A systematic review of effective data augmentation in cervical cancer detection

• Autorzy: Wubineh Betelhem Zewdu , Rusiecki Andrzej , Halawa Krzysztof

Identyfikatory

DOI

10.24425/ijet.2025.153582

• Języki publikacji: EN

Abstrakty

EN

The rapid progress of AI has made computer-assisted systems essential in medical fields like cervical cytology analysis. Deep learning requires large datasets, but data scarcity and privacy concerns pose challenges. Data augmentation addresses this by generating additional images and improving model accuracy and generalizability. This review examines effective augmentation techniques and top-performing deep-learning models for segmentation and classification in cervical cancer detection. Analyzing 57 articles, we found that hybrid deep feature fusion with augmentation (rotation, flipping, shifting, brightness adjustments) achieved 99.8% accuracy in binary and 99.1% in multiclass classification. Augmentation is vital for enhancing model performance in limited data scenarios.

Słowa kluczowe

EN

cervical cancer; data augmentation; deep learning; artificially generated images

• Wydawca: Polish Academy of Sciences, Committee of Electronics and Telecommunication
• Czasopismo: International Journal of Electronics and Telecommunications
• Rocznik: 2025
• Tom: Vol. 71, No. 2
• Strony: 369--377
• Opis fizyczny: Bibliogr. 74 poz., tab., rys.

