Penggunaan Dual Attention Network pada DenseNet-169 untuk Klasifikasi Multi-kelas Citra X-Ray Dada
DOI:
https://doi.org/10.52060/juptik.v4i1.4333Abstrak
Klasifikasi multi-kelas citra X-ray dada menjadi salah satu pendekatan yang dapat membantu membedakan kondisi COVID-19, normal, dan pneumonia secara otomatis. Namun, kemiripan karakteristik visual antar kelas dapat menyebabkan model kesulitan dalam mengekstraksi fitur yang relevan. Penelitian ini mengintegrasikan Dual Attention Network (DANet) pada DenseNet-169 untuk meningkatkan representasi fitur melalui kombinasi Grouped Channel Attention Module dan Strip Spatial Attention Module. Dataset yang digunakan terdiri atas 5.228 citra X-ray dada yang dibagi menjadi data latih dan data uji dengan rasio 80:20. Model DenseNet-169 baseline dan DenseNet-169 dengan DANet dievaluasi menggunakan akurasi, presisi, recall, F1-score, sensitivitas, spesifisitas, ROC-AUC, confusion matrix, dan Grad-CAM. Hasil pengujian menunjukkan bahwa DenseNet-169 dengan DANet memperoleh akurasi 98,47%, presisi 98,55%, recall 98,50%, F1-score 98,50%, sensitivitas 98,50%, dan spesifisitas 99,22%. Nilai ROC-AUC yang diperoleh pada kelas COVID-19, normal, dan pneumonia masing-masing sebesar 0,9994, 0,9989, dan 0,9980. Hasil tersebut menunjukkan bahwa DenseNet-169 dengan DANet memiliki kemampuan klasifikasi dan diskriminasi yang baik pada ketiga kelas. Visualisasi Grad-CAM menunjukkan bahwa DANet membantu model menghasilkan perhatian yang lebih terarah.
Referensi
[1] D. M. Ibrahim, N. M. Elshennawy, and A. M. Sarhan, “Deep-chest: Multi-classification deep learning model for diagnosing COVID-19, pneumonia, and lung cancer chest diseases,” Computers in Biology and Medicine, vol. 132, Art. no. 104348, Jan. 2021, https://doi.org/10.1016/j.compbiomed.2021.104348
[2] G. M. M. Alshmrani, Q. Ni, R. Jiang, H. Pervaiz, and N. M. Elshennawy, “A deep learning architecture for multi-class lung diseases classification using chest X-ray (CXR) images,” Alexandria Engineering Journal, vol. 64, pp. 923–935, Feb. 2023, https://doi.org/10.1016/j.aej.2022.10.053
[3] S. Kim, B. Rim, S. Choi, A. Lee, S. Min, and M. Hong, “Deep Learning in Multi-Class Lung Diseases’ Classification on Chest X-ray Images,” Diagnostics, vol. 12, no. 4, no. 4, Art. no. 915, Apr. 2022, https://doi.org/10.3390/diagnostics12040915
[4] S. Katreddi, A. Midatani, A. P. Roy, U. Velpuri, and S. Kasani, “Pediatric pneumonia X-ray image classification: predictive model development with DenseNet-169 transfer learning,” Journal of Medical Artificial Intelligence, vol. 8, Art. no. 37, Apr. 2025, https://doi.org/10.21037/jmai-24-356
[5] Md. S. Alam, D. Wang, and A. Sowmya, “DLA Net: dual lesion attention network for classification of pneumoconiosis using chest X ray images,” Scientific Reports, vol. 14, Art. no. 11616, May 2024 doi: https://doi.org/10.1038/s41598-024-61024-3
[6] D. Li, “Attention-enhanced architecture for improved pneumonia detection in chest X-ray images,” BMC Medical Imaging, vol. 24, no. 1, Art. no. 6, Jan. 2024, https://doi.org/10.1186/s12880-023-01177-1
[7] X. Li et al., “Deep Learning Attention Mechanism in Medical Image Analysis: Basics and Beyonds,” International Journal of Network Dynamics and Intelligence, vol. 2, no. 1, pp. 93–116, Mar. 2023 https://doi.org/10.53941/ijndi0201006
[8] Q. Xu and W. Duan, “DualAttNet: Synergistic fusion of image-level and fine-grained disease attention for multi-label lesion detection in chest X-rays,” Computers in Biology and Medicine, vol. 168, Art. no. 107742, Jan. 2024, https://doi.org/10.1016/j.compbiomed.2023.107742
[9] J. Zhang, X. Chen, B. Yang, Q. Guan, Q. Chen, J. Chen, Q. Wu, Y. Xie, and Y. Xia, “Advances in attention mechanisms for medical image segmentation,” Computer Science Review, vol. 56, Art. no. 100721, May 2025 https://doi.org/10.1016/j.cosrev.2024.100721
[10] L. Chen, T. Mao, and Q. Zhang, “Identifying cardiomegaly in chest x-rays using dual attention network,” Applied Intelligence, vol. 52, no. 10, pp. 11058–11067, Jul. 2022, https://doi.org/10.1007/s10489-021-02935-w
[11] L. Z. Daulay, B. S. Negara, Y. Vitriani, I. Iskandar, and F. Kurnia, “Penerapan Squeeze-and-Excitation Attention pada DenseNet169 untuk Klasifikasi Multi-Kelas Citra X-Ray Dada: Squeeze-and-Excitation Attention on DenseNet169 for Multi-Class Classification of Chest X-Ray Images,” MALCOM: Indonesian Journal of Machine Learning and Computer Science, vol. 6, no. 2, pp. 986–996, Apr. 2026, doi: 10.57152/malcom.v6i2.2665.
