Abstract
The work reported in this paper presents a novel hierarchical modular neural network architecture (HMNNA) for automated screening of cervical cancer. HMNNA consists of three neural networks trained specifically on different areas of problem space under consideration, and the trained networks are then arranged in a tree structure forming hierarchical modular neural network architecture. The three specialized neural networks are trained by Levenberg–Maarquardt neural network algorithm. As compared to the standard back propagation algorithm, Levenberg–Maarquardt is fast and stable for convergence with only one drawback, i.e., storage requirement for estimated Hessian Matrix. For training and testing of HMNNA, a huge primary database is created which contains 8091 cervical cell images pertaining to 200 clinical cases collected from two health care institutions of northern India. The raw cases of cervical cancer in the form of Pap smear slides were photographed under a multi-headed digital microscope. Individual cells were manually cropped off from these slide images which were then passed through a feature extraction module for morphological profiling. Each cell was calibrated on the basis of 40 features from both cytoplasm and nucleus. After profiling, these cells were vigilantly assigned cell classes as per the latest 2001-Bethesda system of cervical cancer cell classification, by trained cytotechnicians and histopathologists. HMNNA is also trained and tested on the Herlev Benchmark dataset created by the Denmark University, which consists of 1417 cervical cancer cells. Both the datasets have seven classes of diagnosis, i.e., superficial squamous, intermediate squamous, columnar, mild dysplasia, moderate dysplasia, severe dysplasia, and carcinoma in situ, corresponding to the level of abnormality in cervical cells. These datasets are available in public domain at http://digitalpapsmeardb.in/ and http://mde-lab.aegean.gr/index.php/downloads. The screening potential of the HMNNA is compared with 25 well-known machine learning algorithms available in MatlabR2016 (Machine learning and statistics toolbox 10.2) and monolithic neural network algorithms available in Matlab neural network pattern recognition toolbox. The HMNNA outperformed in all the 25 algorithms for both the datasets. For the Novel Benchmark database, it produced a classification accuracy of 95.32% with an F-value of 0.949310 and classification accuracy of 88.41% with an F-value of 0.89145 for the Herlev dataset. The screening potential of HMNNA was also evaluated and compared with the other diagnostic systems available in the recently published literature and was found to be performing much better than the counterparts on multiple parameters of performance evaluation.
Similar content being viewed by others
References
Parkin DM, Bray FI, Devesa SS (2001) Cancer burden in the year 2000: the global picture. Eur J Cancer 37:S4–S66
Goldie SJ, Kuhn L, Denny L, Pollack A, Wright T (2001) Policy analysis of cervical cancer screening strategies in low-resource setting: clinical benefits and cost effectiveness. J Am Med Assoc 285:3107–3115
Sarwar A, Sharma V, Gupta R (2015) Hybrid ensemble learning technique for screening of cervical cancer using Papanicolaou smear image analysis. Pers Med Universe 4:54–62. doi:10.1016/j.pmu.2014.10.001
Sarwar A, Suri J, Ali M, Sharma V (2016) Novel benchmark database of digitized and calibrated cervical cells for artificial intelligence based screening of cervical cancer. J Ambient Intell Humaniz Comput. doi:10.1007/s12652-016-0353-8
Castellsagué X, de Sanjosé S, Aguado T, Louie KS, Bruni L, Muñoz J, Diaz M, Irwin K, Gacic M, Beauvais O, Albero G, Ferrer E, Byrne S, Bosch FX (2007) HPV and cervical cancer in the World 2007 Report. Vaccine, Elsevier
Chaturvedi A, Gillison ML (2010) Human papillomavirus and head and neck cancer. In: Epidemiology, pathogenesis, and prevention of head and neck cancer, pp 87–116
Munoz N, Bosch FX, de Sanjose S, Herrero R, Castellsague X, Shah KV et al (2003) Epidemiologic classification of human Papillomavirus types associated with cervical Cancer. N Engl J Med 348:518–527
Cronjé HS (2005) Screening for cervical cancer in the developing world. Best Pract Res: Clin Obstet Gynaecol 19(4):517–529
Delgado G, Bundy B, Zaino R, Sevin BU, Creasman WT, Major F (1990) Prospective surgical—pathological study of disease-free interval in patients with stage Ib squamous cell carcinoma of the cervix: a gynecologic oncology group study. Gynecol Oncol 38:352–357
