EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Comparison Of CNN, Resnet 50, And Vgg 16 For Pneumonia Classification Using Transfer Learning

Gallen Cakra Adhi Wibowo, Dita Madonna Simanjuntak, Henoch Juli Christanto

International Journal of Health Engineering and Technology · 11.07.2026 · 5 (2)

DOI: 10.55227/ijhet.v5i2.978 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Health Engineering and Technology, online erschienen am 11.07.2026. Verfasst von Gallen Cakra Adhi Wibowo und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Pneumonia is one of the leading causes of death from infectious diseases worldwide, making rapid and accurate radiological diagnosis crucial for successful medical treatment. This study implemented and compared three deep learning architectures—a custom Convolutional Neural Network (CNN), ResNet50, and VGG16—for binary classification of chest X-ray images into Normal and Pneumonia categories. The Chest X-ray Pneumonia dataset from Kaggle (5,863 images) was used with an 80/10/10 (train/validation/test) data split and data augmentation to address class imbalance. ResNet50 with transfer learning from ImageNet weights achieved the best performance: 95.1% accuracy, 92.3% precision, 96.7% recall, 94.4% F1-score, and 97.5% AUC-ROC, outperforming the custom CNN (89.4% accuracy, 95.2% AUC) and VGG16 (93.7% accuracy, 96.1% AUC). Statistical analysis confirmed that the performance difference between ResNet50 and the custom CNN was statistically significant (p < 0.05). The results showed that residual learning on ResNet50 effectively addressed the vanishing gradient problem in deep networks and achieved clinically relevant classification accuracy, supporting its potential integration into computer-aided diagnosis (CAD) systems.

Zitieren

APA

Wibowo, G. C. A., Simanjuntak, D. M., & Christanto, H. J. (2026). Comparison Of CNN, Resnet 50, And Vgg 16 For Pneumonia Classification Using Transfer Learning. International Journal of Health Engineering and Technology, 5(2). https://doi.org/10.55227/ijhet.v5i2.978

Vancouver

Wibowo GCA, Simanjuntak DM, Christanto HJ. Comparison Of CNN, Resnet 50, And Vgg 16 For Pneumonia Classification Using Transfer Learning. International Journal of Health Engineering and Technology. 2026;5(2). doi:10.55227/ijhet.v5i2.978

BibTeX
@article{Wibowo2026,
  author = {Wibowo, Gallen Cakra Adhi and Simanjuntak, Dita Madonna and Christanto, Henoch Juli},
  title = {Comparison Of CNN, Resnet 50, And Vgg 16 For Pneumonia Classification Using Transfer Learning},
  journal = {International Journal of Health Engineering and Technology},
  year = {2026},
  volume = {5},
  number = {2},
  doi = {10.55227/ijhet.v5i2.978}
}
Kostenlos starten →