Abstract
In this paper, Levenberg–Marquardt feedforward MLP neural network (LMFFNN) was proposed to classify cervical cell images obtained from 100 patients including healthy, low-grade intraepithelial squamous lesion and high-grade intraepithelial squamous lesion cases. This neural network along with extracted cell image features is a new model for cervical cell image classification. The semiautomated cervical cancer diagnosis system is composed of two phases: image preprocessing/processing and feedforward MLP neural network. In the first stage, image preprocessing is done to reduce the existing noises without lowering the resolution. After that, image processing algorithms were applied to manually cropped cell images to achieve a linear plot which includes real components, were used as LMFFNN inputs for classification of cervical cell images. Based on the results, cervical cell images were classified successfully with 100 % correct classification rate using the proposed method. Moreover, the rates of sensitivity and specificity were calculated as 100 % using LMFFNN method. It was shown there was a good agreement between the expert decision and values gained from the ANN model.
Similar content being viewed by others
References
World Health Organization (WHO) (2007) Fact sheet no. 297. Cancer
National Cancer Institute (2007) NCI women’s health report fiscal years 2005, 2006, 2007
Breen N, Wagnere DK, Brown ML, Davis WW, Barbash RB (2001) (2001) Progress in cancer screening over a decade: results of cancer screening from the 1987, 1992 and 1998 National Health Interview Surveys. J Natl Cancer Inst 93(22):1704–1713
Adami HO, Ponten J, Sparen P, Bergstrom R, Gustafsson L, Friberg LG (1994) Survival trend after invasive cervical cancer diagnosis in Sweden before and after cytologic screening. Cancer 73(1):140–147
Farmer PS (2001) Screening for cancer: progress but more can be done. J Natl Cancer Inst 93(22):1676–1677
Hislop TG, Band PR, Deschamps M, Clarke HF, Smith JM, Ng VT (1994) Cervical cancer screening in Canadian native women: adequacy of the Papanicolaou smear. Acta Cytol 38(1):29–32
Othman NH, Ayub MC, Aziz WA, Muda M, Wahid R, Selvarajan S (1997) Pap smears—is it an effective screening methods for cervical cancer neoplasia? An experience with 2289 cases. Malays J Med Sci 4(1):45–50
Othman NH (2003) Cancer of the cervix-from bleak past to bright future. Pustaka Reka Publishing Company, Kelantan
Kuie TS (1996) Cervical cancer: its causes and prevention. Times Book Int, Singapura
Abel EW, Zacharia PC, Forster A, Farrow TL (1996) Neural network analysis of the EMG interference pattern. Med Eng Phys 18:12–17
Kara S, Kemaloglu S, Guven A (2005) Detection of femoral artery occlusion from spectral density of Doppler signals using the artificial neural network. Expert Syst Appl 29:945–952
Edenbrandt L, Heden B, Pahlm O (1993) Neural networks for analysis of ECG complexes. J Electrocardiol 26:66–73
Sokouti B, Sokouti M, Haghipour S (2011) A non-linear system’s response identification using artificial neural networks. Elektron Elektrotech 7(113):63–66
Walker DC, Brown BH, Hose DR, Smallwood RH (2000) Modeling the electrical impedivity of normal and premalignant cervical tissue. Electron Lett 36(19):1603–1604
Chang KS, Pavlova I, Marin N, Follen M, Richards-Kortum R (2005) Fluorescence spectroscopy as a diagnostic tool for detecting cervical pre-cancer. Int Conf Gynecol Oncol 99(3):S61–S63
Balas C (2001) A novel optical imaging method for the early detection, quantitative grading and mapping of cancerous and precancerous lesions of cervix. IEEE T Bio Med Eng 48(1):96–104
Frable WJ (2001) Cervical screening by neural networks. Cancer 93(3):171–172
Kok MR, Boon ME, Kok PGS, Hermans J, Grobbee DE, Kok LP (2001) Less medical intervention after sharp demarcation of grade 1–2 cervical intraepithelial neoplasia smears by neural network screening. Cancer 93(3):173–178
Li Z, Najarian K (2001) Automated classification of Pap smear tests using neural networks. IEEE IJCNN 4:2899–2901
Balasubramaniam R, Rajan S, Doraiswami R, Stevenson M (1998) A reliable composite classification strategy. IEEE Can Conf Elect Comput Eng P 2:914–917
HTAC (2002) Pap smears and prevention of cervical cancer. Citing from internet source URL: http://www.health.state.mn,us/htac/papq&a.html
WebMD (2002) How can cervical cancer be prevented? Citing from internet source URL: http://www.webmd.com/content/dmk/dmk_article_3961643
