data augmentation to enhance generalization. DenseNet121 and EfficientNet-B0 were fine-tuned using pretrained ImageNet weights under identical training settings. Performance was evaluated using accuracy, F1-score, Matthews Correlation Coefficient (MCC), and recall. Model explainability was incorporated using Gradient-weighted Class Activation Mapping (Grad-CAM) and Local Interpretable Model-agnostic Explanations (LIME) to visualize image regions influencing predictions. Results: EfficientNet-B0 outperformed DenseNet121, achieving an accuracy of 84.6%, F1-score of 0.8899, and MCC of 0.6849. DenseNet121 achieved 79.7% accuracy, an F1-score of 0.8597, and MCC of 0.5852. Both models demonstrated high recall values above 0.99, indicating strong sensitivity to pneumonia detection. Grad-CAM and LIME visualizations showed consistent focus on clinically relevant lung regions, supporting the reliability of model decisions. Conclusions: EfficientNet-B0 provided a more balanced and computationally efficient performance compared to DenseNet121, making it a strong candidate for clinical deployment. The integration of explainability techniques enhances transparency and trustworthiness in AI-assisted pediatric pneumonia diagnosis.

Problem

• pediatric pneumonia
• chest X-ray
• explainable deep learning
• medical image analysis
• diagnostic support

Innovation

• Explainable AI
• Pediatric Pneumonia Detection
• Chest X-Ray
• EfficientNet
• Grad-CAM