Transfer Learning Based CNN Model Optimization for Pneumonia Classification in Chest X-Ray Images
DOI:
https://doi.org/10.32664/smatika.v15i01.1985Keywords:
DenseNet-121, Fine-Tuning, Pneumonia, Transfer LearningAbstract
Pneumonia is a leading cause of child mortality worldwide, and its diagnosis often relies on chest X-ray interpretation, which is prone to human error. This study aims to optimize a Convolutional Neural Network (CNN) model based on transfer learning using the DenseNet-121 architecture for pneumonia classification in chest X-ray images. The model was trained on a Kaggle dataset consisting of two classes: Normal and Pneumonia. Preprocessing included class balancing and data augmentation. Five fine-tuning strategies were tested, ranging from training only the classifier to unfreezing the entire pretrained layers. Evaluation metrics included accuracy, precision, recall, F1-score, and ROC-AUC. Results showed that the strategy of unfreezing Block 3–4 yielded the best performance with 94.39% accuracy, 95.61% F1-score, and 98.04% ROC-AUC. This study demonstrates that selective fine-tuning strategies significantly improve classification performance compared to training only the classifier or the entire network.
References
R. G. Bender et al., “Global, regional, and national incidence and mortality burden of non-COVID-19 lower respiratory infections and aetiologies, 1990–2021: a systematic analysis from the Global Burden of Disease Study 2021,†Lancet Infect Dis, vol. 24, no. 9, pp. 974–1002, Sep. 2024, doi: 10.1016/S1473-3099(24)00176-2.
F. M. Qaimkhani, M. Hussain, Y. Shiren, and J. Xingfang, “Pneumonia Detection Using Deep Learning Methods,†International Journal Of Scientific Advances, vol. 3, no. 3, 2022, doi: 10.51542/ijscia.v3i3.32.
M. Husna, F. Dewi Pertiwi, and A. Saputra Nasution, “FAKTOR-FAKTOR YANG BERHUBUNGAN DENGAN KEJADIAN PNEUMONIA PADA BALITA DI PUSKESMAS SEMPLAK KOTA BOGOR 2020,†PROMOTOR, vol. 5, no. 3, pp. 273–280, May 2022, doi: 10.32832/pro.v5i3.6168.
S. Showkat and S. Qureshi, “Efficacy of Transfer Learning-based ResNet models in Chest X-ray image classification for detecting COVID-19 Pneumonia,†Chemometrics and Intelligent Laboratory Systems, vol. 224, p. 104534, May 2022, doi: 10.1016/j.chemolab.2022.104534.
W. B. Gefter, B. A. Post, and H. Hatabu, “Commonly Missed Findings on Chest Radiographs,†Chest, vol. 163, no. 3, pp. 650–661, Mar. 2023, doi: 10.1016/j.chest.2022.10.039.
D. J. Mollura et al., “Artificial Intelligence in Low- and Middle-Income Countries: Innovating Global Health Radiology,†Radiology, vol. 297, no. 3, pp. 513–520, Dec. 2020, doi: 10.1148/radiol.2020201434.
M. M. Zulfa and C. Sri Kusuma Aditya, “CATARACT CLASSIFICATION USING CONVOLUTIONAL NEURAL NETWORK (CNN) INCEPTION RESNETV2,†Jurnal Teknik Informatika (Jutif), vol. 5, no. 5, pp. 1299–1307, Oct. 2024, doi: 10.52436/1.jutif.2024.5.5.2340.
E. C. Yaurentius, T. R. D. Saputri, E. Tanuwijaya, and R. E. Sutanto, “COMPARATIVE STUDY OF CNN-BASED ARCHITECTURES ON EYE DISEASES CLASSIFICATION USING FUNDUS IMAGES TO AID OPHTHALMOLOGIST,†Jurnal Teknik Informatika (Jutif), vol. 6, no. 1, pp. 249–257, Feb. 2025, doi: 10.52436/1.jutif.2025.6.1.3699.
T. Rahman et al., “Transfer Learning with Deep Convolutional Neural Network (CNN) for Pneumonia Detection Using Chest X-ray,†Applied Sciences, vol. 10, no. 9, p. 3233, May 2020, doi: 10.3390/app10093233.
