Optimizing Image Preprocessing for AI-Driven Cervical Cancer Diagnosis
DOI:
https://doi.org/10.26877/asset.v7i1.1128Keywords:
Artificial Intelligence, Cervical Cancer Diagnosis, Deep Learning, Medical Image Processing, Pretrained ModelsAbstract
Cervical cancer ranks among the top causes of cancer-related deaths in women globally. Early detection is vital for improving patient survival rates. The multiclass classification of cervical cell images presents challenges primarily due to the notable variations in cell sizes across different classes. Conventional AI methods for diagnosing cervical cancer often rely on image-resizing techniques that overlook crucial features like relative cell dimensions, which impairs the models' ability to distinguish between classes effectively. This paper presents a novel AI-driven approach that employs constant padding to maintain the natural size differences among cells. Our method utilizes deep learning for both feature extraction and multiclass classification. We assessed the method using the publicly accessible SIPaKMeD dataset. Experimental findings indicate that our approach surpasses traditional image-resizing methods, especially in classes that are more challenging to predict. This strategy highlights AI's potential to improve cervical cancer diagnosis, offering a more precise and dependable tool for early detection. A reliable and precise AI model for diagnosing cervical cancer is crucial for promoting widespread screening and ensuring timely and effective treatment, which can ultimately lower mortality rates. By aiding early and accurate diagnosis, this approach aligns with global health efforts to alleviate the burden of cancer and other diseases, especially in areas with limited access to advanced healthcare services facilities.
References
[1] H. Sung et al., “Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries,” CA. Cancer J. Clin., vol. 71, no. 3, pp. 209–249, 2021, doi: 10.3322/caac.21660.
[2] J. M. Lemp et al., “Lifetime Prevalence of Cervical Cancer Screening in 55 Low-and Middle-Income Countries,” JAMA - J. Am. Med. Assoc., vol. 324, no. 15, pp. 1532–1542, 2020, doi: 10.1001/jama.2020.16244.
[3] D. Saslow et al., “American Cancer Society, American Society for Colposcopy and Cervical Pathology, and American Society for Clinical Pathology screening guidelines for the prevention and early detection of cervical cancer,” CA. Cancer J. Clin., vol. 62, no. 3, pp. 147–172, May 2012, doi: 10.3322/CAAC.21139.
[4] M. K. Maysaa R. Naeemah, “Advances in Deep Learning for Skin Cancer Diagnosis”, doi: https://doi.org/10.26877/asset.v6i4.1002.
[5] Abdillah, S. Syaharuddin, V. Mandailina, and S. Mehmood, “The Role of Mathematics in Machine Learning for Disease Prediction: An In-Depth Review in the Healthcare Domain,” Adv. Sustain. Sci. Eng. Technol., vol. 6, no. 4, p. 02404010, 2024, doi: 10.26877/asset.v6i4.845.
[6] J. Wang et al., “Artificial intelligence enables precision diagnosis of cervical cytology grades and cervical cancer,” Nat. Commun., vol. 15, no. 1, pp. 1–14, 2024, doi: 10.1038/s41467-024-48705-3.
[7] X. Zhu et al., “Hybrid AI-assistive diagnostic model permits rapid TBS classification of cervical liquid-based thin-layer cell smears,” Nat. Commun., vol. 12, no. 1, pp. 1–12, 2021, doi: 10.1038/s41467-021-23913-3.
[8] Y. Xiang, W. Sun, C. Pan, M. Yan, Z. Yin, and Y. Liang, “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: 10.1016/j.bbe.2020.01.016.
[9] M. Cao et al., “Patch-to-Sample Reasoning for Cervical Cancer Screening of Whole Slide Image,” IEEE Trans. Artif. Intell., vol. PP, pp. 1–11, 2023, doi: 10.1109/TAI.2023.3323637.
[10] X. Tan et al., “Automatic model for cervical cancer screening based on convolutional neural network: a retrospective, multicohort, multicenter study,” Cancer Cell Int., vol. 21, no. 1, pp. 1–10, 2021, doi: 10.1186/s12935-020-01742-6.
