Investigating deep learning approaches for cervical cancer diagnosis: a focus on modern image-based models

Background: Cervical cancer is a leading health concern for women globally, necessitating accurate and timely diagnostic methods. While the Papanicolaou smear (Pap smear) test remains the gold standard for cervical cancer screening, it is time-consuming and prone to human error. This highlights the need for automated diagnostic tools to improve efficiency and accuracy. Methods: This study evaluated the performance of deep learning models for automating cervical cancer diagnosis using Pap smear images. A new dataset was constructed by merging the Mendeley Liquid-Based Cytology (LBC) dataset (963 images) and the Malhari dataset (318 images), resulting in 1,281 images. Twenty-seven cutting-edge deep learning models, including Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs), were used for classification. Data augmentation and transfer learning techniques were applied to enhance model performance. Results: The majority of ViT-based models achieved a high classification accuracy of 99.48%. Among the 13 CNN-based models evaluated, EfficientNetV2-Small was the only model to achieve the same accuracy level. The results demonstrate the superiority of ViT-based models in achieving high diagnostic accuracy. Conclusions: Deep learning methods, particularly ViT-based models, show substantial potential in automating cervical cancer diagnosis. These models can enhance diagnostic accuracy, reduce human error, and provide timely results, thereby supporting more efficient and reliable cervical cancer screening practices.

Deep learning; CNNs and ViTs; Cervical cancer detection; Artificial intelligence in medicine

[1] Siegel RL, Giaquinto AN, Jemal A. Cancer statistics, 2024. CA: A Cancer Journal for Clinicians. 2024; 74: 12–49.

[2] Siegel RL, Miller KD, Wagle NS, Jemal A. Cancer statistics, 2023. CA: A Cancer Journal for Clinicians. 2023; 73: 17–48.

[3] Bedell SL, Goldstein LS, Goldstein AR, Goldstein AT. Cervical cancer screening: past, present, and future. Sexual Medicine Reviews. 2020; 8: 28–37.

[4] Scarinci IC, Garcia FA, Kobetz E, Partridge EE, Brandt HM, Bell MC, et al. Cervical cancer prevention: new tools and old barriers. Cancer. 2010; 116: 2531–2542.

[5] Jiang P, Li X, Shen H, Chen Y, Wang L, Chen H, et al. A systematic review of deep learning-based cervical cytology screening: from cell identification to whole slide image analysis. Artificial Intelligence Review. 2023; 56: 2687–2758.

[6] Rerucha CM., Caro RJ, Wheeler VL. Cervical cancer screening. American Family Physician. 2018; 97: 441–448.

[7] Mishra GA, Pimple SA, Shastri SS. An overview of prevention and early detection of cervical cancers. Indian Journal of Medical and Paediatric Oncology. 2011; 32: 125–132.

[8] Kang Z, Liu J, Ma C, Chen C, Lv X, Chen C. Early screening of cervical cancer based on tissue Raman spectroscopy combined with deep learning algorithms. Photodiagnosis and Photodynamic Therapy. 2023; 42: 103557.

[9] Attallah O. Cervical cancer diagnosis based on multi-domain features using deep learning enhanced by handcrafted descriptors. Applied Sciences. 2023; 13: 1916.

[10] Sahoo P, Saha S, Mondal S, Seera M, Sharma SK, Kumar M. Enhancing computer-aided cervical cancer detection using a novel fuzzy rank-based fusion. IEEE Access. 2023; 11: 145281–145294.

[11] Liu W, Li C, Xu N, Jiang T, Rahaman MM, Sun H, et al. CVM-Cervix: a hybrid cervical Pap-smear image classification framework using CNN, visual transformer and multilayer perceptron. Pattern Recognition. 2022; 130: 108829.

[12] Pacal I. MaxCerVixT: a novel lightweight vision transformer-based approach for precise cervical cancer detection. Knowledge-Based Systems. 2024; 289: 111482.

[13] Chen W, Gao L, Li X, Shen W. Lightweight convolutional neural network with knowledge distillation for cervical cells classification. Biomedical Signal Processing and Control. 2022; 71: 103177.

[14] Pacal İ. Deep learning approaches for classification of breast cancer in ultrasound (US) images. Journal of the Institute of Science and Technology. 2022; 12: 1917–1927.

[15] Pacal I. A novel Swin transformer approach utilizing residual multi-layer perceptron for diagnosing brain tumors in MRI images. International Journal of Machine Learning and Cybernetics. 2024; 15: 3579–3597.