Twórcy

autor

Wubineh Betelhem Zewdu

• Wroclaw University of Science and Technology, Poland

• https://orcid.org/0000-0002-4790-7449

autor

Rusiecki Andrzej

• Wroclaw University of Science and Technology, Poland

• https://orcid.org/0000-0003-2239-1076

autor

Halawa Krzysztof

• Wroclaw University of Science and Technology, Poland

• https://orcid.org/0000-0001-6508-0468

Bibliografia

• [1] Z. Ahmad, S. Rahim, M. Zubair, and J. Abdul-Ghafar, “Artificial intelligence (AI) in medicine, current applications and future role with special emphasis on its potential and promise in pathology: present and future impact, obstacles including costs and acceptance among pathologists, practical and philosoph,” Diagn. Pathol., vol. 16, no. 1, pp. 1-16, 2021, https:\\doi.org\10.1186/s13000-021-01085-4
• [2] K. P. Win, Y. Kitjaidure, K. Hamamoto, and T. M. Aung, “Computer-assisted screening for cervical cancer using digital image processing of pap smear images,” Appl. Sci., vol. 10, no. 5, 2020, https:\\doi.org\10.3390/app10051800.
• [3] B. Z. Wubineh, A. Rusiecki, and K. Halawa, “Segmentation and Classification Techniques for Pap smear Images in Detecting Cervical Cancer: A Systematic Review,” IEEE Access, vol. 12, no. August, pp. 118195-118213, 2024, https:\\doi.org\10.1109/ACCESS.2024.3447887.
• [4] P. Chlap, H. Min, N. Vandenberg, J. Dowling, L. Holloway, and A. Haworth, “A review of medical image data augmentation techniques for deep learning applications,” J. Med. Imaging Radiat. Oncol., vol. 65, no. 5, pp. 545-563, 2021, https:\\doi.org\10.1111/1754-9485.13261.
• [5] D. Muchlinski, “Machine learning and deep learning,” Elgar Encycl. Technol. Polit., pp. 114-118, 2022, https:\\doi.org\10.4337/9781800374263.machine.learning.deep.
• [6] T. Wan, S. Xu, C. Sang, Y. Jin, and Z. Qin, “Accurate segmentation of overlapping cells in cervical cytology with deep convolutional neural networks,” Neurocomputing, vol. 365, pp. 157-170, 2019, https:\\doi.org\10.1016/j.neucom.2019.06.086.
• [7] S. K. Zhou et al., “A Review of Deep Learning in Medical Imaging: Imaging Traits, Technology Trends, Case Studies with Progress Highlights, and Future Promises,” Proc. IEEE, vol. 109, no. 5, pp. 820-838, 2021, https:\\doi.org\10.1109/JPROC.2021.3054390.
• [8] C. Shorten and T. M. Khoshgoftaar, “A survey on Image Data Augmentation for Deep Learning,” J. Big Data, vol. 6, no. 1, 2019, https:\\doi.org\10.1186/s40537-019-0197-0.
• [9] V. Sandfort, K. Yan, P. J. Pickhardt, and R. M. Summers, “Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks,” Sci. Rep., vol. 9, no. 1, pp. 1-9, 2019, https:\\doi.org\10.1038/s41598-019-52737-x.
• [10] J. Nalepa, M. Marcinkiewicz, and M. Kawulok, “Data Augmentation for Brain-Tumor Segmentation: A Review,” Front. Comput. Neurosci., vol. 13, no. December, pp. 1-18, 2019, https:\\doi.org\10.3389/fncom.2019.00083.
• [11] Z. Hussain, F. Gimenez, D. Yi, and D. Rubin, “Differential Data Augmentation Techniques for Medical Imaging Classification Tasks,” AMIA ... Annu. Symp. proceedings. AMIA Symp., vol. 2017, no. May, pp. 979-984, 2017.
• [12] W. A. Mustafa, N. A. Alias, M. A. Jamlos, S. Ismail, and H. Alquran, “A Recent Systematic Review of Cervical Cancer Diagnosis: Detection and Classification,” J. Adv. Res. Appl. Sci. Eng. Technol., vol. 28, no. 1, pp. 81-96, 2022, https:\\doi.org\10.37934/araset.28.1.8196.
• [13] K. Maharana, S. Mondal, and B. Nemade, “A review: Data pre-processing and data augmentation techniques,” Glob. Transitions Proc., vol. 3, no. 1, pp. 91-99, 2022, https:\\doi.org\10.1016/j.gltp.2022.04.020.
