MACHINE LEARNING TECHNIQUES IN SKIN TUMOR IDENTIFICATION
DOI:
https://doi.org/10.65405/wpfjys47Keywords:
skin tumor, benign, malignant, Malignancy; machine learning; classification system; backpropagation neural network, Gaussian filtering, and image opening, radial basis function network.Abstract
Recently, artificial intelligence started to invade medicine in its entire fields: diagnosis and therapy. Artificial intelligence can be a key part in the diagnostic medicine field for easy, fast, and accurate diagnosis of diseases. Thus, machine learning systems or so called intelligent systems that takes on the unpracticed physicians’ job are in urgent need. In this paper, we present the use of two different intelligent systems for the skin tumor classification system. The approach is based on both image processing techniques and artificial intelligence tools such as backpropagation and Radial basis function neural networks. The main aim of this study is to investigate the best performance and accuracy in such medical classification application between the both used networks. Moreover, in this work we propose a simple image processing algorithm for segmenting the skin tumor from images using simple and fast techniques such as Gaussian filtering and image opening. Upon processing and rescaling the images are fed to both networks to be trained and tested and accuracy, training time, and error were calculated. Experimentally, both networks succeeded in generalizing the correct classification results of the unseen skin tumor images but with different rates, accuracies, and errors. As a result, it was found that a radial basis function network outperforms the backpropagation network in terms of accuracy, training time, and minimum square error achieved.
Downloads
References
1-Donaldson, M.R. and Coldiron, B.M. (2011). No end in sight: the skin cancer epidemic continues. Seminars in cutaneous medicine and surgery, 30(1), pp. 3–5.
2-Ekwueme, D.U. Guy, G.P. Li, C. Rim, S.H. Parelkar, P. and Chen, S.C. (2011). The health burden and economic costs of cutaneous melanoma mortality by race/ethnicity-United States, 2000 to 2006. Journal of the American Academy of Dermatology, 65(5 Suppl 1):S133–43.
3-P. Sermanet, D. Eigen, X. Zhang, M. Mathieu, R. Fergus, and Y. LeCun. OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks. arXiv.org, Dec. 2013.
4-Simonyan, K. and Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv.org.
5-Ma, L. and Stauton, R.C. (2013). Analysis of the contour structural irregularity of skin lesion using wavelet decomposition,” Pattern recognition, vol. 46, pp. 98–106.
6-Fan, Y., Jiang, T., and Evans, D. J. (2002). Volumetric segmentation of brain images using parallel genetic algorithms. IEEE Transactions on Medical Imaging, 21(8), 904 – 909.
7-Gonzalez R.C., Woods R.E. (2001) Digital Image Processing. New York: CRC Presss.
8-Wallace, S., Vaclav H., ,Roger B. (1998). Image Processing Analysis, and Machine Vision. 2nd Edition. Pws Publishing.
9-Rao, K.M.M., Rao, V.D.P., (2014). Medical Image Processing. In the proceeding of Image Analysis and Interpretation (SSIAI), IEEE Southwest Symposium (p.p 6-8). India: Indian Institute of Science.
10-Khashman, A. (2011). Credit risk evaluation using neural networks: Emotional versus conventional models. Applied Soft Computing, 11(8), 5477-5484.
11-Caruana, R., & Niculescu-Mizil, A. (2006, June). An empirical comparison of supervised learning algorithms. In Proceedings of the 23rd international conference on Machine learning (pp. 161-168). ACM.
12-Amr Radi and Samy K. Hindawi (2013). Applying Artificial Neural Network Hadron - Hadron Collisions at LHC, Artificial Neural Networks - Architectures and Applications, Prof. Kenji Suzuki (Ed.), InTech, DOI: 10.5772/51273
13- Sathya, R., & Abraham, A. (2013). Comparison of supervised and unsupervised learning algorithms for pattern classification. Int J Adv Res Artificial Intell, 2(2), 34-38.
14-Gosavi, A. (2009). Reinforcement learning: A tutorial survey and recent advances. INFORMS Journal on Computing, 21(2), 178-192.
15- Eluyode, O. S., Akomolafe, D. T., & MNCS, M. (2013). Comparative study of biological and artificial neural networks. European Journal of Applied Engineering and Scientific Research, 2(1).
