Identification of Breast Cancer Using the Extreme Learning Machine Assisted by Firefly Algorithm

Abstract

The Breast cancer is the second cancer type which causes death of women. The premature detection of cancer and the suitable treatment applied to cancer cells can reduce the deadly risk. The medical doctors can make faults in diagnosis of the cancer disease. The performance of artificial intelligence methods (AIMs) containing increased thanks to rapid improvements in the technologies of the computer hardware. AIMs can be used regarding the enhancement of diagnostic accuracy. Standard Gradient–Based back propagation artificial neural networks (BP–ANN) has been commonly utilized in the diagnosis of the breast cancer disease. Even though BP–ANN are good performance in diagnosis of cancer disease, it has some limitations such as possible to be trapped in local minima and long time in the training process. In this study, the extreme learning machine assisted by heuristic firefly algorithm (FF–ELM) is proposed for diagnoses of breast cancer disease on the Breast Cancer Wisconsin Dataset. The diagnostic performance of proposed FF–ELM was compared with the standard ELM and BP–ANN methods. The results show that FF–ELM provides a meaningful enhancement regarding the classification performance and it can be used as a powerful technique for the medical problems.

Keywords

• Extreme Learning Machine,Firefly Algorithm,Breast Cancer,Medical Decision Support Systems

Ateş Böceği Algoritması Destekli Aşırı Öğrenme Makinesi ile Göğüs Kanseri Veri Kümelerinin Sınıflandırılması

Öz

Göğüs kanseri hastalığı, kadınların ölümüne neden olan ikinci kanser türüdür. Kanser hastalığının erken teşhisi ve kanser hücrelerine uygulanan uygun ve doğru tedavi hastalığın ölümcül riskini azaltabilir. Tıp doktorları, kanser hastalığının teşhisinde zaman, zaman hata yapabilmektedirler. Yapay zeka tekniklerinin (YZT) performansı, bilgisayar donanım teknolojilerindeki hızlı gelişmeler sayesinde artmıştır. Buna bağlı olarak, kanser hastalığının tanı doğruluğunun arttırılması ile ilgili olarak YZT’ler kullanılabilir. Standart Eğime Dayalı Geri Yayılım Yapay Sinir Ağları (GY–YZT), göğüs kanseri hastalığının tanısında yaygın olarak kullanılmaktadır. GY–YZT, kanser hastalığının teşhisinde iyi bir performans sergilese de, yerel minimum ve eğitim sürecinde uzun süre takılma gibi bazı sınırlamaları vardır. Bu çalışmada, Göğüs Kanseri Wisconsin veri kümesinde göğüs kanseri hastalığının teşhisi için, sezgisel ateş böceği algoritması tarafından desteklenen aşırı öğrenme  makinesi (AB–AÖM) önerilmiştir. Önerilen AB–AÖM’nin hastalık tanı üzerindeki performansı standart AÖM ve GY–ANN yöntemleriyle karşılaştırıldı. Sonuçlar, AB–AÖM’nin sınıflandırma performansıyla ilgili anlamlı bir gelişme sağladığını ve tıbbi problemler için güçlü bir teknik olarak kullanılabileceğini göstermektedir.

Anahtar Kelimeler

• Aşırı Öğrenme Makineleri,Ateş Böceği Algoritması,Göğüs Kanseri,Tıbbi Karar Destek Sistemleri

Kaynakça

1. Subashini, T. S.; Ramalingam, V.; Palanivel, S., “Breast mass classification based on cytological patterns using RBFNN and SVM”, Expert Syst. Appl., 2009, 36 (3): 5284–5290.
2. The American Cancer Society, What is Breast Cancer.
3. Akay, M. F., “Support vector machines combined with feature selection for breast cancer diagnosis”, Expert Syst. Appl., 2009, 36(2), 3240–3247.
4. West, D.; Mangiameli, P.; Rampal, R.; West, V., “Ensemble strategies for a medical diagnostic decision support system: A breast cancer diagnosis application”, Eur. J. Oper. Res., 2005, 162(2), 532–551.
5. Brause, R. W., “Medical Analysis and Diagnosis by Neural Networks”, In Proceeding ISMDA’01 Proceedings of the Second International Symposium on Medical Data Analysis, Madrid, Spain, 1–13, 2001.
6. P. Kshirsagar; N. Rathod, “Artificial neural network”, International Journal of Computer Applications, 2012, NCRTC(2), 12–16.
7. N. Gupta, “Artificial neural network”, Network and Complex Systems, 2013, 3(1), 24 – 28.
8. Huang, G.-B.; Chen, L., “Convex incremental extreme learning machine.”, Neurocomputing, 2007,70(16), 3056-3062.

