OPTIMIZING VGG-16 CONVOLUTIONAL NEURAL NETWORK FOR PAP SMEAR IMAGE CLASSIFICATION IN CERVICAL CANCER DETECTION
DOI:
https://doi.org/10.33480/jitk.v11i3.7131Kata Kunci:
Cervical Cancer, Image Classification, Pap Smear, Transfer Learning, VGG16Abstrak
Early detection of cervical cancer through Pap smear image analysis plays a crucial role in reducing mortality rates associated with this disease. This study aims to optimize the VGG16 architecture to improve the classification accuracy of Pap smear images. The proposed method employs transfer learning with pre-trained ImageNet weights, customization of fully connected layers, and data augmentation techniques to enhance the diversity of training images. Experimental results demonstrate a significant improvement in training accuracy, reaching 98.50%, while validation accuracy remained stable at 88.24%, indicating potential overfitting. Performance testing on unseen data yielded an accuracy of 80%, with high precision for the negative class but low recall for the positive class, suggesting a bias toward the majority class. These findings highlight the need for additional strategies, such as data balancing and hybrid method integration, to improve sensitivity to positive cases. This research contributes to the development of adaptive deep learning-based classification models that support clinical decision-making in cervical cancer screening and opens opportunities for further research on model optimization and dataset expansion.
Unduhan
Referensi
[1] M. Kalbhor, S. Shinde, P. Wajire, and H. Jude, “CerviCell-detector: An object detection approach for identifying the cancerous cells in pap smear images of cervical cancer,” Heliyon, vol. 9, no. 11, 2023, doi: 10.1016/j.heliyon.2023.e22324.
[2] R. Kundu and S. Chattopadhyay, “Deep features selection through genetic algorithm for cervical pre-cancerous cell classification,” vol. 82, no. 9, pp. 13431–13452, 2023, doi: 10.1007/s11042-022-13736-9.
[3] X. Zhang et al., “FD-Net: Feature Distillation Network for Oral Squamous Cell Carcinoma Lymph Node Segmentation in Hyperspectral Imagery,” vol. 28, no. 3, pp. 1552–1563, 2024, doi: 10.1109/JBHI.2024.3350245.
[4] B. Chitra, S. S. Kumar, and D. Subbulekshmi, “Prediction Models Applying Convolutional Neural Network based Deep Learning to Cervical Cancer Outcomes,” vol. 70, no. 8, pp. 7058–7068, 2024, doi: 10.1080/03772063.2024.2305831.
[5] R. Ahmed, N. Dahmani, G. Dahy, A. Darwish, and A. E. Hassanien, “Early Detection and Categorization of Cervical Cancer Cells Using Smoothing Cross Entropy-Based Multi-Deep Transfer Learning,” vol. 12, pp. 157838–157853, 2024, doi: 10.1109/ACCESS.2024.3485888.
[6] W. Gao, D. Wang, and Y. Huang, “Designing a Deep Learning-Driven Resource-Efficient Diagnostic System for Metastatic Breast Cancer: Reducing Long Delays of Clinical Diagnosis and Improving Patient Survival in Developing Countries,” Cancer Inform, vol. 22, 2023, doi: 10.1177/11769351231214446.
[7] J. Yi, X. Liu, S. Cheng, L. Chen, and S. Zeng, “Multi-scale window transformer for cervical cytopathology image recognition,” vol. 24, pp. 314–321, 2024, doi: 10.1016/j.csbj.2024.04.028.
[8] M. Salehi, A. Vafaei Sadr, S. R. Mahdavi, H. Arabi, I. Shiri, and R. Reiazi, “Deep Learning-based Non-rigid Image Registration for High-dose Rate Brachytherapy in Inter-fraction Cervical Cancer,” vol. 36, no. 2, pp. 574–587, 2023, doi: 10.1007/s10278-022-00732-6.
[9] Y. Khalifa, C. Donohue, J. L. Coyle, and E. Sejdić, “Autonomous Swallow Segment Extraction Using Deep Learning in Neck-Sensor Vibratory Signals From Patients With Dysphagia,” vol. 27, no. 2, pp. 956–967, 2023, doi: 10.1109/JBHI.2022.3224323.
[10] J. B. A. Teixeira et al., “Segmentation of cervical nuclei using convolutional neural network for conventional cytology,” vol. 11, no. 5, pp. 1876–1888, 2023, doi: 10.1080/21681163.2023.2197086.
[11] R. Klangbunrueang, P. Pookduang, W. Chansanam, and T. Lunrasri, “AI-Powered Lung Cancer Detection: Assessing VGG16 and CNN Architectures for CT Scan Image Classification,” Informatics, vol. 12, no. 1, p. 18, 2025, doi: 10.3390/informatics12010018.
[12] V. Lakide, “Advancement of Lung Cancer Diagnosis With Transfer Learning: Insights From VGG16 Implementation,” Journal of Electronics Electromedical Engineering and Medical Informatics, vol. 7, no. 3, pp. 729–739, 2025, doi: 10.35882/jeeemi.v7i3.704.
