DeepCerviCancer - Deep Learning-Based Cervical Image Classification using Colposcopy and Cytology Images

Madhura Kalbhor; Swati Shinde; Sagar Lahade; Tanupriya Choudhury

doi:10.4108/eetpht.9.3473

Authors

Madhura Kalbhor Pimpri Chinchwad College of Engineering
Swati Shinde Pimpri Chinchwad College Of Engineering https://orcid.org/0000-0002-8271-3025
Sagar Lahade Pimpri Chinchwad College of Engineering
Tanupriya Choudhury University of Petroleum and Energy Studies

DOI:

https://doi.org/10.4108/eetpht.9.3473

Keywords:

computer vision, smart Healthcare, Artificial Intelligence, Internet of Things, MoveNet, Pose estimation, Machine Learning, deep learning, KNN, SVM, LDA

Abstract

INTRODUCTION: Cervical cancer is a deadly malignancy in the cervix, affecting billions of women annually.

OBJECTIVES: To develop deep learning-based system for effective cervical cancer detection by combining colposcopy and cytology screening.

METHODS: It employs DeepColpo for colposcopy and DeepCyto+ for cytology images. The models are trained on multiple datasets, including the self-collected cervical cancer dataset named Malhari, IARC Visual Inspection with Acetic Acid (VIA) Image Bank, IARC Colposcopy Image Bank, and Liquid-based Cytology Pap smear dataset. The ensemble model combines DeepColpo and DeepCyto+, using machine learning algorithms.

RESULTS: The ensemble model achieves perfect recall, accuracy, F1 score, and precision on colposcopy and cytology images from the same patients.

CONCLUSION: By combining modalities for cervical cancer screening and conducting tests on colposcopy and cytology images from the same patients, the novel approach achieved flawless results.

Downloads

Download data is not yet available.

Author Biographies

Madhura Kalbhor, Pimpri Chinchwad College of Engineering

Assistant Professor at Pimpri Chinchwad College of Engineering

Swati Shinde, Pimpri Chinchwad College Of Engineering

Dean- Research and Developments Professor in the Department of Computer Engineering Pimpri Chinchwad College of Engineering, Pune.

Principal Investigator- DST Funded Research Project,

NVIDIA Ambassador and Certified Instructor for Deep Learning,

Member ACM, IEEE, ISTE, IAENG

References

Anupama Bhan, Divyam Sharma, Sourav Mishra. Computer Based Automatic Segmentation of Pap smear Cells for Cervical Cancer Detection. 2018 5th International Conference on Signal Processing and Integrated Networks (SPIN), Noida, 22-23 February 2018, DOI: 10.1109/SPIN.2018.8474108. DOI: https://doi.org/10.1109/SPIN.2018.8474108

Zhi Lu et. al, Evaluation of Three Algorithms for the Segmentation of Overlapping Cervical Cells. IEEE Journal of Biomedical and Health Informatics, Volume: 21, Issue: 2, March 2017, DOI: 10.1109/JBHI.2016.2519686. DOI: https://doi.org/10.1109/JBHI.2016.2519686

Zaid Alyafeai et. al, A fully-automated deep learning pipeline for cervical cancer classification. Expert Systems with Applications, Volume 141, 1 March 2020, 112951, https://doi.org/10.1016/j.eswa.2019.112951. DOI: https://doi.org/10.1016/j.eswa.2019.112951

R. Elakkiya, V. Subramaniyaswamy et al, Cervical Cancer Diagnostics Healthcare System Using Hybrid Object Detection Adversarial Networks. IEEE Journal of Biomedical and Health Informatics, Volume: 26, Issue: 4, April 2022, DOI: 10.1109/JBHI.2021.3094311.