[12] L. A. Gonçalves, G. B. Junior, M. L. L. Bessa, C. E. F. Matos, and A. G. S. Fernandes, “DualAttentionNet: A Convolutional Neural Network for Thoracic Disease Classification in Chest X-Rays,” Procedia Computer Science, vol. 256, pp. 797–804, 2025, https://doi.org/10.1016/j.procs.2025.02.181.
[13] S. Kumar, “Covid19-Pneumonia-Normal Chest X-Ray Images,” Mendeley Data, V1, 2022, doi: 10.17632/dvntn9yhd2.1. Accessed: Apr. 08, 2026. [Online]. Available: https://data.mendeley.com/datasets/dvntn9yhd2/1
[14] H. Bichri, A. Chergui, and M. Hain, “Investigating the impact of train/test split ratio on the performance of pre-trained models with custom datasets,” International Journal of Advanced Computer Science and Applications, vol. 15, no. 2, pp. 331–339, 2024, https://doi.org/10.14569/IJACSA.2024.0150235
[15] M. R. S. Sahri and Y. Azhar, “Klasifikasi pengemudi yang terdistraksi menggunakan DenseNet 169,” Jurnal Repositor, vol. 7, no. 3, pp. 361–370, Aug. 2025, doi: 10.22219/repositor.v7i3.38353.
[16] B. Oltu, S. Güney, S. E. Yuksel, and B. Dengiz, “Automated classification of chest X-rays: a deep learning approach with attention mechanisms,” BMC Medical Imaging, vol. 25, no. 1, Art. no. 71, Mar. 2025, https://doi.org/10.1186/s12880-025-01604-5
[17] T. Zebin and S. Rezvy, “COVID-19 detection and disease progression visualization: Deep learning on chest X-rays for classification and coarse localization,” Applied Intelligence, vol. 51, no. 2, pp. 1010–1021, Feb. 2021, https://doi.org/10.1007/s10489-020-01867-1
[18] M. Elgendi et al., “The Effectiveness of Image Augmentation in Deep Learning Networks for Detecting COVID-19: A Geometric Transformation Perspective,” Frontiers in Medicine, vol. 8, Art. no. 629134, Mar. 2021, https://doi.org/10.3389/fmed.2021.629134
[19] M. Bundea and G. M. Danciu, “Pneumonia Image Classification Using DenseNet Architecture,” Information (Switzerland), vol. 15, no. 10, 2024, https://doi.org/10.3390/info15100611
[20] F. Kanavati and M. Tsuneki, “Partial transfusion: on the expressive influence of trainable batch norm parameters for transfer learning,” in Proceedings of the Fourth Conference on Medical Imaging with Deep Learning, ser. Proceedings of Machine Learning Research, vol. 143, pp. 338–353, Jul. 2021. [Online]. Available: https://proceedings.mlr.press/v143/kanavati21a.html
[21] S. Patel, “Classification of COVID-19 from chest X-ray images using a deep convolutional neural network,” Turkish Journal of Computer and Mathematics Education, vol. 12, no. 9, pp. 2643–2651, Apr. 2021. [Online]. Available: https://turcomat.org/index.php/turkbilmat/article/view/3983
[22] Ž. Vujović, “Classification Model Evaluation Metrics,” International Journal of Advanced Computer Science and Applications, vol. 12, no. 6, pp. 599–606, 2021, https://doi.org/10.14569/IJACSA.2021.0120670
[23] F. J. M. Shamrat, S. Azam, A. Karim, K. Ahmed, F. M. Bui, and F. De Boer, “High-precision multiclass classification of lung disease through customized MobileNetV2 from chest X-ray images,” Computers in Biology and Medicine, vol. 155, Art. no. 106646, Mar. 2023, https://doi.org/10.1016/j.compbiomed.2023.106646
[24] O. Rainio, J. Teuho, and R. Klén, “Evaluation metrics and statistical tests for machine learning,” Scientific Reports, vol. 14, no. 1, Art. no. 6086, Mar. 2024, https://doi.org/10.1038/s41598-024-56706-x
[25] K. Raghavan, S. B, and K. v, “Attention guided grad-CAM : an improved explainable artificial intelligence model for infrared breast cancer detection,” Multimedia Tools Application., vol. 83, no. 19, pp. 57551–57578, Jun. 2024, https://doi.org/10.1007/s11042-023-17776-7
| Keywords | : |
Kata Kunci:
DenseNet-169, Dual Attention Network, Citra X-Ray Dada, Klasifikasi Multi-Kelas, Deep Learning
|
| Galleys | : | |
| Diterbitkan | : |
2026-06-01
|
| Terbitan | : |
Hak Cipta (c) 2026 Jurnal Pengembangan Teknologi Informasi dan Komunikasi (JUPTIK)
Artikel ini berlisensi Creative Commons Attribution 4.0 International License.