• [14] J. J. Jeong, A. Tariq, T. Adejumo, H. Trivedi, J. W. Gichoya, and I. Banerjee, “Systematic Review of Generative Adversarial Networks (GANs) for Medical Image Classification and Segmentation,” J. Digit. Imaging, vol. 35, no. 2, pp. 137-152, 2022, https:\\doi.org\10.1007/s10278-021-00556-w.
• [15] B. Z. Wubineh, A. Rusiecki, and K. Halawa, “Data Augmentation Techniques to Detect Cervical Cancer Using Deep Learning: A Systematic Review,” in International Conference on Dependability of Computer Systems, Cham: Springer Nature Switzerland, 2024, pp. 325-336.
• [16] H. Kamioka, “Preferred reporting items for systematic review and meta-analysis protocols (prisma-p) 2015 statement,” Japanese Pharmacol. Ther., vol. 47, no. 8, pp. 1177-1185, 2019.
• [17] R. Sarkis-Onofre, F. Catalá-López, E. Aromataris, and C. Lockwood, “How to properly use the PRISMA Statement,” Syst. Rev., vol. 10, no. 1, pp. 13-15, 2021, https:\\doi.org\10.1186/s13643-021-01671-z.
• [18] Y. Zhao, C. Fu, S. Xu, L. Cao, and H. feng Ma, “LFANet: Lightweight feature attention network for abnormal cell segmentation in cervical cytology images,” Comput. Biol. Med., vol. 145, no. November 2021, p. 105500, 2022, https:\\doi.org\10.1016/j.compbiomed.2022.105500.
• [19] J. G. Atkinson Amorim et al., “A novel approach on segmentation of Agnor-stained cytology images using deep learning,” Proc. - IEEE Symp. Comput. Med. Syst., vol. 2020-July, pp. 552-557, 2020, https:\\doi.org\10.1109/CBMS49503.2020.00110.
• [20] Y. Zhang, Y. Zall, R. Nissim, Satyam, and R. Zimmermann, “Evaluation of a new dataset for visual detection of cervical precancerous lesions,” Expert Syst. Appl., vol. 190, no. October 2021, p. 116048, 2022, https:\\doi.org\10.1016/j.eswa.2021.116048.
• [21] N. Sompawong et al., “Automated Pap Smear Cervical Cancer Screening Using Deep Learning,” Proc. Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. EMBS, pp. 7044-7048, 2019, https:\\doi.org\10.1109/EMBC.2019.8856369.
• [22] F. Miranda Ruiz et al., “CNN stability training improves robustness to scanner and IHC-based image variability for epithelium segmentation in cervical histology,” Front. Med., vol. 10, no. July, pp. 1-14, 2023, https:\\doi.org\10.3389/fmed.2023.1173616.
• [23] J. Zhao, Y. jun He, S. H. Zhou, J. Qin, and Y. ning Xie, “CNSeg: A dataset for cervical nuclear segmentation,” Comput. Methods Programs Biomed., vol. 241, no. May, p. 107732, 2023, https:\\doi.org\10.1016/j.cmpb.2023.107732.
• [24] Y. C. Lin et al., “Deep learning for fully automated tumor segmentation and extraction of magnetic resonance radiomics features in cervical cancer,” Eur. Radiol., vol. 30, no. 3, pp. 1297-1305, 2020, https:\\doi.org\10.1007/s00330-019-06467-3.
• [25] S. Sornapud et al., “DeepCIN: Attention‑Based Cervical histology Image Classification with Sequential Feature Modeling for Pathologist‑Level Accuracy,” J. Pathol. Inform., vol. 11, no. 40, pp. 1-9, 2020, https:\\doi.org\10.4103/jpi.jpi.
• [26] D. Brenes et al., “Multi-task network for automated analysis of high-resolution endomicroscopy images to detect cervical precancer and cancer,” Comput. Med. Imaging Graph., vol. 97, no. February, 2022, https:\\doi.org\10.1016/j.compmedimag.2022.102052.
• [27] N. Alemi Koohbanani, M. Jahanifar, N. Zamani Tajadin, and N. Rajpoot, “NuClick: A deep learning framework for interactive segmentation of microscopic images,” Med. Image Anal., vol. 65, 2020, https:\\doi.org\10.1016/j.media.2020.101771.
• [28] M. Xia, G. Zhang, C. Mu, B. Guan, and M. Wang, “Cervical Cancer Cell Detection Based on Deep Convolutional Neural Network,” Chinese Control Conf. CCC, vol. 2020-July, pp. 6527-6532, 2020, https:\\doi.org\10.23919/CCC50068.2020.9188454.
