.png)
Improving Early Detection of Cervical Cancer Through Deep Learning-Based Pap Smear Image Classification
Abstract
Cervical cancer is one of the leading causes of death in women worldwide, making early detection of the disease crucial. This study proposes a deep learning-based approach that has the advantage of leveraging pre-trained models to save data, time, and computation to classify Pap smear images without relying on segmentation, which is traditionally required to isolate key morphological features. Instead, this method leverages deep learning to identify patterns directly from raw images, reducing preprocessing complexity while maintaining high accuracy. The dataset used in this study is a public data repository from Nusa Mandiri University (RepomedUNM), which has a wider variety of data. This dataset is used to classify images into four categories: Normal, LSIL, HSIL, and Koilocytes. The dataset consists of 400 images evenly distributed, ensuring class balance during training. Transfer learning is applied using five Convolutional Neural Network (CNN) architectures: ResNet152V2, InceptionV3, ResNet50V2, DenseNet201, and ConvNeXtBase. To prevent overfitting, techniques such as data augmentation, dropout regularization, and class weight adjustment are applied. The evaluation results in this study showed the highest accuracy with a value of ResNet152V2 = 0.9025, InceptionV3 = 0.8953 and DenseNet201 = 0.8845. ResNet152V2 excelled in extracting complex features, while InceptionV3 showed better computational efficiency. The study also highlighted the clinical impact of misclassification between Koilocytes and LSIL, which may affect diagnostic outcomes. Data augmentation techniques, including horizontal and vertical flipping and normalization, improved the model's generalization to a wide variety of images. Specificity was emphasized as a key evaluation metric to minimize false positives, which is important in medical diagnostics. The findings confirmed that transfer learning effectively overcomes the limitations of small datasets and improves the classification accuracy of pap smear images. This approach shows potential for integration into clinical workflows to enable automated and efficient cervical cancer detection.
Keywords
Full Text:
PDFReferences
G. Putri, “Wanita Beresiko Terkena Kanker Serviks,” Web Dirjen Pelayanan Kesehatan, 2022. https://yankes.kemkes.go.id/view_artikel/389/wanita-beresiko-terkena-kanker-serviks (accessed Jul. 22, 2022).
Y. Huang and H. Zhu, “Segmentation of Overlapped Cervical Cells Using Asymmetric Mixture Model and Shape Constraint Level Set Method,” Hindawi, vol. 2020, pp. 1–14, 2020, doi: https://doi.org/10.1155/2020/3728572.
D. Riana, D. H. Widyantoro, and T. L. Mengko, “Extraction and Classification Texture of Inflammatory Cells and Nuclei in Normal Pap smear Images,” 2015 4th Int. Conf. Instrumentation, Commun. Inf. Technol. Biomed. Eng., 2015.
W. William, A. Ware, A. H. Basaza-Ejiri, and J. Obungoloch, “Cervical cancer classification from Pap-smears using an enhanced fuzzy C-means algorithm,” Informatics Med. Unlocked, vol. 14, pp. 23–33, 2019, doi: https://doi.org/10.1016/j.imu.2019.02.001.
W. William, A. Ware, A. H. Basaza-Ejiri, and J. Obungoloch, “A pap-smear analysis tool (PAT) for detection of cervical cancer from pap-smear images,” BioMedical Engineering Online, vol. 18, no. 1. 2019. doi: 10.1186/s12938-019-0634-5.
X. Li, Z. Xu, X. Shen, Y. Zhou, B. Xiao, and T. Q. Li, “Detection of cervical cancer cells in whole slide images using deformable and global context aware faster rcnn-fpn,” Curr. Oncol., vol. 28, no. 5, pp. 3585–3601, 2021, doi: 10.3390/curroncol28050307.
A. Tareef et al., “Optimizing the cervix cytological examination based on deep learning and dynamic shape modeling,” Neurocomputing, vol. 248, pp. 28–40, 2017, doi: https://doi.org/10.1016/j.neucom.2017.01.093.
R. R. V Silva, F. H. D. Araujo, D. M. Ushizima, A. G. C. Bianchi, C. M. Carneiro, and F. N. S. Medeiros, “Radial feature descriptors for cell classification and recommendation,” J. Vis. Commun. Image Represent., vol. 62, pp. 105–116, 2019, doi: https://doi.org/10.1016/j.jvcir.2019.04.012.
