Comparative Evaluation of VGG16, MobileNetV2, and ResNet50 for Pediatric Pneumonia Classification Using Grad-CAM

Rendra Gunawan; Cinantya Paramita; Suryanti Chan

doi:10.30591/jpit.v11i2.10373

Comparative Evaluation of VGG16, MobileNetV2, and ResNet50 for Pediatric Pneumonia Classification Using Grad-CAM

Rendra Gunawan, Cinantya Paramita, Suryanti Chan

Abstract

Pneumonia ranks among the deadliest respiratory infections, particularly affecting young children, where rapid and precise detection proves essential for prompt intervention and averting severe outcomes. This research examines the deployment of three leading deep learning models VGG16, MobileNetV2, and ResNet50. This research categorizes pediatric chest X-rays into normal, bacterial pneumonia, and viral pneumonia classes using a dataset of children's chest radiographs (ages 1-5 years) from Guangzhou Hospital, enhanced through preprocessing, normalization, and augmentation techniques to boost model robustness. Model performance was assessed via accuracy, precision, recall, specificity, F1-score, G-Mean, and AUC metrics for thorough evaluation, revealing accuracies between 79% and 82% with VGG16 leading, followed by ResNet50 and MobileNetV2. Grad-CAM visualizations effectively highlighted key diagnostic regions on X-rays, offering clinicians valuable insights into infection sites identified by the models, and advancing automated chest X-ray systems for precise bacterial/viral pneumonia detection with supportive interpretability.

Keywords

Pediatric Pneumonia, Image Classification, VGG16, MobileNetV2, ResNet50.

Full Text:

References

S. Phine, “Pneumonia Classification Using Deep Learning VGG19 Model,” in IEEE International Conference on Control and Automation, ICCA, IEEE Computer Society, 2023, pp. 67–71. doi: 10.1109/ICCA51723.2023.10181954.

A. F. Nurjannah, A. S. D. Kurniasari, Z. Sari, and Y. Azhar, “Pneumonia Image Classification Using CNN with Max Pooling and Average Pooling,” Jurnal RESTI, vol. 6, no. 2, pp. 330–338, Apr. 2022, doi: 10.29207/resti.v6i2.4001.

E. Shakeri and B. Far, “Advancing Pneumonia Classification and Detection: Comparative Analysis of Deep Learning Models Using Convolutional Neural Networks,” in Proceedings - 2024 IEEE International Conference on Information Reuse and Integration for Data Science, IRI 2024, Institute of Electrical and Electronics Engineers Inc., 2024, pp. 108–113. doi: 10.1109/IRI62200.2024.00033.

P. Dhungana, M. Roy, R. Aryal, S. Chaudhary, T. R. Mahesh, and P. Dhungana, “Ensemble Deep Learning Approach for Pneumonia Detection Using DenseNet, MobileNet, and EfficientNet with Transfer Learning,” in 2025 International Conference on Data Science and Business Systems, ICDSBS 2025, Institute of Electrical and Electronics Engineers Inc., 2025. doi: 10.1109/ICDSBS63635.2025.11031996.

H. Bysani, S. Garg, A. Danda, T. Singh, C. Jyotsna, and P. Duraisamy, “Detection of Pneumonia in Chest X-Ray Using Ensemble Learners and Transfer Learning with Deep Learning Models,” in 2023 14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023, Institute of Electrical and Electronics Engineers Inc., 2023. doi: 10.1109/ICCCNT56998.2023.10307035.

Y. Xu, G. He, and D. Chen, “A ResNet Based Pneumonia Classification Algorithm for Chest X-Ray Images,” in 2024 IEEE 6th International Conference on Power, Intelligent Computing and Systems, ICPICS 2024, Institute of Electrical and Electronics Engineers Inc., 2024, pp. 1588–1592. doi: 10.1109/ICPICS62053.2024.10796977.

T. S. Arulananth, S. W. Prakash, R. K. Ayyasamy, V. P. Kavitha, P. G. Kuppusamy, and P. Chinnasamy, “Classification of Paediatric Pneumonia Using Modified DenseNet-121 Deep-Learning Model,” IEEE Access, vol. 12, pp. 35716–35727, 2024, doi: 10.1109/ACCESS.2024.3371151.

F. Ojo, S. Guntupalli, and O. Adewunmi, “A Two-Phase Pneumonia Detection and Subclassification Model Using Hybridized EfficientNet and Random Forest,” in Proceedings - 2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024, Institute of Electrical and Electronics Engineers Inc., 2024, pp. 5032–5037. doi: 10.1109/BIBM62325.2024.10822155.

Kementerian Kesehatan Republik Indonesia, “Keputusan Menteri Kesehatan Republik Indonesia Nomor HK.01.07/MENKES/2147/2023 tentang Pedoman Nasional Pelayanan Kedokteran Tata Laksana Pneumonia pada Dewasa,” Jakarta, Nov. 2023.

M. Shenghan and T. T. Toe, “High-Precision Detection and Classification of Pneumonia Cases Based on Optimized ResNet,” in Proceedings of the IEEE International Conference on Computer and Communications, ICCC, Institute of Electrical and Electronics Engineers Inc., 2024, pp. 2090–2095. doi: 10.1109/ICCC62609.2024.10942079.

