Application of Artificial Neural Networks in the Classification of Cervical Cells Based on the Bethesda System

Authors

  • Nor Ashidi Mat Isa Control and Electronic Intelligent System (CELTS) Research Group, School of Electrical & Electronic Engineering, Universiti Sains Malaysia, Engineering Campus, 14300 Nibong Tebal, Penang, Malaysia
  • Mohd Yusoff Mashor Control and Electronic Intelligent System (CELTS) Research Group, School of Electrical & Electronic Engineering, Universiti Sains Malaysia, Engineering Campus, 14300 Nibong Tebal, Penang, Malaysia
  • Nor Hayati Othman Deputy Dean and Professor of Pathology, School of Medical Sciences, Universiti Sains Malaysia, Health Campus, 16150 Kubang Kerian, Kelantan, Malaysia
  • Kamal Zuhairi Zamli Control and Electronic Intelligent System (CELTS) Research Group, School of Electrical & Electronic Engineering, Universiti Sains Malaysia, Engineering Campus, 14300 Nibong Tebal, Penang, Malaysia

DOI:

https://doi.org/10.32890/jict2005.4.5

Keywords:

RBF neural network, HRBF neural network, MLP neural network, HMLP neural network, cervical cancer, diagnostic system

Abstract

Neural networks have been used in the medical field in various applications such as medical imaging processing and disease diagnostic technique. In this paper, we investigate the capability of two conventional neural networks as an intelligent diagnostic system. In particular, the radial basis function (RBF) and multilayered perceptron (MLP) neural networks were used to classify the type of cervical cancer in its early stage. The study is divided into two stages. In the first stage, we investigate the applicability of neural networks to classify cervical cells into normal and abnormal cells. In the second stage, we classify cervical cells abnormality into three classes based on The Bethesda Classification System; normal, low-grade squamous intraepithelial lesion (LSIL) and high-grade squamous intraepithelial lesion (HSIL). Diagnosis obtained using RBF and MLP neural networks gave promising results. Nevertheless, classification of abnormal cells into LSIL and HSIL yielded unsatisfactory results. In order to address this problem, this study adopted two hybrid neural networks namely hybrid radial basis function (HRBF) and hybrid multilayered perceptron (HMLP) networks in order to improve the performances of conventional neural networks. The overall diagnostic performance was measured using accuracy, sensitivity, specificity, false negative and false positive analysis by comparing to the diagnoses made by pathologists. This study indicates that HMLP network produces better overall diagnostic performance than the MLP, RBF and HRBF networks.

 

References

Adami, H. O., Ponten, J., Sparen, P., Bergstrom, R., Gustafsson, L. & Friberg,

L. G. (1994). Survival Trend After Invasive Cervical Cancer Diagnosis in Sweden Before and After Cytologic Screening. Cancer. Vol. 73. No. 1, pp. 140-147.

Ashfaq, R., Solares, B. & Saboorian, M. (1996). Detection of Endocervical Component by Papnet System on Negative Cervical Smears. Diagnosis Cytopathology. Vol. 15. No. 2. pp. 121-123.

Balasubramaniam, R., Rajan, S., Doraiswami, R. & Stevenson, M. (1998). A Reliable Composite Classification Strategy. Proc. of IEEE Canadian Conf. on Electrical and Computer Engineering. Vol. 2. pp. 914-917.

Bazoon, M., Stacey, D. A., Cui, C. & Harauz, G. (1994). A Hierarchical Artificial Neural Network System for The Classification of Cervical Cells. Proc. of IEEE Int. Conf. on Neural Network. Vol. 6. pp. 3525-3529.

Breen, N., Wagener, D. K., Brown, M. L., Davis, W. W. & Barbash, R. B. (2001). Progress in Cancer Screening Over a Decade: Results of Cancer //ict.uum.edu.my/ http Journal of ICT, 4, pp: 77-ee Screening From the 1987, 1992 and 1998 National Health Interview Surveys. J. of the National Cancer Institute. Vol. 93. No. 22. pp. 1704-1713.