S. E. Plissiti ; P. Dimitrakopoulos ; G. Sfikas ; Christophoros Nikou ; O. Krikoni ; A. Charchanti, “Dataset for Feature and Image Based Classification of Normal and Pathological Cervical Cells in Pap Smear Images,” 25th IEEE Int. Conf. Image Process., 2018.
M. K. Bhowmik, S. D. Roy, N. Nath, and A. Datta, “Nucleus Region Segmentation Towards Cervical Cancer Screening Using AGMC-TU Pap-Smear Dataset,” in Proceedings of the International Conference on Pattern Recognition and Artificial Intelligence, in {PRAI} 2018. New York, NY, USA: Association for Computing Machinery, 2018, pp. 44–53. doi: 10.1145/3243250.3243258.
N. Merlina, E. Noersasongko, P. N. Andono, M. A. Soeleman, D. Riana, and J. Na, “Medical Image Registration at Pap Smear for Early Identification of Cervical Cancer,” vol. 12, no. 2, pp. 726–731, 2023, doi: 10.18421/TEM122.
N. Merlina, E. Noersasongko, P. N. Andono, M. A. Soeleman, and D. Riana, “Optimization of the preprocessing method for edge detection on overlapping cells at Pap smear images,” JOIV, vol. 7, no. 2, 2023, doi: http://dx.doi.org/10.30630/joiv.7.2.1329.
N. Youneszade, M. Marjani, and C. P. Pei, “Deep Learning in Cervical Cancer Diagnosis: Architecture, Opportunities, and Open Research Challenges,” IEEE Access, vol. 11, no. January, pp. 6133–6149, 2023, doi: 10.1109/ACCESS.2023.3235833.
M. Kalbhor, S. Shinde, D. E. Popescu, and D. J. Hemanth, “Hybridization of Deep Learning Pre-Trained Models with Machine Learning Classifiers and Fuzzy Min–Max Neural Network for Cervical Cancer Diagnosis,” Diagnostics, vol. 13, no. 7, 2023, doi: 10.3390/diagnostics13071363.
M. MOMENZADEH, M. SEHHATI, A. M. DEHNAVI, A. TALEBI, and H. RABBANI, “Automatic Diagnosis of Vulvovaginal Candidiasis from Papsmear Images . Segmentasi dan Clasification,” Microscopy, vol. 267, no. 3, pp. 299–308, 2017, doi: https://doi.org/10.1111/jmi.12566.
A. A. Rudiansyah, Lemi Iryani, Lucky Indra Kesuma, Puspa Sari, “Deep Learning based Cervical Cancer Classification and Segmentation from Pap Smears Images using an EfficientNet,” J. Informatics Telecommun. Eng., vol. 7, no. 2, pp. 575–586, 2024, doi: 10.31289/jite.v7i2.10399.
O. Holmström et al., “Point-of-Care Digital Cytology with Artificial Intelligence for Cervical Cancer Screening in a Resource-Limited Setting,” JAMA Netw. Open, vol. 4, no. 3, pp. 1–13, 2021, doi: 10.1001/jamanetworkopen.2021.1740.
S. L. Tan, G. Selvachandran, W. Ding, R. Paramesran, and K. Kotecha, “Cervical Cancer Classification From Pap Smear Images Using Deep Convolutional Neural Network Models,” Interdiscip. Sci. – Comput. Life Sci., vol. 16, no. 1, pp. 16–38, 2023, doi: 10.1007/s12539-023-00589-5.
W. W. Q. L. H. F. J. S. H. L. R. Yang and A. Authors, “Salient Object Detection in the Deep Learning Era: An In-Depth Survey,” ieee, vol. 44, no. 6, pp. 3239–3259, 2021, doi: 10.1109/TPAMI.2021.3051099.
A. Borji, M.-M. Cheng, Q. Hou, H. Jiang, and J. Li, Computational Visual Media Salient object detection: A survey, vol. 5, no. 2. 2019. [Online]. Available: https://doi.org/10.1007/s41095-019-0149-9
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, p. e22324, 2023, doi: 10.1016/j.heliyon.2023.e22324.
