Integrasi Efficient Channel Attention (ECA) pada DenseNet169 untuk Klasifikasi Multi-Kelas Citra X-ray Dada: Integration of Efficient Channel Attention (ECA) in DenseNet169 for Multi-Class Chest X-ray Classification

Husna Satira; Benny Sukma Negara; Muhammad Irsyad; Jasril Jasril; Surya Agustian

doi:10.57152/malcom.v6i3.2799

Authors

Husna Satira Universitas Islam Negeri Sultan Syarif Kasim Riau
Benny Sukma Negara Universitas Islam Negeri Sultan Syarif Kasim Riau
Muhammad Irsyad Universitas Islam Negeri Sultan Syarif Kasim Riau
Jasril Jasril Universitas Islam Negeri Sultan Syarif Kasim Riau
Surya Agustian Universitas Islam Negeri Sultan Syarif Kasim Riau

DOI:

https://doi.org/10.57152/malcom.v6i3.2799

Keywords:

Citra X-ray Dada, DenseNet169, Efficient Channel Attention (ECA), Klasifikasi Multi-Kelas

Abstract

Penyakit paru seperti pneumonia dan COVID-19 masih menjadi masalah kesehatan global yang memerlukan deteksi dini dan akurat. X-ray dada merupakan modalitas pencitraan yang umum digunakan, namun interpretasinya masih bergantung pada keahlian serta ketelitian radiolog. Penelitian ini bertujuan untuk mengevaluasi efektivitas integrasi Efficient Channel Attention (ECA) pada arsitektur DenseNet169 untuk klasifikasi multi-kelas pada citra X-ray dada. ECA dipilih karena merupakan mekanisme attention yang ringan serta mampu menangkap hubungan antarkanal fitur dengan kompleksitas parameter yang rendah. Dataset yang digunakan terdiri dari 5.228 citra yang terbagi ke dalam tiga kelas, yaitu COVID-19, pneumonia, dan normal. Penelitian ini membandingkan model DenseNet169 baseline dan DenseNet169 dengan ECA menggunakan parameter pelatihan yang sama untuk memastikan perbandingan yang adil. Evaluasi dilakukan menggunakan metrik accuracy, precision, recall, dan F1-score. Hasil menunjukkan bahwa model baseline memperoleh accuracy sebesar 96,75%, sedangkan model dengan ECA memperoleh 96,27%. Dengan demikian, integrasi ECA belum memberikan peningkatan performa yang signifikan dibandingkan dengan DenseNet169 pada dataset yang digunakan. Temuan ini menunjukkan bahwa efektivitas ECA dipengaruhi oleh karakteristik arsitektur model, strategi integrasi, serta karakteristik dataset, sehingga penerapan attention mechanism tidak selalu menghasilkan peningkatan performa secara langsung.

Downloads

Download data is not yet available.

References

World Health Organization, Guideline on Management of Pneumonia and Diarrhoea in Children up to 10 Years of Age. 2024. [Daring]. Tersedia pada: https://iris.who.int/server/api/core/bitstreams/bddcc725-8ffd-4d38-bec4-d6ead2904911/content

World Health Organization WHO, “COVID-19 epidemiological update – 24 December 2024 Special edition 174,” no. October, 2024, [Daring]. Tersedia pada: https://cdn.who.int/media/docs/default-source/documents/emergencies/20241224_covid-19_epi_update_special-edition.pdf

World Health Organization, “World Health Statistics 2022,” 2022. [Daring]. Tersedia pada: https://cdn.who.int/media/docs/default-source/gho-documents/world-health-statistic-reports/worldhealthstatistics_2022.pdf

E. Ayan dan H. M. Unver, “Diagnosis of Pneumonia from Chest X-Ray Images Using Deep Learning,” in 2019 Scientific Meeting on Electrical-Electronics & Biomedical Engineering and Computer Science (EBBT), IEEE, Apr 2019, hal. 1–5. doi: 10.1109/EBBT.2019.8741582.

A. P. Brady, “Error and discrepancy in radiology: inevitable or avoidable?,” Insights into Imaging, vol. 8, no. 1, hal. 171–182, 2017, doi: 10.1007/s13244-016-0534-1.