R. Elakkiya, V. Subramaniyaswamy et al, Cervical Cancer Diagnostics Healthcare System Using Hybrid Object Detection Adversarial Networks. IEEE Journal of Biomedical and Health Informatics, Volume: 26, Issue: 4, April 2022, DOI: 10.1109/JBHI.2021.3094311. DOI: https://doi.org/10.1109/JBHI.2021.3094311

Jennyfer Susan M.B et. al, Design and Development of Webportal for Cervical Cancer Diagnosis using MobileODT Images. 2019 IEEE International Smart Cities Conference (ISC2), doi:10.1109/ISC246665.2019.9071683. DOI: https://doi.org/10.1109/ISC246665.2019.9071683

Kaggle. Intel & mobileodt Cervical Cancer Screening, https://www.kaggle.com/c/intel-mobileodt-cervical-cancerscreening, 2017.

Balkin, M.S. Cervical Cancer Prevention and Treatment: Science, Public Health and Policy Overview. In Proceedings of the Challenges and Opportunities for Women’s Right to Health, Brussels, Belgium, 27–28 September 2007.

Ferlay J, Bray F, Pisani P et al. Globocan 2002 cancer incidence, mortality, and prevalence worldwide. Version 2.0. 2004: Lyon, France, IARC Press. IARC CancerBase No. 5.

D. M. Eddy, Secondary prevention of cancer: an overview. B World Health Organ, vol. 64, no. 3, p. 421, 1986.

Madhura Kalbhor, Dr. Swati Shinde, et al, DeepCyto: A Hybrid Framework for Cervical Cancer Classification by using Deep Feature Fusion of Cytology Images Mathematical Biosciences and Engineering 2022, Volume 19, Issue 7: 6415-6434. doi: 10.3934/mbe.2022301. DOI: https://doi.org/10.3934/mbe.2022301

Gay, J D et al. False-negative results in cervical cytologic studies, Acta cytologica vol. 29, 6 (1985): 1043-6, PMID: 3866457.

Bosch, M et al. “Characteristics of false-negative smears tested in the normal screening situation”, Acta cytologica vol. 36, 5 (1992): 711-6, PMID: 1523929.

Naryshkin, S. The false-negative fraction for Papanicolaou smears: how often are "abnormal" smears not detected by a "standard" screening cytologist?. Archives of pathology & laboratory medicine vol. 121, 3 (1997): 270-2, PMID: 9111116.

Koonmee S, Bychkov A, Shuangshoti S, Bhummichitra K, Himakhun W, Karalak A, Rangdaeng S, False-Negative Rate of Papanicolaou Testing: A National Survey from the Thai Society of Cytology, Acta Cytologica 2017; 61:434-440, doi: 10.1159/000478770. DOI: https://doi.org/10.1159/000478770

Anjali Deswal, Sanjeev Dhawan et. al, A Technique For Determining The Early Detection For Cervical Cancer, 2019 5th International Conference on Signal Processing, Computing and Control (ISPCC), DOI: 10.1109/ISPCC48220.2019.8988374. DOI: https://doi.org/10.1109/ISPCC48220.2019.8988374

Romuere Silva et. al, Searching for cell signatures in multidimensional feature spaces, International Journal of Biomedical Engineering and Technology, 2021 Vol.36 No.3, pp.236 - 256, doi:10.1504/IJBET.2021.10040044. DOI: https://doi.org/10.1504/IJBET.2021.116988

Wenya linda bi et. al, Artificial Intelligence in Cancer Imaging: Clinical Challenges and Applications, A Cancer Journal for Clinicians, 05 February 2019 https://doi.org/10.3322/caac.21552. DOI: https://doi.org/10.3322/caac.21552

Krishna Prasad Battula et.al ,Deep Learning based Cervical Cancer Classification and Segmentation from Pap Smears Images using an EfficientNet, International Journal of Advanced Computer Science and Applications(IJACSA), Volume 13 Issue 9, 2022, Doi:10.14569/IJACSA.2022.01309104. DOI: https://doi.org/10.14569/IJACSA.2022.01309104

O. Attallah, Cervical Cancer Diagnosis Based on Multi-Domain Features Using Deep Learning Enhanced by Handcrafted Descriptors. Applied Sciences, vol. 13, no. 3, p. 1916, Feb. 2023, doi: 10.3390/app13031916. DOI: https://doi.org/10.3390/app13031916