9. Huang, G.-B.; Chen, L., “Enhanced random search based incremental extreme learning machine.”, Neurocomputing, 2008, 71(16), 3460-3468.
10. Huang, G.-B.; Chen, L.; Siew, C. K., Universal approximation using incremental constructive feedforward networks with random hidden nodes., IEEE Trans. Neural Networks, 2006, 17(4), 879-892.
11. Liu, X.; Lin, S.; Fang, J.; Xu, Z., “Is extreme learning machine feasible? A theoretical assessment (Part I). IEEE Transactions on Neural Networks and Learning Systems, 2015, 26(1), 7-20.
12. Huang, G.-B.; Zhou, H.; Ding X., Zhang R., “Extreme learning machine for regression and multiclass classification”, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2012, 42(2), 513-529.
13. Suykens, J. A.; Vandewalle, J., “Least squares support vector machine classifiers. Neural processing letters”, 1999, 9(3), 293-300.
14. Cortes, C.; Vapnik, V., “Support vector machine”, Machine learning, 1995, 20(3), 273-297.
15. Abdolmaleki, P.; Buadu, L.D.; Naderimanesh, H., “Feature extraction and classification of breast cancer on dynamic magnetic resonance imaging using artificial neural network”, Elsevier, Cancer Letters, 2001, 171 (2), 183-191.
16. Fogel, D. B.; Wasson, E.C.; Boughton, E.M.; Porto, V.W., “A step toward computer assisted mammography using evolutionary programming and neural Networks”, Cancer Letters, 1997, 119(1), 93-97.
17. Revett, K.; Gorunescu, F.; Gorunescu, M.; El-Darzı E.; Ene, M., “A breast cancer diagnosis system: a combined approach using rough sets and probabilistic neural Networks”, Computer as a tool Eurocon 2005, Belgrade, 2005, 1124- 1127.
18. Gorunescu, M.; Gorunescu, F.; Revett, K., “Investigating a Breast Cancer Dataset Using a Combined Approach: Probabilistic Neural Networks and Rough Sets”, Proc. 3rd ACM International Conference on Intelligent Computing and Information Systems -ICICIS07, Cairo, Egypt, , 246-249, 2007.
19. Hsiao, Y.H.; Huang, Y.L.; Liang, W.M.; Kuo S.J.; Chen D.R., “Characterization of benign and malignant solid breast masses: harmonic versus nonharmonic 3D power Doppler imaging”, Ultrasound Medicine & Biology, 2009, 35 (3), 353-359.
20. Karapınar Şentürk, Z.; Şentürk, A., “Neural Networks with Breast Cancer Forecast”, El-Cezerî Journal of Science and Engineering, 2016, 3(2), 345-350.
21. Prasetyo Utomo, C.; Kardiana, A.; Yuliwulandari, R., “Breast Cancer Diagnosis using Artificial Neural Networks with Extreme Learning Techniques”, International Journal of Advanced Research in Artificial Intelligence, 2014, 3(7), 10-14.
22. Wolberg, W. H.; Mangasarian, O. L., “Multisurface method of pattern separation for medical diagnosis applied to breast cytology”, in Proceedings of the National Academy of Sciences, U.S.A., 87, 9193–9196, 1990.
23. Yang, X.S., Nature-Inspired Metaheuristic Algorithms, Luniver Press, London, 2008.
24. Yang, X. S., “Firefly algorithms for multimodal optimization”, Stochastic Algorithms: Foundations and Applications, SAGA, Lecture Notes in Computer Sciences 5792, 169–178, 2009.
25. Łukasik, S.; Żak, S., “Firefly algorithm for continuous constrained optimization task”, Computational Collective Intelligence. Semantic Web, Social Networks and Multiagent Systems LNCS 5796, 97–106, 2009.
26. Melamud, E.; Moult, J., “Evaluation of Disorder Predictions” in CASP5. Proteins 53:561–565, 2003.
27. Yang, R. Z.; Thomso, R.; Mcneil, P.; Esnouf, R. M., “RONN: The bio-basis function neural network technique applied to the detection of natively disordered regions in proteins”, Bioinformatics, 2005, 21, 3369–3376.