Abstract

Analysis of pap smear images under a microscope by experts is a laborious and time consuming task. Computer-assisted diagnostic (CAD) systems can simplify this tedious process and allow experts to focus on more critical cases. Effective screening and early diagnosis can help to detect precancerous cells and allow early treatment. In this study, we have used a deep learning approach for classification of cervical cell images which obtained from pap smear slides. The proposed method automatically classifies cervical cell images into five categories without using any pre-processing on raw input images. We have obtained the promising results as compared to the previous studies in the literature. The proposed model can give a second opinion to clinicians in their daily routines and help them to focus on more complex cases.

References

[1] Khazaei, Z., Jarrahi, A. M., Momenabadi, V., Ghorat, F., Adineh, H. A., Sohrabivafa, M., &Goodarzi, E. (2019). Global cancer statistics 2018: GLOBOCAN estimates of incidence andmortality worldwide stomach cancers and their relationship with the human developmentindex (HDI). World Cancer Research Journal, 6, 9.
[2] Okunade, K. S. (2019). Human papillomavirus and cervical cancer. Journal of Obstetrics andGynaecology, 1-7.
[3] Catarino, R., Petignat, P., Dongui, G., & Vassilakos, P. (2015). Cervical cancer screening indeveloping countries at a crossroad: Emerging technologies and policy choices. Worldjournal of clinical oncology, 6(6), 281.
[4] Cox, S. (2012). Guidelines for Papanicolaou Test Screening and Follow-Up. Journal ofMidwifery & Women’s Health, 57(1), 86-89.
[5] Hartikainen, J. (2001). The Papanicolaou test: its utility and efficacy in cancerdetection. Contemporary nurse, 11(1), 45-49.
[6] M. Sharma, S. Kumar Singh, P. Agrawal, and V. Madaan, “Classification of Clinical Datasetof Cervical Cancer using KNN,” Indian J. Sci. Technol., vol. 9, no. 28, 2016
[7] R. Kumar, R. Srivastava, and S. Srivastava, “Detection and Classification of Cancer fromMicroscopic Biopsy Images Using Clinically Significant and Biologically InterpretableFeatures,” vol. 2015, 2015
[8] B. Ashok and P. Aruna, “Comparison of Feature selection methods for diagnosis of cervicalcancer using SVM classifier,” vol. 6, no. 1, pp. 94–99, 2016.
[9] Chankong, T., Theera-Umpon, N., & Auephanwiriyakul, S. (2009). Cervical cell classification using Fourier transform. In 13th International Conference on BiomedicalEngineering (pp. 476-480). Springer, Berlin, Heidelberg.
[10] Plissiti, M. E., & Nikou, C. (2012, June). Cervical cell classification based exclusively onnucleus features. In International Conference Image Analysis and Recognition (pp. 483-490). Springer, Berlin, Heidelberg.
[11] Chankong, T., Theera-Umpon, N., & Auephanwiriyakul, S. (2014). Automatic cervical cellsegmentation and classification in Pap smears. Computer methods and programs inbiomedicine, 113(2), 539-556.
[12] Bora, K., Chowdhury, M., Mahanta, L. B., Kundu, M. K., & Das, A. K. (2017). Automatedclassification of Pap smear images to detect cervical dysplasia. Computer methods andprograms in biomedicine, 138, 31-47.
[13] Mousser, W., & Ouadfel, S. (2019, April). Deep Feature Extraction for Pap-Smear ImageClassification: A Comparative Study. In Proceedings of the 2019 5th InternationalConference on Computer and Technology Applications (pp. 6-10). ACM.
[14] Plissiti, M. E., Dimitrakopoulos, P., Sfikas, G., Nikou, C., Krikoni, O., & Charchanti, A.(2018, October). SIPAKMED: A new dataset for feature and image based classification ofnormal and pathological cervical cells in Pap smear images. In 2018 25th IEEE InternationalConference on Image Processing (ICIP) (pp. 3144-3148). IEEE.
[15] Shi, J., Wang, R., Zheng, Y., Jiang, Z., & Yu, L. (2019). Graph Convolutional Networks forCervical Cell Classification.
[16] Kiran, G. V., & Meghana Reddy, G. (2019). Automatic Classification of Whole Slide PapSmear Images Using CNN with PCA Based Feature Interpretation. In Proceedings of theIEEE Conference on Computer Vision and Pattern Recognition Workshops (pp. 0-0).
[17] William, W., Ware, A., Basaza-Ejiri, A. H., & Obungoloch, J. (2018). A review of imageanalysis and machine learning techniques for automated cervical cancer screening from papsmear images. Computer methods and programs in biomedicine, 164, 15-22.
[18] Singh, Y., Srivastava, D., Chandranand, P. S., & Singh, D. (2018). Algorithms for screeningof Cervical Cancer: A chronological review. arXiv preprint arXiv:1811.00849.
[19] Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017). Densely connectedconvolutional networks. In Proceedings of the IEEE conference on computer vision andpattern recognition (pp. 4700-4708).
[20] Talo, M. (2019, April). Pneumonia Detection from Radiography Images using ConvolutionalNeural Networks. In 2019 27th Signal Processing and Communications ApplicationsConference (SIU) (pp. 1-4). IEEE.
[21] Ay, B., Yildirim, O., Talo, M., Baloglu, U. B., Aydin, G., Puthankattil, S. D., & Acharya, U.R. (2019). Automated Depression Detection Using Deep Representation and SequenceLearning with EEG Signals. Journal of medical systems, 43(7), 205.
[22] Talo, M. Meme Kanseri Histopatalojik Görüntülerinin Konvolüsyonal Sinir Ağları ileSınıflandırılması. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, 31(2), 391-398.
[23] Talo, M. (2019). Convolutional Neural Networks for Multi-class Histopathology ImageClassification. arXiv preprint arXiv:1903.10035.
[24] Milletari, F., Navab, N., & Ahmadi, S. A. (2016, October). V-net: Fully convolutional neuralnetworks for volumetric medical image segmentation. In 2016 Fourth InternationalConference on 3D Vision (3DV) (pp. 565-571). IEEE.