Development of a Classifier Using Neural Networks for Child-hood Pneumonia Diagnosis Through X-ray Images
DOI:
https://doi.org/10.70554/OBJK2026.v02n01.08Keywords:
Classifier, Chest X-ray images, Pediatric pneumonia, Neural networks, Computer-aided diagnosis, Artificial intelligenceAbstract
This study presents the development of a neural network-based classifier for the diagnosis of childhood pneumonia using chest X-ray images. The database used contains anteroposterior radiographs from retrospective cohorts of pediatric patients aged one to five years from the Guangzhou Women and Children’s Medical Center. Using a routine developed in MATLAB, seven texture features were extracted from each image: mean, standard deviation, entropy, contrast, correlation, energy, and homogeneity. These features were used as inputs for a feed-forward artificial neural network designed to classify the images as normal or associated with bacterial pneumonia. The database consisted of 49 normal images and 48 images with bacterial pneumonia. The best-performing neural network achieved an overall accuracy of 96.9%, suggesting that the proposed approach may constitute an efficient and interpretable tool to support computer-aided diagnosis. However, the reduced size of the dataset and the lack of external validation limit the clinical generalizability of the model, an aspect that should be addressed in future research.
References
Blasi Sanchiz, A. (2021). Classificació d’imatges pel diagnòstic de pneumònia.
Chaguendo Sanchez, C. A., & Avirama Buitrago, J. A. (2020). Plataforma móvil para el diagnóstico automático de la neumonía a partir de radiografías torácicas soportada en deep learning.
Godoy Francisco, V. L. (2020). Algoritmo de diagnóstico preliminar de neumonía a partir de imágenes radiográficas del tórax.
Harib, W., Fouad, S., & Mahmoud, T. F. (2026). A Dirichlet distribution-based trust-adaptive ensemble approach for pneumonia classification from chest X-ray images. In IEEE International Symposium on Biomedical Imaging (ISBI). IEEE. DOI: https://doi.org/10.1109/ISBI61048.2026.11515438
International Society for Pharmacoeconomics and Outcomes Research. (2026). Evaluating a deep learning model for classifying pediatric pneumonia in Israel. Retrieved March 6, 2026.
Katreddi, S., Midatani, A., Roy, A. P., Velpuri, U., & Kasani, S. (2025). Pediatric pneumonia X-ray image classification: Predictive model development with DenseNet-169 transfer learning. Journal of Medical Artificial Intelligence, 8(0). DOI: https://doi.org/10.21037/jmai-24-356
Khadidos, A. O., Nanyonga, A., Khadidos, A. O., Mirza, O. M., & Yilmaz, M. T. (2026). Explainable deep learning for pediatric pneumonia detection in chest X-ray images.
Naar Pérez, A., & Barreto Martínez, F. (2019). Modelo de red neuronal convolucional para el diagnóstico de neumonía en imágenes radiológicas.
Rickard, D., Kabir, M. A., & Homaira, N. (2025). Machine learning-based approaches for distinguishing viral and bacterial pneumonia in paediatrics: A scoping review. Computer Methods and Programs in Biomedicine, 268, 108802. DOI: https://doi.org/10.1016/j.cmpb.2025.108802
Salamon, S., & Książek, W. (2025). Capsule neural networks with Bayesian optimization for pediatric pneumonia detection from chest X-ray images. Journal of Clinical Medicine, 14(20), 7212. DOI: https://doi.org/10.3390/jcm14207212
Sánchez, J. M. B., Villagómez, J. L., Moreno, A. L., & Jiménez, L. M. (2024). The development of a classifier based on neural networks and k-neighbors for pediatric pneumonia diagnosis through X-ray images.
Tapia Vargas, G. R. (2015). Utilidad de la radiografía de tórax en el diagnóstico de neumonía en pacientes pediátricos, de 2 a 5 años, del Hospital III Yanahuara, Arequipa, Perú.
Ye, Y., & Zhou, W. (2026). Artificial intelligence in the diagnosis and prognosis of pediatric bacterial pneumonia: Current advances and challenges. Current Opinion in Pediatrics, 38(2), 149. DOI: https://doi.org/10.1097/MOP.0000000000001545
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Fredy Munera Romero, Adrian Gómez Consuegra
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
The authors retain copyright and grant the journal the right to publish the work under a Creative Commons Attribution License, which allows third parties to use the published content as long as they credit the author(s) and the publication in OnBoard Knowledge Journal.
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
a 