Melanoma skin cancer detection based on deep learning methods and binary Harris Hawk optimization

In this thesis, we present a robust method for skin melanoma cancer detection as melanoma and non-melanoma. The proposed method for the melanoma skin cancer divided into three steps. The convolutional neural network is used to extract the features of the images in the first step. For convolutional neural network the googLeNet and residual network are used. The extracted features are huge and for training of the system these number of features cannot be successful, for this reason in second step the metaheuristic method is used to reduce the number of features. In this study the Harris hawks optimization is used to select the best features from the feature data. Finally, with machine learning methods the melanoma skin cancer was diagnosed. Three classification methods are employed to assess of the proposed method. These methods were decision tree, support vector machine, and KNN method. The data that we used, obtained from the GitHub and Kaggle database. Finally, we compared the proposed classification method results with other methods and we show that our results have good performance than the other methods. The code was implemented on ISIC 2016, ISIC 2017 and ISIC 2019 database with MATLAB 2021a.