TRANSFER LEARNING BASED PNEUMONIA DIAGNOSIS USING RESNET50
DOI: 
SHARE THIS ARTICLE
DOWNLOAD ARTICLE
REVIEW REPORT
CITE THIS ARTICLE
Early and precise diagnosis is essential to preventing complications and saving lives from pneumonia, a dangerous respiratory infection. Although chest X-rays are frequently used for detection, their interpretation is highly dependent on a physician's skill and may be impacted by human factors such as fatigue, workload, and subjective judgment. Our study presents a deep learning and transfer learning-powered intelligent pneumonia diagnosis system to address this. The system classifies chest X-ray images as either normal or pneumonia using the ResNet50 architecture. Grad-CAM technology then makes the logic of the system clear and reliable by highlighting the precise lung regions that underlie each diagnosis. Additionally, the system uses activation map analysis to classify infection severity as low, medium, or high. Each prediction is further assessed by an integrated confidence mechanism, which highlights ambiguous cases for human review. Strong classification accuracy and easily comprehensible results were confirmed by testing on a dataset of chest X-rays
Keywords
Article Information
Article Metrics
HOW TO CITE
Copy
C.USHARANI, & THOUFIQ, M. (2026). Transfer Learning Based Pneumonia Diagnosis using Resnet50. International Journal of Science, Strategic Management and Technology, 02(03). https://doi.org/10.55041/ijsmt.v2i3.349
C.USHARANI, , and MOHAMED THOUFIQ. "Transfer Learning Based Pneumonia Diagnosis using Resnet50." International Journal of Science, Strategic Management and Technology, vol. 02, no. 03, 2026, pp. . doi:https://doi.org/10.55041/ijsmt.v2i3.349.
C.USHARANI, , and MOHAMED THOUFIQ. "Transfer Learning Based Pneumonia Diagnosis using Resnet50." International Journal of Science, Strategic Management and Technology 02, no. 03 (2026). https://doi.org/https://doi.org/10.55041/ijsmt.v2i3.349.
References
2.C. Shin et al., “Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning,” IEEE Transactions on Medical Imaging, vol. 35, no. 5, pp. 1285–1298, 2016.
3.Gupta et al., “Pneumonia Detection from Chest X-Ray Images Using Convolutional Neural Networks and Data Augmentation Techniques,” International Journal of Medical Informatics, 2022.
4.Chen et al., “Lightweight Transfer Learning-Based CNN Model for Pneumonia Detection from Chest Radiographs,” Computers in Biology and Medicine, 2023.
5.Shakeel et al., “Automated Pneumonia Recognition in Chest X-Ray Images Using Deep Convolutional Neural Networks,” Journal of Medical Systems, 2024.
6.Usharani, C. and Selvapandian, A., 2025. FedLRes: enhancing lung cancer detection using federated learning with convolution neural network (ResNet50). Neural Computing and Applications, 37(14), pp.8273-8284.
7.Colin and Surantha, “An Interpretable Deep Learning Framework for Pneumonia Detection Using Grad-CAM Visualization,” IEEE Access, 2025.
8.Rahman et al., “Exploring the Effect of Image Enhancement Techniques on Pneumonia Detection Using Chest X-Ray Images,” Computers in Biology and Medicine, vol. 132, 2021.
9.Wang et al., “Multi-Task Learning for Thoracic Disease Classification and Localization in Chest Radiographs,” IEEE Transactions on Medical Imaging, 2024.
10.Li et al., “Lightweight Transfer Learning Framework for Real-Time Pneumonia Diagnosis from Chest X-Ray Images,” Biomedical Signal Processing and Control, 2025.
Ethics and Compliance
Indexed In
Similar Articles
Previous Article