• [29] S. K and G. C, “A hybrid model for efficient cervical cell classification,” Biomed. Signal Process. Control, vol. 72, no. PA, p. 103288, 2022, https:\\doi.org\10.1016/j.bspc.2021.103288.
• [30] Kurnianingsih et al., “Segmentation and classification of cervical cells using deep learning,” IEEE Access, vol. 7, pp. 116925-116941, 2019, https:\\doi.org\10.1109/ACCESS.2019.2936017.
• [31] J. Kang and N. Li, “CerviSegNet-DistillPlus: An Efficient Knowledge Distillation Model for Enhancing Early Detection of Cervical Cancer Pathology,” IEEE Access, vol. 12, no. June, pp. 85134-85149, 2024, https:\\doi.org\10.1109/ACCESS.2024.3415395.
• [32] H. Hu, J. Zhang, T. Yang, Q. Hu, Y. Yu, and Q. Huang, “CNAC-Seg: Effective segmentation for cervical nuclei in adherent cells and clusters via exploring gaps of receptive fields,” Biomed. Signal Process. Control, vol. 90, no. December 2023, p. 105833, 2024, https:\\doi.org\10.1016/j.bspc.2023.105833.
• [33] H. Hu, J. Zhang, T. Yang, Q. Hu, Y. Yu, and Q. Huang, “PATrans: Pixel-Adaptive Transformer for edge segmentation of cervical nuclei on small-scale datasets,” Comput. Biol. Med., vol. 168, no. December 2023, p. 107823, 2024, https:\\doi.org\10.1016/j.compbiomed.2023.107823.
• [34] B. Z. Wubineh, A. Rusiecki, and K. Halawa, “Segmentation of Cytology Images to Detect Cervical Cancer Using Deep Learning Techniques,” in International Conference on Computational Science, Switzerland: Springer Nature, 2024, pp. 270-278.
• [35] M. M. Rahaman et al., “DeepCervix: A deep learning-based framework for the classification of cervical cells using hybrid deep feature fusion techniques,” Comput. Biol. Med., vol. 136, no. May, p. 104649, 2021, https:\\doi.org\10.1016/j.compbiomed.2021.104649.
• [36] B. Chitra and S. S. Kumar, “An optimized deep learning model using Mutation-based Atom Search Optimization algorithm for cervical cancer detection,” Soft Comput., vol. 25, no. 24, pp. 15363-15376, 2021, https:\\doi.org\10.1007/s00500-021-06138-w.
• [37] R. Pramanik, M. Biswas, S. Sen, L. A. de Souza Júnior, J. P. Papa, and R. Sarkar, “A fuzzy distance-based ensemble of deep models for cervical cancer detection,” Comput. Methods Programs Biomed., vol. 219, p. 106776, 2022, https:\\doi.org\10.1016/j.cmpb.2022.106776.
• [38] D. Xue et al., “An Application of Transfer Learning and Ensemble Learning Techniques for Cervical Histopathology Image Classification,” IEEE Access, vol. 8, pp. 104603-104618, 2020, https:\\doi.org\10.1109/ACCESS.2020.2999816.
• [39] M. Benhari and R. Hossseini, “An Improved Fuzzy Deep Learning (IFDL) model for managing uncertainty in classification of pap-smear cell images,” Intell. Syst. with Appl., vol. 16, no. July, p. 200133, 2022, https:\\doi.org\10.1016/j.iswa.2022.200133.
• [40] I. Pacal and S. Kılıcarslan, “Deep learning-based approaches for robust classification of cervical cancer,” Neural Comput. Appl., vol. 35, no. 25, pp. 18813-18828, 2023, https:\\doi.org\10.1007/s00521-023-08757-w.
• [41] 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, no. P2, p. 104156, 2023, https:\\doi.org\10.1016/j.bspc.2022.104156.
• [42] N. K. Chauhan, K. Singh, A. Kumar, and S. B. Kolambakar, “HDFCN: A Robust Hybrid Deep Network Based on Feature Concatenation for Cervical Cancer Diagnosis on WSI Pap Smear Slides,” Biomed Res. Int., vol. 2023, 2023, https:\\doi.org\10.1155/2023/4214817.
• [43] N. S. Joynab, M. N. Islam, R. R. Aliya, A. S. M. R. Hasan, N. I. Khan, and I. H. Sarker, “A federated learning aided system for classifying cervical cancer using PAP-SMEAR images,” Informatics Med. Unlocked, vol. 47, no. November 2023, p. 101496, 2024, https:\\doi.org\10.1016/j.imu.2024.101496.