16-Strumiłło P, Kamiński W. Radial basis function neural networks: theory and applications. Neural Networks and Soft Computing - Advances in Soft Computing. 2003; 19: 107-11917
17-Garg S, Patra K, Pal SK, Chakraborty D. Effect of different basis functions on a radial basis function network in prediction of drill flank wear from motor current signals. Soft Computing. 2008; 12(8): 777-787.
18-Bose N, Liang P. Neural network fundamentals with graphs, algorithms and applications. McGraw-Hill, Inc.; 1996.
19-McCulloch, W.S. and Pitts, W., 1943. A logical calculus of the ideas immanent in nervous activity. The bulletin of mathematical biophysics, 5(4), pp.115-133.
20-Hebb, D.O., 2005. The organization of behavior: A neuropsychological theory. Psychology Press.
21-Graupe, D., 2013. Principles of artificial neural networks (Vol. 7). World Scientific.
22-Abdi, H., Valentin, D., Edelman, B. and O'Toole, A.J., 1996. A Widrow–Hoff learning rule for a generalization of the linear auto-associator. Journal of Mathematical Psychology, 40(2), pp.175-182.
23-Zurada, J.M., 1992. Introduction to artificial neural systems (Vol. 8). St. Paul: West publishing company.
24-Krenker, A., Kos, A. and Bešter, J., 2011. Introduction to the artificial neural networks. INTECH Open Access Publisher.
25-Beham, M. P., & Gurulakshmi, A. B. (2012). Morphological image processing approach on the detection of tumor and cancer cells. In Proceeding of Devices, Circuits and Systems International Conference on (pp. 350-354). Italy: University of Bologna.
26-Wang, Y., Chen, Q., & Zhang, B. (1999). Image enhancement based on equal area dualistic sub-image histogram equalization method. IEEE Transactions on Consumer Electronics, 45(1), 68-75.
27-James Church, Dr. Yixin Chen, and Dr. Stephen Rice (2008), “A Spatial Median Filter for Noise Removal in Digital Images”. Southeastcon. IEEE, p.p.618 – 623.
28-Gonzalez and Woods, Digital Image Processing, Second Edition, PrenticeHall, pp. 108-120, 2002.
29-R.Radha and Bijee Lakshman, “Retinal Image Analysis Using Morphological Process and Clustering Technique”. Signal & Image Processing: An International Journal (SIPIJ) Vol.4, No.6, December 2013.
30-Ankit Aggarwal, R.S. Chauhan and Kamaljeet Kaur (2013),”An Adaptive Image Enhancement Technique Preserving Brightness Level Using Gamma Correction”. Advance in Electronic and Electric Engineering, Volume 3, Number 9 (2013), pp. 1097-1108.
31-Haar, A. "Zur Theorie der orthogonalen Funktionensysteme." Math. Ann. 69, 331-371, 1910.
32-Sonka M., Hlavac V., Boyle R.: Image processing, Analysis and Machine Vision. Brooks/Cole Publishing Comp.1999.
33-Michael Negnevitsky, 2005. Artificial Intelligence: A Guide to Intelligent Systems, Second Edition. pp.167.
34-WG. Baxt, 1995. “Application of artificial neural networks to clinical medicine” Lancet. vol. 346 (8983), pp. 1135-1138.
35-L. Deng, “An Overview of Deep-Structured Learning for Information Processing,” Asia-Pacific Signal and Information Processing Association: Annual Summit and Conference, 2014, pp.2-4.
36-D. Erhan at el, “Why Does Unsupervised Pre-training Help Deep Learning?,” Vol. 9 of JMLR: W&CP 9, pp.1-5 [13th International Conference on Artificial Intelligence and Statistics (AISTATS) 2010, Chia Laguna Resort, Sardinia, Italy.
37-R. Rojas, (1996). Neural Networks: a systematic introduction, Springer-Verlag.Davis.
38- Tariq Alnnale. (2026).Predictive Governance in Digital Enterprises: An LSTM- Enhanced Deep Learning Framework for Economic Optimization of IT Incident Management Using Enriched Process Logs.DOI: https://doi.org/10.65405/dctw1z34.
39-Nabeel Al-Milli, 2013. A backpropogation neural network for prediction of heart disease. Journal of Theoretical and Applied Information Technology, vol.56, no.1, pp. 131-135.