Y. Lu and Y. Zheng, “A Lightweight Residual Network for Pneumonia Classification,” in Proceedings - 2024 4th Asia-Pacific Conference on Communications Technology and Computer Science, ACCTCS 2024, Institute of Electrical and Electronics Engineers Inc., 2024, pp. 597–601. doi: 10.1109/ACCTCS61748.2024.00111.

C. V. Narayana, Y. Neha, C. V. Kumar, V. G. Manasa, and T. C. Teja, “Classification of Pneumonia in Chest Radiographs using Deep Learning Techniques,” in Proceedings of 8th International Conference on Inventive Computation Technologies, ICICT 2025, Institute of Electrical and Electronics Engineers Inc., 2025, pp. 104–110. doi: 10.1109/ICICT64420.2025.11004923.

S. Pappula, T. Nadendla, N. B. Lomadugu, and S. Revanth Nalla, “Detection and Classification of Pneumonia Using Deep Learning by the Dense Net-121 Model,” in 2023 9th International Conference on Advanced Computing and Communication Systems, ICACCS 2023, Institute of Electrical and Electronics Engineers Inc., 2023, pp. 1671–1675. doi: 10.1109/ICACCS57279.2023.10113110.

S. Shi, “A comparison of MobileNetV2, VGG16, and ResNet50 for classifying brain tumors,” in 2024 IEEE 2nd International Conference on Electrical, Automation and Computer Engineering, ICEACE 2024, Institute of Electrical and Electronics Engineers Inc., 2024, pp. 176–180. doi: 10.1109/ICEACE63551.2024.10898757.

Paul Mooney, “Chest X-Ray Images (Pneumonia),” Kaggle. [Online]. Available: https://www.kaggle.com/datasets/paultimothymooney/chest-xray-pneumonia/data

M. Ennab and H. Mcheick, “Enhancing Pneumonia Diagnosis Through AI Interpretability: Comparative Analysis of Pixel-Level Interpretability and Grad-CAM on X-ray Imaging With VGG19,” IEEE Open Journal of the Computer Society, vol. 6, pp. 1155–1165, 2025, doi: 10.1109/OJCS.2025.3582726.

E. Şahin, A. Çelikten, S. Demirel, A. Akpulat, K. Budak, and H. Karataş, “Pneumonia Detection in Chest X-Ray Images Using Deep Learning and Grad-CAM++ Visualization,” in 2024 Innovations in Intelligent Systems and Applications Conference, ASYU 2024, Institute of Electrical and Electronics Engineers Inc., 2024. doi: 10.1109/ASYU62119.2024.10756959.

C. Paramita, S. Rakasiwi, P. N. Andono, G. F. Shidik, Shier Nee Saw, and M. I. Rafsanjani, “Deep Learning-Based Eye Disorder Classification: A K-Fold Evaluation of EfficientNetB and VGG16 Models,” Scientific Journal of Informatics, vol. 12, no. 3, pp. 441–452, Sep. 2025, doi: 10.15294/sji.v12i3.26257.

E. Mustika Sari, C. Sabila, R. Fakhrizal Adam, and R. Kurniawan, “Analisis dan Prediksi Indeks Kualitas Udara Jakarta: Penerapan Algoritma XGBoost,” Jurnal Nasional Teknologi dan Sistem Informasi, vol. 11, no. 2, pp. 161–169, Sep. 2025, doi: 10.25077/teknosi.v11i2.2025.161-169.

B. Bryant and M. R. Abid, “COVID-19 and Pneumonia X-ray Classification via Custom Convolutional Neural Network,” in 2022 IEEE 13th Annual Information Technology, Electronics and Mobile Communication Conference, IEMCON 2022, Institute of Electrical and Electronics Engineers Inc., 2022, pp. 239–245. doi: 10.1109/IEMCON56893.2022.9946540.

M. Fu, C. Tantithamthavorn, and T. Le, “DAViT: A Domain-Adapted Vision Transformer for Automated Pneumonia Detection and Explanation Using Chest X-Ray Images,” IEEE Access, vol. 13, pp. 103033–103044, 2025, doi: 10.1109/ACCESS.2025.3579314.

J. Yang, H. Li, L. Zhang, L. Zhao, S. Jiang, and H. Xie, “Multilabel Concrete Bridge Damage Classification Using Graph Convolution,” IEEE Trans Instrum Meas, vol. 73, 2024, doi: 10.1109/TIM.2024.3400345.

“G-Mean Score (GMS),” Permetrics. Accessed: Nov. 16, 2025. [Online]. Available: https://permetrics.readthedocs.io/en/latest/pages/classification/GMS.html

C. Paramita, C. S. Simbolon, A. S. Pamungkas, J. M. Triono, E. P. Widi Utomo, and E. R. Subhiyakto, “Analisis Pengaruh SMOTE terhadap Kinerja Model KNN untuk Prediksi Risiko Stroke,” Jurnal Informatika: Jurnal Pengembangan IT, vol. 10, no. 4, pp. 978–988, Sep. 2025, doi: 10.30591/jpit.v10i4.8809.

M. Wildan Akhya, C. Paramita, P. N. Andono, and A. History, “Jurnal Teknologi dan Manajemen Informatika Market Value Tier Classification of Indonesian Football Players Using Ensemble Machine Learning and SHAP Analysis Article Info ABSTRACT,” vol. 11, no. 2, pp. 212–223, 2025, [Online]. Available: http://http://jurnal.unmer.ac.id/index.php/jtmi

DOI: https://doi.org/10.30591/jpit.v11i2.10373