Investigation of the eczema and skin cancer disease diagnosis by using image processing techniques

Abstract

It is seen that many diseases, especially dermatological diseases, arise due to bad weather conditions such as high temperature, dust, smoke, and sun in the environment. The most common diseases are eczema caused by malnutrition, soil, bacteria, bad food, and other factors, and risky moles, which are usually caused by excessive sunlight or during childbirth. Due to all these environmental, physiological, and chemical factors, it is important to quickly detect all existing skin diseases, especially eczema and risky moles, and it has become inevitable to establish a less costly diagnostic system with the help of doctors to prevent the aggravation of the diseases. If eczema and risky skin problems progress, they will be difficult to treat and take a long time. For this reason, the research aims to take an image from the infection site and then process this image in many ways in a MATLAB environment to obtain an output that can help doctors in their work. Differently, in this study, diseases were classified by the decision tree method using the clinical data of the related image. In addition, it is seen that it is determined in normal depth together with the idea developed originally. Decision trees supported the currently used image processing and classification method, and the results of both methods are also compared with this method. According to the results obtained, the accuracy, sensitivity, and selectivity ratios of decision trees are obtained compared to image processing. The software used gives a warning when the image processing and decision tree methods give conflicting results. If this occurs, it is necessary to stick to the doctor's data. The system in this study aims to improve human life and make it safe by recognizing eczema and risky moles. In this study, samples were selected from various layers of the body. In addition, a different interpretation can be made in the normal situation. When this approach technique is applied, more appropriate results have emerged in the process of detecting eczema and risky moles. In addition, normal skin is also involved in the process. Being able to define the normal state has been a contribution to science and it is aimed in this study to facilitate the work of medical personnel.

Keywords

• eczama
• MATLAB
• image processing
• skin disease
• skin cancer
• decision trees

References

1. Reference1 Kaplan, M. Implementation of an Auxiliary System for the Diagnosis of Skin Diseases Using Artificial Neural Networks, TC Fırat University, Institute of Science, Master Thesis, 2016.
2. Reference2 Season, V. (2010). Epidemiology of dermatological diseases, disease burden, and place in primary care. Turkey Clinics J. Fam Md-Special Topics, 2010; 1(2): 15-20.
3. Reference3 Alonso, DH., Wernick, MN., Yang, Y., Germano, G., Berman, DS., Slmoka, P. Prediction of cardiac death after adenosine myocardial perfusion SPECT based on machine learning. J Nucl Cardiol. https://doi.org/10.1007/s12350-017-0924-x, 2018.
4. Reference4 Narula, S., Shameer, K., Salem Omar, AM., Dudley, JT., Sengupta, PP. Reply Deep learning with unsupervised features in echocardiographic imaging. J Am Coll Cardiol; 2017, 69: 2101–2.
5. Reference5 Esteva, A., Kupre, B., Novoa, RA., et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature, 2017, 542:115–8.
6. Reference6 Cichosz, SL., Johansen, MD., Hejlesen, O. Toward big data analytics: a review of predictive models in the management of es and its complications. J es Sci Technol, 2015, 10(1):27-34.
7. Reference7 Tran, BX,. Latkin, CA., Giang, VT., et al., The Current Research Landscape of the Application of Artificial Intelligence in Managing Cerebrovascular and Heart Diseases: A Bibliometric and Content Analysis. Int. J. Environ. Res. Public Health, 2019, 16:2699.
8. Reference8 Char, DS., Shah, NH., Magnus, D. Implementing Machine Learning in Health Care, Addressing Ethical Challenges. N. Engl. J. Med., 2018, 378: 981–983.