Frankel K, Sidawy MK (1994) Formal proposal to combine the papanicolaou numerical system with Bethesda terminology for reporting cervical/vaginal cytologic diagnoses. Diagn Cytopathol 10(4):395–396
Bishop CM (2006) Pattern recognition and machine learning. Springer, New York
The discipline of machine learning: Carnegie Mellon University Carnegie Mellon University, School of Computer Science, Machine Learning Department (2006)
Witten IH, Frank E (2005) Data mining: practical machine learning tools and techniques. Morgan Kaufmann, Los Altos
Tan P-N (2006) Introduction to data mining. Pearson Education, India
Niknejad A, Petrovic D (2013) Introduction to computational intelligence techniques and areas of their applications in medicine. In: Agah A (ed) Medical applications of artificial intelligence. CRC Press, Boca Raton, FL, USA, pp 51–70
Ayer T, Alagoz O, Chhatwal J, Shavlik JW, Kahn CE, Burnside ES (2010) Breast cancer risk estimation with artificial neural networks revisited. Cancer 116:3310–3321
Baxt WG (1995) Application of artificial neural networks to clinical medicine. Lancet 346:1135–1138
Lundin J (1998) Artificial neural networks in outcome prediction. Anns Chir Gynaecol 87:128–130
Murre JMJ (1992) Learning and categorization in modular neural networks. Harvester – Wheatcheaf
Jacobs R. Task decomposition through competition in modular neural network architecture Ph.D. thesis
Johannes S, Wieringa BM, Matzke M, Münte TF (1996) Hierarchical visual stimuli: electrophysiological evidence for separate left hemispheric global and local processing mechanisms in humans. Neurosci Lett 210(2):111–114
Alpaydin E (1993) Multiple networks for function learning. In: International conference on neural networks, vol. 1, CA, USA, pp 9–14
Waibel A (1989) Modular construction of time-delay neural networks for speech recognition. Neural Comput 1:39–46
Manju T, Priya K, Chitra R (2013) Heart disease prediction system using weight optimized neural network. Int J Comput Sci Manag Res 2:2391–2397. (ISSN:2278-733X)
Ayer T, Alagoz O, Chhatwal J, Shavlik JW, Kahn CE, Burnside ES (2010) Breast cancer risk estimation with artificial neural networks revisited: discrimination and calibration. Cancer 116:3310–3321
Kourou K, Exarchos TP, Exarchos KP, Karamouzis MV, Fotiadis DI (2015) Machine learning applications in cancer prognosis and prediction. Comput Struct Biotechnol J 13:8–17
Tseng C-J, Lu C-J, Chang C-C, Chen G-D (2014) Application of machine learning to predict the recurrence-proneness for cervical cancer. Neural Comput Appl 24(6):1311–1316. doi:10.1007/s00521-013-1359-1
Mat-Isa NA, Mashor MY, Othman NH (2008) An automated cervical pre-cancerous diagnostic system. Artif Intell Med 42(1):1–11
Übeyli ED (2005) A mixture of experts network structure for breast cancer diagnosis. J Med Syst. doi:10.1007/s10916-005-6112-6
Ashidi N, Isa M, Mashor MY, Othman NH (2003) Classification of abnormal cervical cells using hierarchical multilayered perceptron network. In: CDROM proceedings of world congress on medical physics and biomedical engineering (WC2003). Paper no. 103, vol 4. Sydney, Australia
Sokouti B, Haghipour S, Tabrizi AD (2014) A framework for diagnosing cervical cancer disease based on feedforward MLP neural network and ThinPrep histopathological cell image features. Neural Comput Appl 24:221–232
Kusy M, Obrzut B, Kluska J (2013) Application of gene expression programming and neural networks to predict adverse events of radical hysterectomy in cervical cancer patients. Med Biol Eng Comput 51(12):1357–1365
Mariarputham EJ, Stephen A (2015) Nominated texture based cervical cancer classification. In: Computational and mathematical methods in medicine, Hindawi Publishing Corporation, vol 2015, Article ID 586928, p 10
Sulaiman SN, Mat-Isa NA, Othman NH, Ahmad F (2015) Improvement of features extraction process and classification of cervical cancer for the NeuralPap system. In: 19th International conference on knowledge based and intelligent information and engineering systems, Procedia Computer Science, Elsevier vol 60, pp 750–759
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
This study bears no conflict of interest.
Rights and permissions
About this article
Cite this article
Ali, M., Sarwar, A., Sharma, V. et al. Artificial neural network based screening of cervical cancer using a hierarchical modular neural network architecture (HMNNA) and novel benchmark uterine cervix cancer database. Neural Comput & Applic 31, 2979–2993 (2019). https://doi.org/10.1007/s00521-017-3246-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-017-3246-7