Broomhead, D. S. & Lowe, D. (1988). Multivariable Functional Interpolation and Adaptive Networks. Complex System. Vol. 2. pp. 321-355.

Brouwer, R. K. (1995). Automatic Growing of A Hopfield Style Neural Network for Classification of Patterns. Proceedings of 5" International Conference on Image Processing and Its Applications. pp. 637-641.

Brouwer, R. K. (1993). Using The Hopfield Neural Network As A Classifier by Storing Class Representatives. Proceedings of Canadian Conference on Electrical and Computer Engineering. Vol. 1. pp. 337-340.

Cabaniss, D., Cason, Z., Lemos, L. & Benghuzzi, H. (1997). The Assessment of An Endocervical Component in Cervicovaginal Smears with The Papnet System. Proceedings of 16" Southern Conference on Biomedical Engineering. pp. 357-361.

Chen, S., Billings, S. A. & Grant, P. M. (1992). Recursive Hybrid Algorithm for Non-Linear System Identification Using Radial Basis Function Networks. Int. J. of Control. Vol. 55. pp. 1051-1070.

Chen, S., Cowan, C. F.N., Billings, S. A., & Grant, P. M. (1990). A Parallel Recursive Prediction Error Algorithm for Training Layered Neural Networks. Int. J. of Control. Vol. 51. No. 6. pp. 1215-1228.

Cotran, R. S., Kumar, V. & Robbins, S. L. (1994). Pathologic Basis of Disease (5" Edition), W. B. Saunders Company, Philadelphia.

Framer, P. S. (2001). Screening for Cancer: Progress but More Can Be Done. J. of the National Cancer Institute. Vol. 93. No. 22. pp. 1676-1677. Hislop, T. G., Band, P. R., Deschamps, M., Clarke, H. F., Smith, J. M. & Ng, V.

T. Y. (1994). Cervical Cancer Screening in Canadian Native Women: Adequacy of The Papanicolaou Smear. The J. of Clinical Cytology and Cytopathology. Vol. 38. No. 1. pp. 29-32. //ict.uum.edu.my/ http Journal of ICT, 4, pp: 77-

Kamel, M. S. & Selim, S. Z. (1994). New Algorithms for Solving the Fuzzy Clustering Problem. Pattern Recognition. Vol. 27. No. 3. pp. 421-428.

Kuie, T. S. (1996). Cervical Cancer: Its Causes and Prevention. Singapore: Times Book Int.

Li, Z. & Najarian, K. (2001). Automated Classification of Pap Smear Tests Using Neural Networks. Proc. of Int. Joint Conf. on Neural Networks. Vol. 4. pp. 2899-2901.

Ling, F. (1991). Givens Rotation Based on Least Squares Lattice and Related Algorithms. JEEE Trans. on Signal Processing. Vol. 39. pp. 1541-1551.

Mashor, M. Y. (2000a). Hybrid Training Algorithm for RBF Network. Int. J. of The Computer, The Internet and Management. Vol. 8. No. 2. pp. 50-65.

Mashor, M. Y. (2000b). Hybrid Multilayered Perceptron Networks. Int. J. of System Science. Vol. 31. No. 6. pp. 771-785.

Mat-Isa, N. A, Mashor, M. Y. & Othman, N. H. (2002). Diagnosis of Cervical Cancer Using Hierarchical Radial Basis Function (HiRBF) Network. Proceedings of International Conference on Artificial Intelligence in Engineering & Technology. pp. 458—465.

Mat-Sakim, H. A. (2004). Neural Network — Based Diagnosis and Prognosis Study Using Fine Needle Aspirate of Breast Lesion. PhD Thesis, Universiti Sains Malaysia.

McKenna, S. J., Ricketts, I. W., Cairns, A. Y. & Hussein, K. A. (1992). Cascade-Correlation Neural Networks for The Classification of Cervical Cells. Proc. of IEE Colloquium on Neural Networks for Image Processing Applications. pp. 5/1-5/4.

McLoone, S., Brown, M. D., Irwin, G. & Lightbody, G. (1998). A Hybrid Linear/ Nonlinear Training Algorithm for Feedforward Neural Network. IEEE Trans. on Neural Networks. Vol. 9. No. 4. pp. 669-684.