Ming Fang; Xiujuan Lei et. al, A Deep Neural Network for Cervical Cell Classification Based on Cytology Images, IEEE Access, Volume: 10, DOI: 10.1109/ACCESS.2022.3230280. DOI: https://doi.org/10.1109/ACCESS.2022.3230280

Khaled Mabrouk Amer Adweb et. al, Cervical Cancer Diagnosis Using Very Deep Networks Over Different Activation Functions, IEEE Access, Volume: 9, DOI: 10.1109/ACCESS.2021.3067195. DOI: https://doi.org/10.1109/ACCESS.2021.3067195

Venkatesan Chandran et. al, Diagnosis of Cervical Cancer based on Ensemble Deep Learning Network using Colposcopy Images, Hindawi BioMed Research International Volume 2021, Article ID 5584004, 15 pages, https://doi.org/10.1155/2021/5584004. DOI: https://doi.org/10.1155/2021/5584004

Liu L, Wang Y, Liu X, Han S, Jia L, et. al, Computer-aided diagnostic system based on deep learning for classifying colposcopy images, Ann Transl Med. 2021 Jul; 9(13): 1045, doi: 10.21037/atm-21-885. DOI: https://doi.org/10.21037/atm-21-885

Y. Karasu Benyes, E. C. Welch, A. Singhal, J. Ou, and A. Tripathi, A Comparative Analysis of Deep Learning Models for Automated Cross-Preparation Diagnosis of Multi-Cell Liquid Pap Smear Images, Diagnostics, vol. 12, no. 8, p. 1838, Jul. 2022, doi: 10.3390/diagnostics12081838. DOI: https://doi.org/10.3390/diagnostics12081838

Kyi Pyar Win at. al, Computer-Assisted Screening for Cervical Cancer Using Digital Image Processing of Pap Smear Images, Appl. Sci. 2020, 10, 1800,doi:10.3390/app10051800. DOI: https://doi.org/10.3390/app10051800

Mohammed Alsalatie et. al, "Analysis of Cytology Pap Smear Images Based on Ensemble Deep Learning Approach", Diagnostics 2022, 12, 2756. https://doi.org/10.3390/diagnostics12112756. DOI: https://doi.org/10.3390/diagnostics12112756

Komala Rayavarapu et. al, Prediction of Cervical Cancer using Voting and DNN Classifiers, 2018 International Conference on Current Trends towards Converging Technologies (ICCTCT), DOI: 10.1109/ICCTCT.2018.8551176. DOI: https://doi.org/10.1109/ICCTCT.2018.8551176

N. Sompawong et. al, Automated Pap Smear Cervical Cancer Screening Using Deep Learning, 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), doi:10.1109/EMBC.2019.8856369. DOI: https://doi.org/10.1109/EMBC.2019.8856369

D. N. Diniz et al., A Deep Learning Ensemble Method to Assist Cytopathologists in Pap Test Image Classification, Journal of Imaging, vol. 7, no. 7, p. 111, Jul. 2021, doi: 10.3390/jimaging7070111. DOI: https://doi.org/10.3390/jimaging7070111

Pin Wang et. al, Adaptive Pruning of Transfer Learned Deep Convolutional Neural Network for Classification of Cervical Pap Smear Images, IEEE Access, Volume: 8, doi: 10.1109/ACCESS.2020.2979926. DOI: https://doi.org/10.1109/ACCESS.2020.2979926

International Agency for Research on Cancer, IARC Visual Inspection with Acetic Acid (VIA) Image Bank, [Online]. Available: https://screening.iarc.fr/cervicalimagebank.php. [Accessed: Apr. 19, 2023].

International Agency for Research on Cancer, IARC Colposcopy Image Bank, [Online]. Available: https://screening.iarc.fr/cervicalimagebank.php. [Accessed: Apr. 19, 2023].

E. Hussain, L. B. Mahanta, H. Borah, and C. R. Das, Liquid based-cytology Pap smear dataset for automated multi-class diagnosis of pre-cancerous and cervical cancer lesions. Data in Brief, 30, (2020) 105589. doi:10.1016/j.dib.2020.105589. DOI: https://doi.org/10.1016/j.dib.2020.105589