[13] Z. Hameed, S. Zahia, B. García-Zapirain, J. J. Aguirre, and A. M. Vanegas, “Breast Cancer Histopathology Image Classification Using an Ensemble of Deep Learning Models,” Sensors, vol. 20, no. 16, p. 4373, 2020, doi: 10.3390/s20164373.
[14] F. Hashem et al., “Exploring Data Imbalance Challenges in Cervical Cancer Detection Using Advanced Deep Learning Models,” in 2024 IEEE International Conference on Smart Systems and Power Management, IC2SPM 2024, 2024, pp. 95–101. doi: 10.1109/IC2SPM62723.2024.10841356.
[15] F. Hashem et al., “Exploring Data Imbalance Challenges in Cervical Cancer Detection Using Advanced Deep Learning Models,” in 2024 IEEE International Conference on Smart Systems and Power Management, IC2SPM 2024, Institute of Electrical and Electronics Engineers Inc., 2024, pp. 95–101. doi: 10.1109/IC2SPM62723.2024.10841356.
[16] L. W. Habtemariam, E. T. Zewde, and G. L. Simegn, “Cervix Type and Cervical Cancer Classification System Using Deep Learning Techniques,” Medical Devices Evidence and Research, vol. Volume 15, pp. 163–176, 2022, doi: 10.2147/mder.s366303.
[17] H. Yi, “A Review of Convolutional Neural Networks in Cancer Image Classification,” Applied and Computational Engineering, vol. 97, no. 1, pp. 69–74, 2024, doi: 10.54254/2755-2721/97/20241334.
[18] R. Maurya, N. Nath Pandey, and M. Kishore Dutta, “VisionCervix: Papanicolaou cervical smears classification using novel CNN-Vision ensemble approach,” Biomed Signal Process Control, vol. 79, 2023, doi: 10.1016/j.bspc.2022.104156.
[19] P. Yadav, A. Gupta, A. Parveen, and A. Kumar, “Advancement in Deep Learning Methods for Diagnosis and Prognosis Of Cervical Cancer,” Curr Genomics, vol. 23, no. 4, pp. 234–245, 2022, doi: 10.2174/1389202923666220511155939.
[20] M. Arya, P. K. Yadav, A. Jain, M. Gupta, S. Agarwal, and A. S. Rajpoot, “Neural Network to detect Cervical Cancer early using Pap smears Images,” in Proceedings of International Conference on Contemporary Computing and Informatics, IC3I 2024, 2024, pp. 324–329. doi: 10.1109/IC3I61595.2024.10828866.
[21] W. Huang, S. Sun, Z. Yu, S. Lu, and H. Feng, “Chronic Cervicitis and Cervical Cancer Detection Based on Deep Learning of Colposcopy Images Toward Translational Pharmacology,” Front Pharmacol, vol. 13, 2022, doi: 10.3389/fphar.2022.911962.
[22] T. Yang, H. Hu, X. Li, M. Qing, L. Chen, and Q. Huang, “A pyramid convolutional mixer for cervical pap-smear image classification tasks,” Biomed Signal Process Control, vol. 99, 2025, doi: 10.1016/j.bspc.2024.106789.
[23] O. Attallah, “CerCan·Net: Cervical cancer classification model via multi-layer feature ensembles of lightweight CNNs and transfer learning,” vol. 229, 2023, doi: 10.1016/j.eswa.2023.120624.
[24] S. Jung, S. Wang, and D. Lee, “CancerGATE: Prediction of cancer-driver genes using graph attention autoencoders,” vol. 176, 2024, doi: 10.1016/j.compbiomed.2024.108568.
[25] L. Mishra, R. Dasgupta, Y. S. Chowdhury, S. Nanda, and S. Nanda, “Cervical Cancer Detection Using Hybrid Pooling-Based Convolutional Neural Network Approach,” Indian J Gynecol Oncol, vol. 21, no. 2, 2023, doi: 10.1007/s40944-023-00712-w.
[26] C. Zhang, D. Jia, Z. Li, and N. Wu, “Auxiliary classification of cervical cells based on multi-domain hybrid deep learning framework,” Biomed Signal Process Control, vol. 77, 2022, doi: 10.1016/j.bspc.2022.103739.
[27] A. Khan, S. Han, N. Ilyas, Y.-M. Lee, and B. Lee, “CervixFormer: A Multi-scale swin transformer-Based cervical pap-Smear WSI classification framework,” vol. 240, 2023, doi: 10.1016/j.cmpb.2023.107718.
Unduhan
Diterbitkan
Terbitan
Bagian
Lisensi
Hak Cipta (c) 2026 Odi Nurdiawan, Heliyanti Susana, Ade Rizki Rinaldi, Ahmad Asyraful Hijrah, Indah Diniarti
Artikel ini berlisensi Creative Commons Attribution-NonCommercial 4.0 International License.
-a.jpg)
-b.jpg)
