Automatic Pneumonia Detection Using Deep Convolutional Neural Network on Chest X-Ray Image

rio DHIYA' udin

doi:10.30591/jpit.v11i2.10214

Automatic Pneumonia Detection Using Deep Convolutional Neural Network on Chest X-Ray Image

rio DHIYA' udin

Abstract

Pneumonia adalah infeksi pernapasan akut yang menyebabkan sekitar 2,5 juta kematian setiap tahun di seluruh dunia, dengan beban tertinggi di negara berkembang. Diagnosis dini dan akurat menggunakan citra rontgen dada sangat penting tetapi membutuhkan keahlian radiologi yang seringkali terbatas di daerah dengan keterbatasan sumber daya. Studi ini mengembangkan sistem deteksi pneumonia otomatis berdasarkan Deep Convolutional Neural Network (CNN) dengan arsitektur yang terdiri dari lima blok konvolusional progresif. Model ini dilatih menggunakan dataset Chest X-Ray Pneumonia dari Kaggle yang berisi 5.863 citra rontgen pediatrik. Implementasi mencakup pra-pemrosesan gambar (konversi skala abu-abu, pengubahan ukuran piksel 150×150, dan normalisasi), augmentasi data waktu nyata (rotasi ±30°, zoom ±20%, pergeseran ±10%, dan pembalikan horizontal) bersama dengan teknik regularisasi termasuk normalisasi batch dan lapisan dropout untuk mengurangi overfitting. Jaringan ini menggunakan ukuran filter yang meningkat secara progresif (32-64-64-128-256), dioptimalkan melalui RMSprop dengan mekanisme penjadwalan laju pembelajaran adaptif. Hasil evaluasi pada 624 gambar uji menunjukkan akurasi 90,71% dengan sensitivitas 91,54% untuk deteksi pneumonia. Model mencapai presisi 93% untuk kelas pneumonia dan 86% untuk kelas normal, menunjukkan kinerja yang seimbang. Matriks kebingungan mengungkapkan 357 positif sejati, 209 negatif sejati, 25 positif palsu, dan 33 negatif palsu. Studi ini membuktikan bahwa pendekatan pembelajaran mendalam dapat menjadi alat diagnostik yang efektif bagi ahli radiologi, terutama dalam pusat medis dengan keahlian radiologi yang tidak memadai.

Keywords

Deep Learning; Convolutional Neural Network; Pneumonia Detection; Chest X-Ray, Medical Image Classification; Batch Normalization; Data Augmentation

Full Text:

References

S. B. Sirota et al., “Global burden of lower respiratory infections and aetiologies, 1990–2023: a systematic analysis for the Global Burden of Disease Study 2023,” Lancet Infect. Dis., Dec. 2025, doi: 10.1016/S1473-3099(25)00689-9.

D. S. Kermany et al., “Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning,” Cell, vol. 172, no. 5, pp. 1122-1131.e9, Feb. 2018, doi: 10.1016/j.cell.2018.02.010.

W. Khan, N. Zaki, and L. Ali, “Intelligent Pneumonia Identification From Chest X-Rays: A Systematic Literature Review,” IEEE Access, vol. 9, pp. 51747–51771, 2021, doi: 10.1109/ACCESS.2021.3069937.

R. Siddiqi and S. Javaid, “Deep Learning for Pneumonia Detection in Chest X-ray Images: A Comprehensive Survey,” J. Imaging, vol. 10, no. 8, p. 176, Jul. 2024, doi: 10.3390/jimaging10080176.

S. Domínguez-Rodríguez et al., “Testing the performance, adequacy, and applicability of an artificial intelligence model for pediatric pneumonia diagnosis,” Comput. Methods Programs Biomed., vol. 242, p. 107765, Dec. 2023, doi: 10.1016/j.cmpb.2023.107765.

S. Sharma and K. Guleria, “A systematic literature review on deep learning approaches for pneumonia detection using chest X-ray images,” Multimed. Tools Appl., vol. 83, no. 8, pp. 24101–24151, Aug. 2023, doi: 10.1007/s11042-023-16419-1.

A. Kheirdoust et al., “Evaluation of Machine Learning Methods Developed for Prediction and Diagnosis of Pneumonia: A Systematic Review,” Heal. Sci. Reports, vol. 8, no. 12, Dec. 2025, doi: 10.1002/hsr2.71446.

S.-H. Wang et al., “Multiple Sclerosis Identification by 14-Layer Convolutional Neural Network With Batch Normalization, Dropout, and Stochastic Pooling,” Front. Neurosci., vol. 12, Nov. 2018, doi: 10.3389/fnins.2018.00818.

F. Garcea, A. Serra, F. Lamberti, and L. Morra, “Data augmentation for medical imaging: A systematic literature review,” Comput. Biol. Med., vol. 152, p. 106391, Jan. 2023, doi: 10.1016/j.compbiomed.2022.106391.

(Freddie) Liu, G. Karagoz, and N. Meratnia, “Analyzing the Impact of Data Augmentation on the Explainability of Deep Learning-Based Medical Image Classification,” Mach. Learn. Knowl. Extr., vol. 7, no. 1, p. 1, Dec. 2024, doi: 10.3390/make7010001.

A. Jaiswal, N. Gianchandani, D. Singh, V. Kumar, and M. Kaur, “Classification of the COVID-19 infected patients using DenseNet201 based deep transfer learning,” J. Biomol. Struct. Dyn., vol. 39, no. 15, pp. 5682–5689, Oct. 2021, doi: 10.1080/07391102.2020.1788642.

I. D. Mienye, T. G. Swart, G. Obaido, M. Jordan, and P. Ilono, “Deep Convolutional Neural Networks in Medical Image Analysis: A Review,” Information, vol. 16, no. 3, p. 195, Mar. 2025, doi: 10.3390/info16030195.

Y. Çapkan and A. Yeşildirek, “An Efficient Dropout for Robust Deep Neural Networks,” Appl. Sci., vol. 15, no. 15, p. 8301, Jul. 2025, doi: 10.3390/app15158301.

R. Elshamy, O. Abu-Elnasr, M. Elhoseny, and S. Elmougy, “Improving the efficiency of RMSProp optimizer by utilizing Nestrove in deep learning,” Sci. Rep., vol. 13, no. 1, p. 8814, May 2023, doi: 10.1038/s41598-023-35663-x.

C. Garbin, X. Zhu, and O. Marques, “Dropout vs. batch normalization: an empirical study of their impact to deep learning,” Multimed. Tools Appl., vol. 79, no. 19–20, pp. 12777–12815, May 2020, doi: 10.1007/s11042-019-08453-9.

P. Chlap, H. Min, N. Vandenberg, J. Dowling, L. Holloway, and A. Haworth, “A review of medical image data augmentation techniques for deep learning applications,” J. Med. Imaging Radiat. Oncol., vol. 65, no. 5, pp. 545–563, Aug. 2021, doi: 10.1111/1754-9485.13261.

DOI: https://doi.org/10.30591/jpit.v11i2.10214