9. Reference9 Celebi, V., Inal, A. Problem of Ethics in the Context of Artificial Intelligence. The Journal of International Social Research, 2019, 12, 66.
10. Reference10 Mujumdar, A., Vaidehi, V. Dibetes Prediction Using Machine Learning Algorithms. Procedia Computer Science, 2019, 165: 292–299.
11. Reference11 Farid,D., Sadeghi,H., Hajigol,E. ve Parirooy,N. Classification of Bank Customers by Data Mining: a Case Study of Mellat Bank branches in Shiraz, International Journal of Management Accounting and Economics, 2016, 3: 534-543.
12. Reference12 Walsh, S. Applying Data Mining Techniques Using SAS® Enterprise Miner- Course Notes, SAS Institute Inc., North Carolina, 2005.
13. Reference13 Pratt, W. K., Digital Image Processing. USA: John Wiley & Sons, 2007.
14. Reference14 Nixon, M. S., Aguado, A. S., Feature Extraction, and Image Processing. Newnes, UK, 2002.
15. Reference15 Kaur, H., Kumari, V. Predictive modeling, and analytics for diabetes using a machine learning approach. Applied Computing and Informatics https://doi.org/10.1016/j.aci.2018.12.004, 2018.
16. Reference16 Kavakiotis, I. et al. Machine Learning and Data Mining Methods in Diabetes Research. Computational and Structural Biotechnology, 2017, 15: 104–116.
17. Reference17 Araújo F.H.D. et al. Using machine learning to support healthcare professionals in making preauthorization decisions. International Journal of Medical Informatics, 2016, 94:1–7.
18. Reference18 Parikh, R.B., Kakad, M., Bates, DW. Integrating predictive analytics into high-value care: the dawn of precision delivery. JAMA, 2016, 315: 651-652.
19. Reference19 Bates, DW., Saria, S., Ohno-Machado, L., Shah, A., Escobar, G. Big data in healthcare: using analytics to identify and manage high-risk and high-cost patients. Health Aff, 2014, 33: 1123-1131.
20. Reference20 Mercaldo, F., Nardone, V., Santone, A. Diabetes Mellitus Affected Patients Classification and Diagnosis through Machine Learning Techniques. Procedia Computer Science, 2017, 112: 2519-228.
21. Reference21 Al-Khafaji, Muallah, S. K., Ibraheem, M. R. Detection of Eczema DISEASE by using Image Processing. The Eurasia Proceedings of Science, Engineering & Mathematics (EPSTEM), 2018, Volume 2: 2602–3199.
22. Reference22 Acıbadem Web and Medical Editorial Board. Skin (Skin) Cancer. Acıbadem Healthcare Group. 2019, from https://www.acibadem.com.tr/ilgi-alani/cilt-deri-kanseri/#signs
23. Reference23 Al Shahibi, I. S. S., Koottala, S., Detection of Skin Diseases Using Matlab. Journal of Student Research Fourth Middle East College Student Research Conference, Muscat, Sultanate of Oman, 2020.
24. Reference24 Mathworks Help Center, Retrieved December 6, 2021, from https://www.mathworks.com/help/stats/fitcecoc.html
25. Reference25 https://atozmath.com/example/CONM/Bisection.aspx?he=e&q=it
26. Reference26 Houcque D., Introduction To MATLAB For Engineering Students, https://www.mccormick.northwestern.edu/documents/students/undergraduate/introduction-to-matlab.pdf, 2005.
27. Reference27 Kumar, B., Rai, S.P., Saravana Kumar, U., Verma, S.K., Garg, Pankaj K., Vijaya Kumar, S.V., Jaiswal, R., Purendera, B.K., Kumar, S.R. and Pande, N.G. Isotopic characteristics of Indian Precipitation. Published online in Water Resources Research, 2010, Vol. 46, DOI: 10.1029/2009WRSR008532, 2010.
28. Reference28 Yurtay, N., Adak, M. F., Dural, D., Serttaş. S. A study on use of decision tree method in the diagnosis of thyroid disease. International Science and Technology Conference, Retrieved 28 November 2021. Published, 2012.
29. Reference29 "Dermatitis" defined, Suzanne Smith, Susan Nedorost, 2012.
30. Reference30 MathWorks Help Center, Retrieved December 6, 2021, from https://www.mathworks.com/help/stats/fitcecoc.html
31. Reference31 Image Texture Feature Extraction Using GLCM Approach, P. Mohanaiah, P. Sathyanarayana, L. GuruKumar, 2013.
32. Reference32 Data Scientist Website, Retrieved December 12, 2021, from https://veribilimcisi.com/2017/07/19/destek-vektor-makineleri-support-vector-machine/
33. Reference33 https://www.researchgate.net/publication/221608588
34. Reference34 Yurtay, N. Data Mining Applications Lecture Notes, Week 4, Sakarya University, Retrieved 06 December 2021.