M. A. M. Abueed, D. M. Nor, N. Ibrahim, dan J. M. Ogier, “Pneumonia Detection Using Transfer Learning: A Systematic Literature Review,” International Journal of Advanced Computer Science and Applications, vol. 16, no. 2, hal. 1032–1041, 2025, doi: 10.14569/IJACSA.2025.01602102.

P. Podder, F. B. Alam, M. R. H. Mondal, M. J. Hasan, A. Rohan, dan S. Bharati, “Rethinking Densely Connected Convolutional Networks for Diagnosing Infectious Diseases,” Computers, vol. 12, no. 5, 2023, doi: 10.3390/computers12050095.

S. Wei, Z. Hu, dan L. Tan, “Res-ECA-UNet++: an automatic segmentation model for ovarian tumor ultrasound images based on residual networks and channel attention mechanism,” Frontiers in Medicine, vol. 12, Mei 2025, doi: 10.3389/fmed.2025.1589356.

P. P. Dalvi, D. R. Edla, dan B. R. Purushothama, “Diagnosis of Coronavirus Disease From Chest X-Ray Images Using DenseNet-169 Architecture,” SN Computer Science, vol. 4, no. 3, hal. 214, Feb 2023, doi: 10.1007/s42979-022-01627-7.

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

U. Chutia, A. S. Tewari, J. P. Singh, dan V. K. Raj, “Classification of Lung Diseases Using an Attention-Based Modified DenseNet Model,” Journal of Imaging Informatics in Medicine, vol. 37, no. 4, hal. 1625–1641, Mar 2024, doi: 10.1007/s10278-024-01005-0.

O. O. Oladimeji dan A. O. Ibitoye, “Multi-Scale Adaptive Attention Framework for Improved Lung Disease Classification,” Sakarya University Journal of Computer and Information Sciences, vol. 8, no. 3, hal. 400–409, Sep 2025, doi: 10.35377/saucis...1635644.

P. Rajpurkar et al., “Deep learning for chest radiograph diagnosis: A retrospective comparison of the CheXNeXt algorithm to practicing radiologists,” PLOS Medicine, vol. 15, no. 11, hal. e1002686, Nov 2018, doi: 10.1371/journal.pmed.1002686.

E. J. Hwang, H. Kim, S. H. Yoon, J. M. Goo, dan C. M. Park, “Implementation of a Deep Learning-Based Computer-Aided Detection System for the Interpretation of Chest Radiographs in Patients Suspected for COVID-19,” Korean Journal of Radiology, vol. 21, no. 10, hal. 1150, 2020, doi: 10.3348/kjr.2020.0536.

Y. Hwang dan et al., “High-Suspicion Pulmonary Nodule Detection on Chest Radiographs: Single-Center Retrospective Performance and Additional Detection Analysis of an AI System,” in European Congress of Radiology (ECR), VUNO Med Inc., 2026. [Daring]. Tersedia pada: https://www.vuno.co/en/publication/view/3443

S. You et al., “The diagnostic performance and clinical value of deep learning ? based nodule detection system concerning influence of location of pulmonary nodule,” Insights into Imaging, 2023, doi: 10.1186/s13244-023-01497-4.

G. Huang, Z. Liu, L. Van Der Maaten, dan K. Q. Weinberger, “Densely Connected Convolutional Networks,” in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Jul 2017, hal. 2261–2269. doi: 10.1109/CVPR.2017.243.

F. A. Breve, “COVID-19 detection on Chest X-ray images: A comparison of CNN architectures and ensembles,” Expert Systems with Applications, vol. 204, hal. 117549, Okt 2022, doi: 10.1016/j.eswa.2022.117549.

M. Bundea dan G. M. Danciu, “Pneumonia Image Classification Using DenseNet Architecture,” Information, vol. 15, no. 10, hal. 611, Okt 2024, doi: 10.3390/info15100611.

K. Nair, A. Deshpande, R. Guntuka, dan A. Patil, “Analysing X-Ray Images to Detect Lung Diseases Using DenseNet-169 technique,” SSRN Electronic Journal, 2022, doi: 10.2139/ssrn.4111864.