• [44] P. Jiang et al., “Interpretable detector for cervical cytology using self-attention and cell origin group guidance,” Eng. Appl. Artif. Intell., vol. 134, no. January, p. 108661, 2024, https:\\doi.org\10.1016/j.engappai.2024.108661.
• [45] A. Khowaja, B. Zou, and X. Kui, “Enhancing cervical cancer diagnosis: Integrated attention-transformer system with weakly supervised learning,” Image Vis. Comput., vol. 149, no. December 2023, p. 105193, 2024, https:\\doi.org\10.1016/j.imavis.2024.105193.
• [46] I. Pacal, “MaxCerVixT: A novel lightweight vision transformer-based Approach for precise cervical cancer detection,” Knowledge-Based Syst., vol. 289, no. February, p. 111482, 2024, https:\\doi.org\10.1016/j.knosys.2024.111482.
• [47] L. Xu, F. Cai, Y. Fu, and Q. Liu, “Cervical cell classification with deep-learning algorithms,” Med. Biol. Eng. Comput., vol. 61, no. 3, pp. 821-833, 2023, https:\\doi.org\10.1007/s11517-022-02745-3.
• [48] Z. Alyafeai and L. Ghouti, “A fully-automated deep learning pipeline for cervical cancer classification,” Expert Syst. Appl., vol. 141, p. 112951, 2020, https:\\doi.org\10.1016/j.eswa.2019.112951.
• [49] C. Asawara, Y. Homma, and S. Sy, “Deep Learning Approaches for Determining Optimal Cervical Cancer Treatment,” pp. 1-8, 2017.
• [50] V. Chandran et al., “Diagnosis of Cervical Cancer based on Ensemble Deep Learning Network using Colposcopy Images,” Biomed Res. Int., vol. 2021, 2021, https:\\doi.org\10.1155/2021/5584004.
• [51] L. Wong, A. Ccopa, E. Diaz, S. Valcarcel, D. Mauricio, and V. Villoslada, “Deep Learning and Transfer Learning Methods to Effectively Diagnose Cervical Cancer from Liquid-Based Cytology Pap Smear Images,” Int. J. online Biomed. Eng., vol. 19, no. 4, pp. 77-93, 2023, https:\\doi.org\10.3991/ijoe.v19i04.37437.
• [52] L. Cao et al., “A novel attention-guided convolutional network for the detection of abnormal cervical cells in cervical cancer screening,” Med. Image Anal., vol. 73, p. 102197, 2021, https:\\doi.org\10.1016/j.media.2021.102197.
• [53] Y. Kurita et al., “Accurate deep learning model using semi-supervised learning and Noisy Student for cervical cancer screening in low magnification images,” PLoS One, vol. 18, no. 5 May, pp. 1-17, 2023, https:\\doi.org\10.1371/journal.pone.0285996.
• [54] M. Sato et al., “Application of deep learning to the classification of images from colposcopy,” Oncol. Lett., vol. 15, no. 3, pp. 3518-3523, 2018, https:\\doi.org\10.3892/ol.2018.7762.
• [55] T. Zhang et al., “Cervical precancerous lesions classification using pre-trained densely connected convolutional networks with colposcopy images,” Biomed. Signal Process. Control, vol. 55, p. 101566, 2020, https:\\doi.org\10.1016/j.bspc.2019.101566.
• [56] M. Kalnhor, 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, https:\\doi.org\10.1016/j.heliyon.2023.e22324.
• [57] O. E. Aina, S. A. Adeshina, A. P. Adedigba, and A. M. Aibinu, “Classification of Cervical Intraepithelial Neoplasia (CIN) using fine-tuned Convolutional Neural Networks,” Intell. Med., vol. 5, no. September 2020, p. 100031, 2021, https:\\doi.org\10.1016/j.ibmed.2021.100031.
• [58] A. Pal et al., “Deep multiple-instance learning for abnormal cell detection in cervical histopathology images,” Comput. Biol. Med., vol. 138, no. May, p. 104890, 2021, https:\\doi.org\10.1016/j.compbiomed.2021.104890.
• [59] W. Tian et al., “Development and validation of a deep learning algorithm for pattern-based classification system of cervical cancer from pathological sections,” Heliyon, vol. 9, no. 8, p. e19229, 2023, https:\\doi.org\10.1016/j.heliyon.2023.e19229.
