- Journal of Investigations on Engineering and Technology
- Vol: 5 Issue: 1
- Investigation of the eczema and skin cancer disease diagnosis by using image processing techniques
Investigation of the eczema and skin cancer disease diagnosis by using image processing techniques
Authors : Yusuf Süer Erdem, Özhan Özkan
Pages : 47-62
View : 12 | Download : 5
Publication Date : 2022-06-30
Article Type : Research
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