[16] Sahoo P, Sharma SK, Saha S, Mondal S. A federated multi-stage light-weight vision transformer for respiratory disease detection. In Luo B, Cheng L, Wu ZG, Li H, Li C (eds.) Communications in Computer and Information Science (pp. 300–311). Springer: Singapore. 2023.

[17] Sahoo P, Saha S, Mondal S, Sharma N. COVID-19 detection from lung ultrasound images using a fuzzy ensemble-based transfer learning technique. International Conference on Pattern Recognition. 2022; 5170–5176.

[18] Sahoo P, Saha S, Sharma SK, Mondal S, Gowda S. A multi-stage framework for COVID-19 detection and severity assessment from chest radiography images using advanced fuzzy ensemble technique. Expert Systems with Applications. 2024; 238: 121724.

[19] Sahoo P, Saha S, Mondal S, Chowdhury S, Gowda S. Vision transformer-based federated learning for COVID-19 detection using chest X-ray. In Tanveer M, Agarwal S, Ozawa S, Ekbal A, Jatowt A (eds.) Communications in Computer and Information Science (pp. 77–88). Springer: Singapore. 2023.

[20] Ding W, Wang H, Huang J, Ju H, Geng Y, Lin CT, et al. FTransCNN: fusing transformer and a CNN based on fuzzy logic for uncertain medical image segmentation. Information Fusion. 2023; 99: 101880.

[21] Sahoo P, Sharma SK, Saha S, Jain D, Mondal S. A multistage framework for respiratory disease detection and assessing severity in chest X-ray images. Scientific Reports. 2024; 14: 12380.

[22] Attallah O. Skin-CAD: explainable deep learning classification of skin cancer from dermoscopic images by feature selection of dual high-level CNNs features and transfer learning. Computers in Biology and Medicine. 2024; 178: 108798.

[23] Attallah O. Acute lymphocytic leukemia detection and subtype classification via extended wavelet pooling based-CNNs and statistical-texture features. Image and Vision Computing. 2024; 147: 105064.

[24] Burukanli M, Yumuşak N. COVID-19 virus mutation prediction with LSTM and attention mechanisms. The Computer Journal. 2024; 67; 2934–2944.

[25] Pacal I, Celik O, Bayram B, Cunha A. Enhancing EfficientNetv2 with global and efficient channel attention mechanisms for accurate MRI-Based brain tumor classification. 2024. Available at: https://doi.org/10.1007/s10586-024-04532-1 (Accessed: 12 July 2024).

[26] Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, et al. An image is worth 16´16 words: transformers for image recognition at scale. To be published in ArXiv. 2020. [Preprint].

[27] Rodrigo F, Alexandre P, Marta S, Anselmo DP, Ishak P, António C. Enhancing image annotation with object tracking and image retrieval: a systematic review. 2024. Available at: https://doi.org/10.1109/ACCESS.2024.3406018 (Accessed: 12 July 2024).

[28] Youneszade N, Marjani M, Pei CP. Deep learning in cervical cancer diagnosis: architecture, opportunities, and open research challenges. IEEE Access. 2023; 11: 6133–6149.

[29] Sambyal D, Sarwar A. Recent developments in cervical cancer diagnosis using deep learning on whole slide images: an overview of models, techniques, challenges and future directions. Micron. 2023; 173: 103520.

[30] Ahmadzadeh Sarhangi H, Beigifard D, Farmani E, Bolhasani H. Deep learning techniques for cervical cancer diagnosis based on pathology and colposcopy images. Informatics in Medicine Unlocked. 2024; 47: 101503.

[31] Gao Y, Gonzalez Y, Nwachukwu C, Albuquerque K, Jia X. Predicting treatment plan approval probability for high-dose-rate brachytherapy of cervical cancer using adversarial deep learning. Physics in Medicine & Biology. 2024; 69: 095010.

[32] Mishra AK, Gupta IK, Diwan TD, Srivastava S. Cervical precancerous lesion classification using quantum invasive weed optimization with deep learning on biomedical pap smear images. Expert Systems. 2024; 41: e13308.

[33] Kalbhor M, Shinde S, Joshi H, Wajire P. Pap smear-based cervical cancer detection using hybrid deep learning and performance evaluation. Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization. 2023; 11: 1615–1624.

[34] Devaraj S, Madian N, Menagadevi M, Remya R. Deep learning approaches for analysing papsmear images to detect cervical cancer. Wireless Personal Communications. 2024; 135: 81–98.