Tumer K, Ramanujam N, Ghosh J, Richards-Kortum R (1998) Ensembles of radial basis function networks for spectroscopic detection of cervical precancer. IEEE T Bio Med Eng 45(8):953–961
Bazoon M, Stacey DA, Cui C, Harauz G (1994) A hierarchical artificial neural network system for the classification of cervical cells. IEEE IJCNN 6:3525–3529
Brouwer RK (1995) Automatic growing of a Hopfield style neural network for classification of patterns. Int Conf Image Process Appl P, 637–641. doi:10.1049/cp:19950737
Hagan M, Menhaj M (1994) Training feedforward networks with the Marquardt algorithm. IEEE T Neural Netw 5(6):989–993
Mat-Isa NA, Mashor MY, Othman NH (2003) Classification of cervical cancer cells using HMLP network with confidence percentage and confidence level analysis. Int J Comput Internet Manag 11(1):17–29
Mat-Isa NA (2005) Automated detection technique for Pap smear images using moving K-means clustering and modified seed based region growing algorithm. Int J Comput Internet Manag 13(3):45–59
Mat-Isa NA, Mashor MY, Othman NH (2008) An automated cervical pre-cancerous diagnostic system. Artif Intell Med 42:1–11
Harandi NM, Sadri S, Moghaddam NA, Amirfattahi R (2009) An automated method for segmentation of epithelial cervical cells in image of ThinPrep. J Med Syst 34(6):1043–1058
Genctav A, Aksoy S, Onder S (2012) Unsupervised segmentation and classification of cervical cell images. Pattern Recogniti 45(12):4151–4168
Mohideen Fatima alias Niraimathi M, Seenivasagam V (2012) A hybrid image segmentation of cervical cells by bi-group enhancement and scan line filling. IRACST Int J Comput Sci Inf Technol Secur 2(2):368–375
Plissiti M, Nikou C (2012) Cervical cell classification based exclusively on nucleus features. International conference on image analysis and recognition (ICIAR’12), Lecture Notes in Comput Sci 7325:483–490
Miller FS, Nagel LE, Kenny-Moynihan MB (2007) Implementation of the ThinPrep® imaging system in a high-volume metropolitan laboratory. Diagn Cytopathol 35(4):213–217
Statnikov A, Aliferis CF, Tsamardinos I, Hardin D, Levy S (2005) A comprehensive evaluation of multi-category classification methods for microarray gene expression cancer diagnosis. Bioinformatics 25:631–643
Sokouti B, Haghipour S, Tabrizi AD (2012) A pilot study on image analysis techniques for extracting early uterine cervix cancer cell features. J Med Syst 36(3):1901–1907
Russ JC (2007) The image processing handbook, 5th edn. CRC Taylor & Francis, Boca Raton
Gonzalez RC, Woods RE (2002) Digital image processing, 2nd edn. Prentice Hall, Englewood Cliffs
Otsu NA (1979) Threshold selection method from gray level histograms. IEEE Trans Syst Man Cybern 9(1):62–66. doi:10.1109/TSMC.1979.4310076
Hagan M, Demuth H, Beale M (1996) Neural network design. PWS Publishing Co., Boston
Emiroglua ME, Bilhana O, Kisi O (2011) Neural networks for estimation of discharge capacity of triangular labyrinth side-weir located on a straight channel. Expert Syst Appl 38(1):867–874
Ozbay Y, Ceylan M (2007) Effects of window types on classification of carotid artery Doppler signals in the early phase of atherosclerosis using complex valued artificial neural network. Comput Biol Med 37:287–295
Tarassenko L, Khan YU, Holt MRG (1998) Identification of interictal spikes in the EEG using neural network analysis. Proc Sci Meas Technol IEEE 45:270–278
Dirgenali F, Kara S (2006) Recognition of early phase of atherosclerosis using principles component analysis and artificial neural networks from carotid artery Doppler signals. Expert Syst Appl 31:643–651
Joste NE, Rushing L, Granados R, Zitz JC, Genest DR, Crum CP, Cibas ES (1996) Bethesda classification of cervicovaginal smears: reproducibility and viral correlates. Hum Pathol 27(6):581–585
Stoler MH, Schiffman M (2001) Interobserver reproducibility of cervical cytologic and histologic interpretations: realistic estimates from the ASCUS-LSIL Triage Study. JAMA 285(11):1500–1505
Ramli DA, Kadmin AF, Mashor MY, Mat Isa NA (2004) Diagnosis of cervical cancer using hybrid multilayered perceptron (HMLP) Network Lecture Notes in Artif Intell 3213:591–598
Conflicts of interest
The authors had no competing interests to declare in relation to this article.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Sokouti, B., Haghipour, S. & Tabrizi, A.D. A framework for diagnosing cervical cancer disease based on feedforward MLP neural network and ThinPrep histopathological cell image features. Neural Comput & Applic 24, 221–232 (2014). https://doi.org/10.1007/s00521-012-1220-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-012-1220-y