Mitra, P., Mitra, S. & Pal, S. K. (2000). Staging of Cervical Cancer with Soft Computing. JEEE Trans. on Biomedical Engineering. Vol. 47. No. 7. pp. 934-940. //ict.uum.edu.my/ http Journal of ICT, 4, pp: 77-_SeSSSo Othman, N. H., Ayub, M. C., Aziz, W.A. A., Muda, M., Wahid, R. & Selvarajan,

S. (1997). Pap Smears — Is It An Effective Screening Methods for Cervical Cancer Neoplasia? — An Experience with 2289 Cases. The Malaysian J. of Medical Sciences. Vol. 4. No. 1. pp. 45-50.

Othman, N. H., Ayob, M. C. & Wahid, R. A. (1995). Is Pap Smear Screening Program Effective? A Kelantan Experience with 5000 cases. Malaysian J. of Pathology. Vol. 17. No. 1. pp. 53.

Poggio, T. & Girosi, F. (1990). Network for Approximation and Learning. Proc. of The IEEE. Vol. 78. No. 9. pp. 1481-1497.

Powell, M. J. D. (1998). Radial Basis Functions for Multivariable Interpolation: A Review. Proc. of IMA Conf. on Algorithms for The Approximation of Functions and Data. pp. 143-167. Ricketts, I. W., Banda-Gamboa, H., Cairns, A. Y., Hussein, K., Hipkiss, W.,

McKenna, S. & Parianos, E. (1992). Towards The Automated PreScreening of Cervical Smears. Proc. of The IEE Colloquium on Applications of Image Processing in Mass Health Screening. pp. 7/1-7/4.

Rughooputh, H. C. S. & Rughooputh, S. D. D. V. (1999). EKF Learning Algorithm For The Quaternion-Valued Multi-Layered Perceptron Neural Network. Proc. of The Int. Conf. on Robotics, Vision and Parallel Processing for Automation. Vol. 1. pp. 117-122.

Schmitz, G. P. J. & Aldrich, C. (1999). Combinatorial Evolution of Regression Nodes in Feedforward Neural Networks. IEEE Trans. on Neural Network. Vol. 12. No. 1. pp. 175-189.

Tumer, K., Ramanujam, N., Ghosh, J. & Richards-Kortum, R. (1998). Ensembles of Radial Basis Function Networks for Spectroscopic Detection of Cervical Precancer. JEEE Trans. on Biomedical Engineering. Vol. 45 No. 8. pp. 953-961.

WebMD. (2005). How Can Cervical Cancer Be Prevented?. Citing from internet source URL http://www.webmd.com/content/dmk/dmk_article_3961643.

Xu, L., Krzyzak, A. & Oja, E. (1993). Rival Penalised Competitive Learning t.uum.edu.my/ //ic http Journal of ICT, 4, pp: 77-for Clustering Analysis, RBF Net and Curve Detection. IEEE Trans. on Neural Networks. Vol. 4. No. 4.

Zhu, Q., Cai, Y. & Liu, L. (1990). Global Learning Algorithm for A RBF Network. [EEE Trans. on Neural Networks. Vol. 12. No. 3. pp. 527-540.

Downloads

Published

23-03-2005

Issue

Vol. 4 (2005): Journal of Information and Communication Technology (JICT) Vol. 4, 2005

Section

Articles

How to Cite

Mat Isa, N. A., Mashor, M. Y., Othman, N. H., & Zamli, K. Z. (2005). Application of Artificial Neural Networks in the Classification of Cervical Cells Based on the Bethesda System. Journal of Information and Communication Technology, 4, 77-97. https://doi.org/10.32890/jict2005.4.5

Research impact

Harvested 2026-09-06
1 citations, from OpenAlex — the highest of the sources checked

Counts differ between services because each indexes a different body of literature. None of them is the whole picture.

Identifiers DOI 10.32890/jict2005.4.5 OpenAlex W4391079819

Most read articles by the same author(s)