H. N. Aydin dan O. Yildiz, “Beyin MR Görüntü S?n?fland?r?lmas? için Geli?tirilmi? EKD-DenseNet Çerçevesi Improved ECA-DenseNet Framework for Brain MRI Image Classification,” 2023 31st Signal Processing and Communications Applications Conference (SIU), no. Dvm, hal. 1–4, 2023, doi: 10.1109/SIU59756.2023.10223886.

Q. Tian, Z. Wang, dan X. Cui, “Improved Unet brain tumor image segmentation based on GSConv module and ECA attention mechanism,” Applied and Computational Engineering, vol. 88, no. 1, hal. 214–223, Sep 2024, doi: 10.54254/2755-2721/88/20241740.

M. Zhu, L. Zhang, L. Wang, Z. Wang, Y. Wang, dan G. Qian, “Local Extremum Mapping for Weak Supervision Learning on Mammogram Classification and Localization,” Bioengineering, vol. 12, no. 4. 2025. doi: 10.3390/bioengineering12040325.

M. Kim, J. Jeong, dan S. Kim, “ECAP-YOLO: Efficient Channel Attention Pyramid YOLO for Small Object Detection in Aerial Image,” Remote Sensing, vol. 13, no. 23, hal. 4851, Nov 2021, doi: 10.3390/rs13234851.

Q. Wang, B. Wu, P. Zhu, P. Li, W. Zuo, dan Q. Hu, “ECA-Net: Efficient channel attention for deep convolutional neural networks,” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, no. October, hal. 11531–11539, 2020, doi: 10.1109/CVPR42600.2020.01155.

O. H. Khater, A. S. Shuaibu, S. U. Haq, dan A. J. Siddiqui, “AttCDCNet: Attention-Enhanced Chest Disease Classification Using X-Ray Images,” in 2025 IEEE 22nd International Multi-Conference on Systems, Signals & Devices (SSD), IEEE, Feb 2025, hal. 891–896. doi: 10.1109/SSD64182.2025.10989974.

B. Oltu, S. Güney, S. E. Yuksel, dan B. Dengiz, “Automated classification of chest X-rays: a deep learning approach with attention mechanisms,” BMC Medical Imaging, vol. 25, no. 1, hal. 71, Mar 2025, doi: 10.1186/s12880-025-01604-5.

S. Shastri, I. Kansal, S. Kumar, dan others, “CheXImageNet: a novel architecture for accurate classification of Covid-19 with chest x-ray digital images using deep convolutional neural networks,” Health Technology, vol. 12, hal. 193–204, 2022, doi: 10.1007/s12553-021-00630-x.

S. Kumar, S. Shastri, S. Mahajan, dan others, “LiteCovidNet: A lightweight deep neural network model for detection of COVID-19 using X-ray images,” International Journal of Imaging Systems and Technology, hal. 1–17, 2022, doi: 10.1002/ima.22770.

H. C. Reis dan V. Turk, “COVID-DSNet: A novel deep convolutional neural network for detection of coronavirus (SARS-CoV-2) cases from CT and Chest X-Ray images,” Artificial Intelligence in Medicine, vol. 134, hal. 102427, Des 2022, doi: 10.1016/j.artmed.2022.102427.

D. Zheng, Z. Wei, Z. Wu, dan J. Liu, “Learning Pairwise Potential CRFs in Deep Siamese Network for Change Detection,” Remote Sensing, vol. 14, no. 4, hal. 841, Feb 2022, doi: 10.3390/rs14040841.

I. Y. B. A. C. Goodfellow, Deep Learning (Adaptive Computation and Machine Learning series). The MIT Press, 2016. [Daring]. Tersedia pada: https://www.deeplearningbook.org/

H. Sun et al., “An Improved Medical Image Classification Algorithm Based on Adam Optimizer,” Mathematics, vol. 12, no. 16, hal. 2509, Agu 2024, doi: 10.3390/math12162509.

N. E. L. Faddouli, “Predicting The Severity Of New SARS-COV-2 Variants In Vaccinated Patients Using,” vol. 101, no. 10, hal. 4078–4086, 2023, [Daring]. Tersedia pada: http://www.jatit.org/volumes/Vol101No10/36Vol101No10.pdf