• [60] Y. Guo, Y. Wang, H. Yang, J. Zhang, and Q. Sun, “Dual-attention EfficientNet based on multi-view feature fusion for cervical squamous intraepithelial lesions diagnosis,” Biocybern. Biomed. Eng., vol. 42, no. 2, pp. 529-542, 2022, https:\\doi.org\10.1016/j.bbe.2022.02.009.
• [61] J. Li, P. Hu, H. Gao, N. Shen, and K. Hua, “Classification of cervical lesions based on multimodal features fusion,” Comput. Biol. Med., vol. 177, no. May, p. 108589, 2024, https:\\doi.org\10.1016/j.compbiomed.2024.108589.
• [62] M. Fei et al., “Distillation of multi-class cervical lesion cell detection via synthesis-aided pre-training and patch-level feature alignment,” Neural Networks, vol. 178, no. December 2023, p. 106405, 2024, https:\\doi.org\10.1016/j.neunet.2024.106405.
• [63] S. Chai et al., “DPD-Net: Dual-path Proposal Discriminative Network for abnormal cell detection in cervical cytology images,” Biomed. Signal Process. Control, vol. 89, no. December 2023, p. 105887, 2024, https:\\doi.org\10.1016/j.bspc.2023.105887.
• [64] F. Paucar, C. Bojorque, I. Reyes-Chacón, P. Vizcaino-Imacaña, and M. Morocho-Cayamcela, “Towards Accurate Cervical Cancer Detection: Leveraging Two-Stage CNNs for Pap Smear Analysis,” no. Icsoft, pp. 219-227, 2024, https:\\doi.org\10.5220/0012735800003753.
• [65] 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,” Comput. Methods Programs Biomed., vol. 240, 2023, https:\\doi.org\10.1016/j.cmpb.2023.107718.
• [66] J. Zak, M. K. Grzeszczyk, A. Pater, L. Roszkowiak, K. Siemion, and A. Korzynska, “Cell image augmentation for classification task using GANs on Pap smear dataset,” Biocybern. Biomed. Eng., vol. 42, no. 3, pp. 995-1011, 2022, https:\\doi.org\10.1016/j.bbe.2022.07.003.
• [67] S. Yu et al., “Generative adversarial network based data augmentation to improve cervical cell classification model,” Math. Biosci. Eng., vol. 18, no. 2, pp. 1740-1752, 2021, https:\\doi.org\10.3934/MBE.2021090.
• [68] S. Nayar, D. Priya, and J. Vinitha Panicker, “Deep Learning Approach for Automated Data Augmentation and Multi-class Classification of Pap Smear Images,” Procedia Comput. Sci., vol. 235, pp. 2205-2214, 2024, https:\\doi.org\10.1016/j.procs.2024.04.209.
• [69] M. Ali, M. Ali, and M. Javed, “DCGAN for Synthetic Data Augmentation of Cervical Cancer for Improved Cervical Cancer Classification,” 2024 IEEE Int. Students’ Conf. Electr. Electron. Comput. Sci. SCEECS 2024, no. February, pp. 1-7, 2024, https:\\doi.org\10.1109/SCEECS61402.2024.10482312.
• [70] S. Chen, D. Gao, L. Wang, and Y. Zhang, “Cervical Cancer Single Cell Image Data Augmentation Using Residual Condition Generative Adversarial Networks,” 2020 3rd Int. Conf. Artif. Intell. Big Data, ICAIBD 2020, no. x, pp. 237-241, 2020, https:\\doi.org\10.1109/ICAIBD49809.2020.9137494.
• [71] C. Zhao, R. Shuai, L. Ma, W. Liu, and M. Wu, Improving cervical cancer classification with imbalanced datasets combining taming transformers with T2T-ViT, vol. 81, no. 17. 2022. https:\\doi.org\10.1007/s11042-022-12670-0.
• [72] Y. Xue et al., Synthetic Augmentation and Feature-Based Filtering for Improved Cervical Histopathology Image Classification, vol. 11764 LNCS. 2019. https:\\doi.org\10.1007/978-3-030-32239-7_44.
• [73] Y. Jin et al., “Cervical cytology screening using the fused deep learning architecture with attention mechanisms,” Appl. Soft Comput., vol. 166, no. September, p. 112202, 2024, https:\\doi.org\10.1016/j.asoc.2024.112202.
• [74] B. Z. Wubineh, A. Rusiecki, and K. Halawa, “Classification of cervical cells from the Pap smear image using the RES_DCGAN data augmentation and ResNet50V2 with self-attention architecture,” Neural Comput. Appl., vol. 0123456789, 2024, https:\\doi.org\10.1007/s00521-024-10404-x.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).