Comparison Feed Forward Back Propagation Networks (FFBPNs) with Support Vector Machine (SVM) for Diagnosis of Skin Cancer Based on Images

Skin cancer is a type of malignancy responsible for 70 percent of overall skin cancer-related death worldwide. In previous years, doctors relied on visual examination to identify suspicious pigmented lesions that could indicate skin cancer. The purpose of the research: Uses of AI include detecting skin cancer of all types more quickly and improving the efficiency of diagnostic radiology, which will reduce the rate of inaccurate diagnosis of cancer and diagnose skin cancer more accurately by dermatologists. The method used in this paper is artificial neural network technology implemented for detecting skin cancer and the watershed segmentation method for segmentation. The features extraction for an extracted segment. The features extracted are shaped and Gray-Level Co-Occurrence Matrix. The extracted feature is used for classification. The classifiers are Support Vector Machine and Feed forward Back Propagation applied in Matlab enivermental and an image processing technique on a set of photographs collected from several websites, including the Kaggle web. The implementation of code for the detection of skin cancer by using data as 100 images 50 no cancer and 50 is cancer; the result shows successful implementation for the detection of cancer in FFBP classifiers 45 and 2 is bad detection, as well as in SVM classifier 49 with 1 is bad diagnostic. The conclusion shows that the SVM classifier provides results for the classification of skin lesions with 98% accuracy and an FFBP of 96 %. The conclusion of this study is helping people with skin cancer undergo a CT scan.