Cervical cancer is the fourth most common cause of women cancer deaths worldwide. The primary etiology of cervical cancer is the persistent infection of specific high-risk strains of the human papillomavirus. Liquid-based cytology is the established method for early detection of cervical cancer. The evaluation of cellular abnormalities at a microscopic level allows for the identification of malignant or precancerous features in liquid-based cytology pap smears. This technique is characterized by its time-consuming nature and susceptibility to both inter- and intra-observer variability. Hence, the utilization of Artificial Intelligence in computer-assisted diagnosis can reduce the duration needed for diagnosing this ailment, thereby eliminating delayed diagnosis and facilitating the implementation of an efficient treatment.
Objective
This research presents a new deep learning-based cervical cancer identification decision support system in liquid-based cytology smear images.
Methods
The proposed diagnosis support system incorporates a novel hybrid feature reduction and optimization module, which integrates a sparse Autoencoder with the Binary Harris Hawk metaheuristic optimization algorithm to select the most informative features from a supplemented feature set of the input images. The supplemented feature set is retrieved by three pretrained Convolutional Neural Networks. The module utilizes an improved feature set to conduct a Bayesian-optimized K Nearest Neighbors machine learning classification of cervical cancer in input Pap smears.
Results
The introduced approach achieves a classification accuracy of 99.9% and demonstrates an improved ability to detect the stages of cervical cancer, with a sensitivity of 99.8%. In addition, the system has the ability to identify the lack of cervical cancer stages with a specificity rate of 99.9%.
Conclusion
The proposed system outpaces recent deep learning-based cervical cancer identification systems.
AlquranHMustafaWAQasmiehIA, et al.Cervical Cancer Classification Using Combined Machine Learning and Deep Learning Approach. Comput, Mater Continua2022 Apr 21; 72: 5117–34. doi:https://doi.org/10.32604/cmc.2022.025692
2.
WangBZhangYWuC,et al.Multimodal MRI Analysis of Cervical Cancer on the Basis of Artificial Intelligence Algorithm. Contrast Media Mol Imag2021; 2021. doi:https://doi.org/10.1155/2021/1673490
3.
KangZLiuJMaC, et al.Early screening of cervical cancer based on tissue Raman spectroscopy combined with deep learning algorithms. Photodiagnosis Photodyn Ther2023 Jun 1; 42. doi:https://doi.org/10.1016/j.pdpdt.2023.103557
4.
ZhangZZhangCXiaoL,et al.Diagnosis of Early Cervical Cancer with a Multimodal Magnetic Resonance Image under the Artificial Intelligence Algorithm. Contrast Media Mol Imaging2022; 2022.
5.
ParkYRKimYJJuW, et al.Comparison of machine and deep learning for the classification of cervical cancer based on cervicography images. Sci Rep2021 Dec 1; 11.
6.
ViñalsRJonnalageddaMPetignatP, et al.Artificial Intelligence-Based Cervical Cancer Screening on Images Taken during Visual Inspection with Acetic Acid: A Systematic Review. Diagnostics (Basel)2023 Mar 1; 13.
7.
AtteiaGE. Latent Space Representational Learning of Deep Features for Acute Lymphoblastic Leukemia Diagnosis. Comput Syst Sci Eng.2022 Aug 16; 45: 361–76. doi:https://doi.org/10.32604/csse.2023.029597
8.
RezayiSMohammadzadehNBouraghiH, et al.Timely Diagnosis of Acute Lymphoblastic Leukemia Using Artificial Intelligence-Oriented Deep Learning Methods. Comput Intell Neurosci2021; 2021.
9.
AtteiaGAlnashwanRHassanM. Hybrid Feature-Learning-Based PSO-PCA Feature Engineering Approach for Blood Cancer Classification. Diagnostics2023 Aug 14; 13: 2672. doi:https://doi.org/10.3390/diagnostics13162672
PacalI. MaxCerVixT: A novel lightweight vision transformer-based Approach for precise cervical cancer detection. Knowl Based Syst2024 Apr 8; 289: 111482. doi:https://doi.org/10.1016/j.knosys.2024.111482
12.
OzdemirBPacalI. An innovative deep learning framework for skin cancer detection employing ConvNeXtV2 and focal self-attention mechanisms. Res Eng2025 Mar 1; 25: 103692. doi:https://doi.org/10.1016/j.rineng.2024.103692
13.
BayramBKunduraciogluIInceS,et al.A systematic review of deep learning in MRI-based cerebral vascular occlusion-based brain diseases. Neuroscience2025 Mar 5; 568: 76–94. doi:https://doi.org/10.1016/j.neuroscience.2025.01.020
14.
AtteiaGSameeNAHassanHZ. DFTSA-Net: Deep Feature Transfer-Based Stacked Autoencoder Network for DME Diagnosis. Entropy [Internet]2021 Oct 1; 23(10, [cited 2024 Jan 13]. Available from: /pmc/articles/PMC8534911/.
15.