[11] 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, doi: 10.1016/j.compbiomed.2021.104649.
[12] L. Xu, F. Cai, Y. Fu, and Q. Liu, “Cervical cell classification with deep-learning algorithms,” Medical and Biological Engineering and Computing, vol. 61, no. 3. pp. 821–833, 2023. doi: 10.1007/s11517-022-02745-3.
[13] Y. Guo, D. Chen, C. Bao, and Y. Luo, “Causal Attention-Based Lightweight and Efficient Cervical Cancer Cell Detection Model,” 2023 IEEE Int. Conf. Bioinforma. Biomed., pp. 1104–1111, 2023, doi: 10.1109/BIBM58861.2023.10385353.
[14] 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.
[15] 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,” Biomed. Eng. Online, vol. 18, no. 1, pp. 1–22, 2019, doi: 10.1186/s12938-019-0634-5.
[16] 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, doi: 10.1007/s00521-023-08757-w.
[17] M. Model and S. Liang, “Towards Robust and Accurate Detection of Abnormalities in Musculoskeletal Radiographs with”, doi: 10.3390/s20113153.
[18] H. Tang, A. Ortis, and S. Battiato, The impact of padding on image classification by using pre-trained convolutional neural networks, vol. 11752 LNCS. Springer International Publishing, 2019. doi: 10.1007/978-3-030-30645-8_31.
[19] T. Haryanto, I. S. Sitanggang, M. A. Agmalaro, and R. Rulaningtyas, “The Utilization of Padding Scheme on Convolutional Neural Network for Cervical Cell Images Classification,” CENIM 2020 - Proceeding Int. Conf. Comput. Eng. Network, Intell. Multimed. 2020, pp. 34–38, 2020, doi: 10.1109/CENIM51130.2020.9297895.
[20] T. Albuquerque, R. Cruz, and J. S. Cardoso, “Ordinal losses for classification of cervical cancer risk,” PeerJ Comput. Sci., vol. 7, pp. 1–21, 2021, doi: 10.7717/peerj-cs.457.
[21] SIPaKMeD, “SIPaKMeD Database.” [Online]. Available: https://www.cs.uoi.gr/~marina/sipakmed.html
[22] K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” 3rd Int. Conf. Learn. Represent. ICLR 2015 - Conf. Track Proc., pp. 1–14, 2015.
[23] C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, “Rethinking the Inception Architecture for Computer Vision,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 2016-Decem, pp. 2818–2826, 2016, doi: 10.1109/CVPR.2016.308.
[24] G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” Proc. - 30th IEEE Conf. Comput. Vis. Pattern Recognition, CVPR 2017, vol. 2017-Janua, pp. 2261–2269, 2017, doi: 10.1109/CVPR.2017.243.
[25] F. Chollet, “Xception: Deep learning with depthwise separable convolutions,” Proc. - 30th IEEE Conf. Comput. Vis. Pattern Recognition, CVPR 2017, vol. 2017-Janua, pp. 1800–1807, 2017, doi: 10.1109/CVPR.2017.195.
[26] M. E. Plissiti, G. Sfikas, C. Nikou, and A. Charchanti, “Sipakmed : A New Dataset for Feature and Image Based Classification of Normal and Pathological Cervical Cells in Pap Smear Images SIPAKMED : A NEW DATASET FOR FEATURE AND IMAGE BASED CLASSIFICATION OF,” no. October, 2018, doi: 10.1109/ICIP.2018.8451588.
[27] R. F. Ribeiro, H. R. Torres, B. Oliveira, and ..., “Deep Learning Methods for Lesion Detection on Full Screening Mammography: A Comparative Analysis,” 3rd Symposium of …. bibliotecadigital.ipb.pt, 2023.
[28] W. A. Mustafa, S. Ismail, F. S. Mokhtar, H. Alquran, and Y. Al-Issa, “Cervical Cancer Detection Techniques: A Chronological Review,” Diagnostics, vol. 13, no. 10, 2023, doi: 10.3390/diagnostics13101763.