[35] Ramu K, Ananthanarayanan A, Josephson PJ, Paul NRR, Tumuluru P, Divya C, et al. Augmenting cervical cancer analysis with deep learning classification and topography selection using artificial bee colony optimization. SN Computer Science. 2024; 5: 703.

[36] Mathivanan SK, Francis D, Srinivasan S, Khatavkar V, K P, Shah MA. Enhancing cervical cancer detection and robust classification through a fusion of deep learning models. Scientific Reports. 2024; 14: 10812.

[37] Pacal I, Kılıcarslan S. Deep learning-based approaches for robust classification of cervical cancer. Neural Computing and Applications. 2023; 35: 18813–18828.

[38] Hussain E, Mahanta LB, Borah H, Das CR. Liquid based-cytology Pap smear dataset for automated multi-class diagnosis of pre-cancerous and cervical cancer lesions. Data in Brief. 2020; 30: 105589.

[39] Kalbhor M, Shinde SV. Malhari Dataset. 2023. Available at: https://doi.org/10.17632/M5KXDJ7M36.1 (Accessed: 12 July 2024).

[40] Lasch L, Rathat G, Du Thanh A. Squamous cell carcinoma antigen elevation in cervical cancer follow-up: the forest hiding the tree. European Journal of Gynaecological Oncology. 2018; 39: 324–326.

[41] Yoshida H, Yamamoto M, Shigeta H. Successful treatment of uterine cervical carcinoma with extensive vaginal lesions using laparoscopic surgery: a case report. European Journal of Gynaecological Oncology. 2020; 41: 629–633.

[42] Monika EG, Radosław S, Natalia S, Bartosz B, Stefan S. Synchronous ovarian, endometrial and cervical cancer: case report. European Journal of Gynaecological Oncology. 2021; 42: 1093–1094.

[43] Lecun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015; 521: 436–444.

[44] Kunduracioglu I, Pacal I. Advancements in deep learning for accurate classification of grape leaves and diagnosis of grape diseases. Journal of Plant Diseases and Protection. 2024; 131: 1061–1080.

[45] Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, et al. Attention is all you need. Advances in Neural Information Processing Systems. 2017; 5999–6009.

[46] Lubbad M, Karaboga D, Basturk A, Akay B, Nalbantoglu U, Pacal I. Machine learning applications in detection and diagnosis of urology cancers: a systematic literature review. Neural Computing and Applications. 2024; 36: 6355–6379.

[47] Pacal I, Alaftekin M, Zengul FD. Enhancing skin cancer diagnosis using swin transformer with hybrid shifted window-based multi-head self-attention and SwiGLU-based MLP. Journal of Imaging Informatics in Medicine. 2024. Available at: https://doi.org/10.1007/s10278-024-01140-8 (Accessed: 12 July 2024).

[48] Liu Z, Mao H, Wu CY, Feichtenhofer C, Darrell T, Xie S. A ConvNet for the 2020s. 2022. Available at: http://arxiv.org/abs/2201.03545 (Accessed: 12 July 2024).

[49] Yu W, Zhou P, Yan S, Wang X. InceptionNeXt: when inception meets ConvNeXt. 2023. Available at: http://arxiv.org/abs/2303.16900 (Accessed: 12 July 2024).

[50] Tan M, Le QV. EfficientNetV2: Smaller Models and Faster Training. 2021. Available at: https://arxiv.org/abs/2104.00298v3 (Accessed: 12 July 2024).

[51] Howard A, Sandler M, Chen B, Wang W, Chen LC, Tan M, et al. Searching for mobileNetV3. Proceedings of the IEEE International Conference on Computer Vision. Institute of Electrical and Electronics Engineers Inc.: Seoul, Korea (South). 2019.

[52] Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, et al. Swin transformer: hierarchical vision transformer using shifted windows. Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021; 10012–10022.

[53] Touvron H, Cord M, Jégou H. DeiT III: revenge of the ViT. In Avidan S, Brostow G, Cissé M, Farinella GM, Hassner T (eds.) Lecture Notes in Computer Science (pp. 516–533). Springer: Cham. 2022.

[54] Mehta S, Rastegari M. MobileViT: light-weight, General-purpose, and mobile-friendly vision transformer. 2021. Available at: http://arxiv.org/abs/2110.02178 (Accessed: 12 July 2024).

[55] Heo B, Yun S, Han D, Chun S, Choe J, Oh SJ. Rethinking spatial dimensions of vision transformers. Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021; 11936–11945.