Deteksi Penyakit Paru Melalui Citra X-Ray Menggunakan Convolutional Neural Network Densenet121 Berbasis Transfer Learning
Keywords:
Convolutional Neural Network (CNN), DenseNet121, Transfer learningAbstract
Penelitian ini bertujuan untuk mengembangkan sistem deteksi otomatis penyakit paru, khususnya tuberkulosis dan beberapa penyakit paru lainnya, melalui citra X-ray menggunakan metode Convolutional Neural Network (CNN) dengan arsitektur DenseNet121 berbasis transfer learning. Pendekatan transfer learning dipilih untuk memanfaatkan bobot awal yang telah dilatih pada dataset besar ImageNet, sehingga proses pelatihan menjadi lebih efisien dan efektif meskipun dengan dataset medis yang relatif terbatas. Dataset citra X-ray yang digunakan terdiri dari empat kelas penyakit, yaitu Tuberkulosis, Viral Pneumonia, Lung Opacity, dan Normal. Dataset tersebut dibagi menjadi data pelatihan, validasi, dan pengujian untuk memastikan evaluasi model yang akurat. Proses pelatihan dilakukan dengan teknik augmentasi data untuk meningkatkan keragaman data dan mencegah overfitting. Hasil eksperimen menunjukkan bahwa model DenseNet121 mampu mencapai akurasi validasi sebesar 94,44%, dengan kemampuan klasifikasi yang baik terhadap keempat kelas penyakit paru. Sistem yang dikembangkan dapat digunakan sebagai alat bantu dalam diagnosis penyakit paru berbasis citra X-ray yang cepat dan akurat, mendukung proses pengambilan keputusan medis
References
[1] Rajvardhan Nalawade et al. (2025). Alzheimer’s disease detection from brain MRI: Comparative Study of ResnNet50, VGG19, DenseNet121 Multibranch CNN Model, Procedia Computer Science.
[2] Priyanka R et all (2025). PediaPulmoDX: Harnessing cutting edge preprocessing and explainable AI for pediatric chest X-ray Classification with DenseNet121, Result in Engineering 104320.
[3] Xiaurui Zhang et all (2021). Vehicle Re-Identification Model Based on Optimized DenseNet121 with Joint Loss, Computers, Materials, and Continua Vol 67, Issue 3 pages 3933-3948
[4] Jacinta Potsangbam et all (2024). Classification of Breast Cancer Histopathological Image Using Transfer Learning with DenseNet121, Procedia Computer Science 235, page 1990-1997
[5] G Krishna Lava Kumar et all (2024). An efficient diagnosis of heart disease using optimized cross-layer Densenet121 pyramid mutual attention network, Computer and Electrical Engineering Vol 119, Part B,
[6] Ogundokun et all (2023). MobileNet-SVM Lightweight Deep Tranfer Learning Model to Diagnose BCH Scans for IoMT-Based Imaging Sensor”, Sensor 23 (2), 656
[7] Morovati et all (2023). Reduced Deep Convolutional Activation Features (R-DeCAF) in Histopathology Images to Improve the Classification Performance for Breast Cancer Diagnosis, arXivpreprint arXiv:2301.01931.
[8] U. Chutia, A.S. Tewari, J.P. Singh, V.K. Raj (2024), Classification of lung diseases using an attention-based modified DenseNet model, J. Imag. Inf. Med. 37 (4) 1625–1641
[9] K.V. Priya, J.D. Peter (2021). A federated approach for detecting the chest diseases us ing DenseNet for multi-label classification, Complex Intell. Syst. 8 (4) 3121–3129.
[10] N.Hasan, Y.Bao, A. Shawon, Y. Huang (2021). DenseNet convolutional neural networks application for predicting COVID-19 using CT image, SN Comput. Sci. 2 (5).
[11] M. Kholiavchenko, et al (2020). Contour-aware multi-label chest X-ray organ segmentation, Int. J. Comput. Assisted Radiol. Surg. 15 (3) 425–436
[12] M.W. Kusk, S. Lysdahlgaard (2022). The effect of Gaussian noise on pneumonia detection on chest radiographs, using convolutional neural networks, Radiography 29 (1) 38–43
[13] A. Gielczyk, A. Marciniak, M. Tarczewska, Z. Lutowski (2022), Pre-processing methods in chest X-ray image classification, PLoS ONE 17 (4) e0265949,
[14] C. Ortiz-Toro, A. García-Pedrero, M. Lillo-Saavedra, C. Gonzalo-Martín (2022) Automatic detection of pneumonia in chest X-ray images using textural features, Comput. Biol. Med. 145 105466
[15] I.F. Jassam, S.M. Elkaffas, A.A. El-Zoghabi (2021), Chest X-ray pneumonia detection by Dense-Net, https://doi.org/10.1109/iccta54562.2021.9916637
[16] N. Ullah, et al., (2024). ChestCovidNet: an effective DL-based approach for COVID-19, lung opacity, and pneumonia detection using chest radiographs images, Biochem. Cell Biol. https://doi.org/10.1139/bcb-2023-0265.
[17] V. Parthasarathy, S. Saravanan. (2024) Computer aided diagnosis using Harris Hawks op timizer with deep learning for pneumonia detection on chest X-ray images, Int. J. Inf. Technol. 16 (3) 1677–1683, https://doi.org/10.1007/s41870-023 01700-1.
[18] Swathi S Kundaram and Ketki C Pathak.(2021) Deep learning-based Alzheimer disease detection. In: Proceedings of the Fourth International Conference on Microelectronics, Computing and Communication Systems: MCCS 2019. Springer. 2021, pp. 587–597
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