Y. Y. Liu, P. Sun, N. Wergeles, “A survey and performance evaluation of deep learning methods for small object detection,” Expert Syst. with Appl. Elsevier, vol. 172, no. 6, pp. 1–14, 2021, doi: https://doi.org/10.1016/j.eswa.2021.114602.
P. C. et al Xiang Y, Sun W, “A novel automation-assisted cervical cancer reading method based on convolutional neural network,” Biocybern Biomed Eng, vol. 40, no. 2, pp. 611–623, 2020, doi: https://doi.org/ 10.1016/j.bbe.2020.01.01.
R. E. V. S. V. V. A. Mahanti, “Cervical Cancer Diagnostics Healthcare System Using Hybrid Object Detection Adversarial Networks,” IEEE J. Biomed. Heal. Informatics, vol. 26, no. 4, pp. 1464–1471, 2021, doi: 10.1109/JBHI.2021.3094311.
Y. Karasu Benyes, E. C. Welch, A. Singhal, J. Ou, and A. Tripathi, “A Comparative Analysis of Deep Learning Models for Automated Cross-Preparation Diagnosis of Multi-Cell Liquid Pap Smear Images,” Diagnostics, vol. 12, no. 8, 2022, doi: 10.3390/diagnostics12081838.
P. B. J. M.B. Bijoy, S.M. Akondi, S. Abdul Fathaah, A. Raut, P.N. Pournami, “Cervix type detection using a self-supervision boosted object detection technique,” Int. J. Imag. Syst. Technol, pp. 1–6, 2022, doi: https://doi.org/10.1002/ima.22696.
P. Huang et al., “Classification of cervical biopsy images based on LASSO and EL-SVM,” IEEE Access, vol. 8, pp. 24219–24228, 2020, doi: 10.1109/ACCESS.2020.2970121.
L. P. et al Zhang T, Luo Y, “Cervical precancerous lesions classification using pre-trained densely connected convolutional networks with colposcopy images,” Biomed Signal Process Control, vol. 55, 2020, doi: https://doi.org/10.1016/j.bspc.2019.101566.
W. Wang et al., “3cDe-Net: a cervical cancer cell detection network based on an improved backbone network and multiscale feature fusion,” BMC Med. Imaging, vol. 22, no. 1, pp. 1–13, 2022, doi: 10.1186/s12880-022-00852-z.
W. Mousser and S. Ouadfel, “Deep {Feature} {Extraction} for {Pap}-{Smear} {Image} {Classification}: {A} {Comparative} {Study},” in Proceedings of the 2019 5th {International} {Conference} on {Computer} and {Technology} {Applications}, in {ICCTA} 2019. New York, NY, USA: Association for Computing Machinery, 2019, pp. 6–10. doi: 10.1145/3323933.3324060.
P. Wang, L. Wang, Y. Li, Q. Song, S. Lv, and X. Hu, “Automatic cell nuclei segmentation and classification of cervical Pap smear images,” Biomed. Signal Process. Control, vol. 48, pp. 93–103, 2019, doi: https://doi.org/10.1016/j.bspc.2018.09.008.
M. M. Rahaman et al., “A Survey for Cervical Cytopathology Image Analysis Using Deep Learning,” IEEE Access, vol. 8, pp. 61687–61710, 2020, doi: 10.1109/ACCESS.2020.2983186.
E. Hussain, L. B. Mahanta, C. R. Das, and R. K. Talukdar, “A comprehensive study on the multi-class cervical cancer diagnostic prediction on pap smear images using a fusion-based decision from ensemble deep convolutional neural network,” Tissue Cell, vol. 65, no. November 2019, 2020, doi: 10.1016/j.tice.2020.101347.
C. Zhao and R. Shuai, Improving cervical cancer classification with imbalanced datasets combining taming transformers with T2T-ViT, no. 2. 2022.
DOI: https://doi.org/10.47738/jads.v6i2.576
Refbacks
- There are currently no refbacks.
Journal of Applied Data Sciences
| ISSN | : | 2723-6471 (Online) |
| Publisher | : | Bright Publisher |
| Website | : | http://bright-journal.org/JADS |
| : | taqwa@amikompurwokerto.ac.id (principal contact) | |
| support@bright-journal.org (technical issues) |
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0