CHEST X-RAY BASED DETECTION MODEL FOR PNEUMONIA IN PEDIATRIC

Authors

  • Olabisi Olayinka Onalaja
    Gateway ICT Polytechnic
  • Sakpere Wilson
    Lead City University
  • Adeoluwa Samuel Awosola
    Gateway ICT Polytechnic
  • Adebayo Idowu Peter
    Obafemi Awolowo University

Keywords:

Pneumonia Detection, Pediatric Radiology, Machine Learning, Transfer Learning, Deep Learning, RCMTL, CXR, Resource-Limited Healthcare

Abstract

Pneumonia remains a leading cause of morbidity and mortality among children, particularly in low-resource settings such as Nigeria. The accurate and timely diagnosis of pediatric pneumonia is hindered by the scarcity of skilled radiologists and diagnostic infrastructure. This study proposes a robust, efficient, and scalable classification model utilizing transfer learning to support pneumonia detection from chest X-ray (CXR) images. The model employs pre-trained convolutional neural networks (CNNs), fine-tuned under a novel Resource-Constrained Medical Transfer Learning (RCMTL) framework, to optimize predictive accuracy, computational efficiency, and equipment robustness. The approach shows promise in enhancing clinical decision-making, especially in under-resourced environments, and paves the way for practical AI integration in healthcare delivery.

Dimensions

Ayuk, 2024; Tomys-Składowska et al, 2023. Medical imaging and computer‑aided diagnosis. In Medical Imaging Methods (pp. 45–56). CRC Press. https://doi.org/10.1201/9781003112068‑2

Aziz, N., Minallah, N., Frnda, J., Sher, M., Zeeshan, M., &Durrani, A. H. (2024). Precision meets generalization: Enhancing brain tumor classification via pretrainedDenseNet with global average pooling and hyperparameter tuning. PLOS ONE, 19(9), e0307825. https://doi.org/10.1371/journal.pone.0307825

Bellman, L. A., & Liu, Y. T. (2020). Lung Ultrasound for Diagnosis of Pneumonia in Children. Academic Emergency Medicine, 27(3), 245–246. https://doi.org/10.1111/acem.13920

Bhattacharyya, S. (2011). Neural networks: Evolution, topologies, learning algorithms and applications. In V. Mago & N. Bhatia (Eds.), Cross-disciplinary applications of artificial intelligence and pattern recognition: Advancing technologies (Chapter). IGI Global.

Every Breath Counts. (2024). What do the new Global Burden of Disease estimates tell us about childhood pneumonia? Stop Pneumonia. https://stoppneumonia.org/what-do-the-new-global-burden-of-disease-estimates-tell-us-about-childhood-pneumonia-deaths.

Global Initiative for Asthma, Cañada, G., Cercenado, E., Sánchez-Carrillo, C., Díez, C., Puente, L., Muñoz, P., &Galar, A. (2024). Comparative study of the etiology of nosocomial bacteremic pneumonia in ventilated and non-ventilated patients: a 10-year experience in an institution. Microbiology Spectrum, 11(6).

Hamri, M. E., Bennani, Y., &Falih, I. (2022). Theoretical Guarantees for Domain Adaptation with Hierarchical Optimal Transport (Version 1). arXiv.

Huang, W. E., Matifoll, J. A., Lord, D., &Haggie, S. (2025). A review of imaging in the diagnosis and management of complicated paediatric pneumonia. Paediatric Respiratory Reviews, 54, 12–18. https://doi.org/10.1016/j.prrv.2024.12.001

Liu, X., et al. (2021). Novel Transfer Learning Approach for Medical Imaging with Limited Labeled Data. Cancers, 13(7), 1590.

Nguyen, D. M. H., Nguyen, H., Diep, N. T., Pham, T. N., Cao, T., Nguyen, B. T., Swoboda, P., Ho, N., Albarqouni, S., Xie, P., Sonntag, D., &Niepert, M. (2023). LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching (Version 3). arXiv.

Okafor, C., Olaniran, A., &Darj, E. (2023). Challenges and recommendations for addressing under-five pneumonia morbidity and mortality in Nigeria. African Health Sciences, 23(2), 193–201.

Payal, M., Kumar, S. K., & Kumar, T. A. (2022, May). A review of computer aided diagnosis (CAD) techniques in healthcare. International Journal of Modern Research in Engineering and Technology (IJMRSET), 5(5).

Phung, T., Le, T., Vuong, L., Tran, T., Tran, A., Bui, H., & Phung, D. (2021). On Learning Domain-Invariant Representations for Transfer Learning with Multiple Sources. arXiv.

Teixeira, L. O., Pereira, R. M., Bertolini, D., Oliveira, L. S., Nanni, L., Cavalcanti, G. D. C., & Costa, Y. M. G. (2020). Impact of lung segmentation on the diagnosis and explanation of COVID-19 in chest X-ray images (Version 4). arXiv.

UNICEF Innovation. (2024). Field Trials of Innovative Pneumonia Diagnostics. UNICEF Office of Innovation. https://www.unicef.org/innovation/stories/field-trials-innovative-pneumonia-diagnostics

Published

03-10-2025

How to Cite

CHEST X-RAY BASED DETECTION MODEL FOR PNEUMONIA IN PEDIATRIC. (2025). FUDMA JOURNAL OF SCIENCES, 9(10), 86-93. https://doi.org/10.33003/fjs-2025-0910-3963

How to Cite

CHEST X-RAY BASED DETECTION MODEL FOR PNEUMONIA IN PEDIATRIC. (2025). FUDMA JOURNAL OF SCIENCES, 9(10), 86-93. https://doi.org/10.33003/fjs-2025-0910-3963