N. Nurhaeni, S. E. Prastya, A. Hidayat, and F. N. Anisa, “Pemodelan Sistem Deteksi Parasit Malaria pada Citra Mikroskopis Sel Darah Menggunakan Metode Deep Learning,†SMATIKA JURNAL, vol. 14, no. 02, pp. 409–416, Dec. 2024, doi: 10.32664/smatika.v14i02.1475.
A. W. Salehi et al., “A Study of CNN and Transfer Learning in Medical Imaging: Advantages, Challenges, Future Scope,†Sustainability, vol. 15, no. 7, p. 5930, Mar. 2023, doi: 10.3390/su15075930.
H. E. Kim, A. Cosa-Linan, N. Santhanam, M. Jannesari, M. E. Maros, and T. Ganslandt, “Transfer learning for medical image classification: a literature review,†BMC Med Imaging, vol. 22, no. 1, p. 69, Dec. 2022, doi: 10.1186/s12880-022-00793-7.
Z. Zhao, L. Alzubaidi, J. Zhang, Y. Duan, and Y. Gu, “A comparison review of transfer learning and self-supervised learning: Definitions, applications, advantages and limitations,†Expert Syst Appl, vol. 242, p. 122807, May 2024, doi: 10.1016/j.eswa.2023.122807.
M. Salehi, R. Mohammadi, H. Ghaffari, N. Sadighi, and R. Reiazi, “Automated detection of pneumonia cases using deep transfer learning with paediatric chest X-ray images,†Br J Radiol, vol. 94, no. 1121, May 2021, doi: 10.1259/bjr.20201263.
M. E. H. Chowdhury et al., “Can AI Help in Screening Viral and COVID-19 Pneumonia?,†IEEE Access, vol. 8, pp. 132665–132676, 2020, doi: 10.1109/ACCESS.2020.3010287.
A. Alhudhaif, K. Polat, and O. Karaman, “Determination of COVID-19 pneumonia based on generalized convolutional neural network model from chest X-ray images,†Expert Syst Appl, vol. 180, p. 115141, Oct. 2021, doi: 10.1016/j.eswa.2021.115141.
T. Zhou, X. Ye, H. Lu, X. Zheng, S. Qiu, and Y. Liu, “Dense Convolutional Network and Its Application in Medical Image Analysis,†Biomed Res Int, vol. 2022, no. 1, Jan. 2022, doi: 10.1155/2022/2384830.
A. Davila, J. Colan, and Y. Hasegawa, “Comparison of fine-tuning strategies for transfer learning in medical image classification,†Image Vis Comput, vol. 146, p. 105012, Jun. 2024, doi: 10.1016/j.imavis.2024.105012.
Paul Mooney, “Chest X-Ray Images (Pneumonia),†Kaggle. Accessed: Mar. 24, 2025. [Online]. Available: https://www.kaggle.com/datasets/paultimothymooney/chest-xray-pneumonia
A. A. Handoko, M. A. Rosid, and U. Indahyanti, “Implementasi Convolutional Neural Network (CNN) Untuk Pengenalan Tulisan Tangan Aksara Bima,†SMATIKA JURNAL, vol. 14, no. 01, pp. 96–110, Jul. 2024, doi: 10.32664/smatika.v14i01.1196.
V. Praskatama, C. A. Sari, E. H. Rachmawanto, and N. Mohd Yaacob, “PNEUMONIA PREDICTION USING CONVOLUTIONAL NEURAL NETWORK,†Jurnal Teknik Informatika (Jutif), vol. 4, no. 5, pp. 1217–1226, Oct. 2023, doi: 10.52436/1.jutif.2023.4.5.1353.
Y. Azhar, W. Priyo Wicaksono, and Z. Sari, “PNEUMONIA DIAGNOSIS THROUGH DEEP LEARNING: RESNET50V2 MODEL IMPLEMENTATION,†vol. 13, no. 2, 2024, doi: 10.23887/v13i2.72068.
Downloads
Published
Issue
Section
License
The writer agreed that the article copyright by Smatika journal and the writer has the right to disseminate the paper published without permission in advance.