MehmoodMRizwanMGregus mlMAbbasS. Machine Learning Assisted Cervical Cancer Detection. Front Public Health2021 Dec 23; 9. doi:https://doi.org/10.3389/fpubh.2021.788376
16.
AlsmariyRHealyGAbdelhafezH. Predicting Cervical Cancer using Machine Learning Methods. Int J Adv Comput Sci Appl2020; 11(7): 173–84. doi:https://doi.org/10.14569/IJACSA.2020.0110723
AkhilaKRMuthukumaranNAhilanA. Classification of Cervical Cancer Using an Autoencoder and Cascaded Multilayer Perceptron. IETE J Res2023 Feb 16.
19.
ChandranVSumithraMGKarthickA, et al.Diagnosis of Cervical Cancer based on Ensemble Deep Learning Network using Colposcopy Images. Biomed Res Int2021; 2021.
20.
KhampariaAGuptaDRodriguesJJPC,et al.DCAVN: Cervical cancer prediction and classification using deep convolutional and variational autoencoder network. Multimed Tools Appl2020 Aug 1; 80: 30399–415. doi:https://doi.org/10.1007/s11042-020-09607-w
21.
AlsalatieMAlquranHMustafaWA, et al.A New Weighted Deep Learning Feature Using Particle Swarm and Ant Lion Optimization for Cervical Cancer Diagnosis on Pap Smear Images. Diagnostics (Basel)2023 Sep 1; 13.
22.
HussainEMahantaLBBorahH,et al.Liquid based-cytology Pap smear dataset for automated multi-class diagnosis of pre-cancerous and cervical cancer lesions. Data Brief2020 Jun 1; 30: 105589. doi:https://doi.org/10.1016/j.dib.2020.105589
SandlerMHowardAZhuM, et al.MobileNetV2: Inverted Residuals and Linear Bottlenecks. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2018 Jun 1;4510–20.
25.
ZhangXZhouXLinM,et al.ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2017 Jul 4: 6848–56.
26.
Darknet: Open Source Neural Networks in C [Internet]. [cited 2023 Jul 6]. Available from: https://pjreddie.com/darknet/
27.
GoodfellowIBengioYCourvilleA. Deep Learning - Adaptive Computation and Machine learning. Vol. 1, Massachusetts, USA: MIT press. The MIT Press, 2017. 474–485 p.
HeidariAAMirjaliliSFarisH, et al.Harris hawks optimization: Algorithm and applications. Future Gener Comput Syst.2019 Aug 1; 97: 849–72. doi:https://doi.org/10.1016/j.future.2019.02.028
31.
TooJAbdullahARSaadNM. A New Quadratic Binary Harris Hawk Optimization for Feature Selection. Electronics (Basel).2019 Oct 7; 8: 1130. doi:https://doi.org/10.3390/electronics8101130
32.
MirjaliliSLewisA. S-shaped versus V-shaped transfer functions for binary Particle Swarm Optimization. Swarm Evol Comput2013 Apr 1; 9: 1–14. doi:https://doi.org/10.1016/j.swevo.2012.09.002
33.
SaremiSMirjaliliSLewisA. How important is a transfer function in discrete heuristic algorithms. Neural Comput Appl2015 Apr 1; 26: 625–40. doi:https://doi.org/10.1007/s00521-014-1743-5
JasperSHugoLAdamsR. Practical Bayesian optimization of machine learning algorithms. In: 25th International Conference on Neural Information Processing Systems - Volume 2. 2012. p. 2951–2959.
36.
MafarjaMAljarahIHeidariAA, et al.Binary dragonfly optimization for feature selection using time-varying transfer functions. Knowl Based Syst2018 Dec 1; 161: 185–204. doi:https://doi.org/10.1016/j.knosys.2018.08.003
37.
FarisHMafarjaMMHeidariAA, et al.An efficient binary Salp Swarm Algorithm with crossover scheme for feature selection problems. Knowl Based Syst2018 Aug 15; 154: 43–67. doi:https://doi.org/10.1016/j.knosys.2018.05.009
38.
Karasu BenyesYWelchECSinghalA, et al.A Comparative Analysis of Deep Learning Models for Automated Cross-Preparation Diagnosis of Multi-Cell Liquid Pap Smear Images. Diagnostics (Basel)2022 Aug 1; 12.
39.
AlsalatieMAlquranHMustafaWA, et al.Analysis of Cytology Pap Smear Images Based on Ensemble Deep Learning Approach. 2022.
40.
MathivananSKFrancisDSrinivasanS, et al.Enhancing cervical cancer detection and robust classification through a fusion of deep learning models. Scientific Reports 2024 14:1 [Internet]. 2024 May 11 [cited 2025 Feb 2];14(1):1–14. Available from: https://www.nature.com/articles/s41598-024-61063-w.
41.
SompawongNMopanJPooprasertP, et al.Automated Pap Smear Cervical Cancer Screening Using Deep Learning. Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS. 2019 Jul 1;7044–8.
