Pneumonia App: a mobile application for efficient pediatric pneumonia diagnosis using explainable convolutional neural networks (CNN)

TL;DR

PneumoniaAPP is a mobile app utilizing explainable CNNs trained on chest X-ray images to rapidly and accurately diagnose pediatric Mycoplasma pneumoniae pneumonia, aiding physicians with lung opacity localization.

Contribution

This work introduces a mobile application specifically designed for pediatric pneumonia diagnosis using explainable deep learning, focusing on MPP detection and deployment on mobile devices.

Findings

Achieved 88.20% overall accuracy and 97.64% accuracy for MPP detection.

Integrated explainability techniques for lung opacity localization.

Demonstrated effective deployment on mobile platforms.

Abstract

Mycoplasma pneumoniae pneumonia (MPP) poses significant diagnostic challenges in pediatric healthcare, especially in regions like China where it's prevalent. We introduce PneumoniaAPP, a mobile application leveraging deep learning techniques for rapid MPP detection. Our approach capitalizes on convolutional neural networks (CNNs) trained on a comprehensive dataset comprising 3345 chest X-ray (CXR) images, which includes 833 CXR images revealing MPP and additionally augmented with samples from a public dataset. The CNN model achieved an accuracy of 88.20% and an AUROC of 0.9218 across all classes, with a specific accuracy of 97.64% for the mycoplasma class, as demonstrated on the testing dataset. Furthermore, we integrated explainability techniques into PneumoniaAPP to aid respiratory physicians in lung opacity localization. Our contribution extends beyond existing research by targeting pediatric MPP, emphasizing the age group of 0-12 years, and prioritizing deployment on mobile devices. This work signifies a significant advancement in pediatric pneumonia diagnosis, offering a reliable and accessible tool to alleviate diagnostic burdens in healthcare settings.