Classification of melanoma from Dermoscopic data using machine learning techniques

Skin Lesions Classification Using Deep Learning Techniques: Review

“…In the proposed skin lesion classification methods, different algorithms and techniques are utilized to enhancement the detection and classification accuracy of the models. Through Table 1 there are some authors use preprocessing methods to enhance the image before classification stages [72,78,81], like removal hair and the line also standardization brightness unbalanced and in [76], using anisotropic diffusion filter and unsharp masking is intended to remove the visual noise such as lines and edges and improve the image information for feature extraction methods usually based on convolution neural network to extract the most [81] to generate high-level features based on combining stacked convolutional neural networks in order to extract important discrimination features. ABCD rule is preferred for checking skin diseases worldwide as a common reference, [83] proposed ABCD for extracting the features like Asymmetry, Border, and Color features, as well as the diameter.…”

“…While other reviewed skin lesion classification methods were based on Optimized neutrosophic k-means (ONKM) in [74] Genetic algorithm for optimizing the value of α in α-mean operation in the neutrosophic set. Also, adaptive k-means and Random Fores in [76], Multiclass SVM in [77,78,91], SVM, ANN, KNN, and TDV in [83]. A buzzard optimization function extraction algorithm and SVM classifier provides accuracy 94.3% and the buzzard optimization for feature extraction is awesome.…”

“…A comparative study is discussed in this proposed work [76] to identify the melanoma category with supervised machine learning algorithms. The classification of dermoscopic image melanoma is suggested to assist the clinical use of dermatoscopy imaging methods for the classification of skin sores.…”

Optical Technologies for the Improvement of Skin Cancer Diagnosis: A Review

“…The ML process initially requires segmenting the lesion from the surrounding skin to isolate it; this might be critical, because in some cases, there is not a clear boundary limiting the lesion. Some of the segmentation algorithms used are built from Otsu’s thresholding, k-means, fuzzy c-means, and neural networks [ 108 , 109 ]. Most of ML approaches try to reproduce physicians’ assessments, the well-known ABCDE rule, and because of that, the next step consists in feature extraction of morphological (e.g.…”

“…There is not an ideal classification algorithm that outperforms the others as it depends on the dataset, image segmentation, and feature extraction (see Figure 9 ); however, in the literature, some of them have been found to provide better discrimination among skin lesions. Support Vector Machine (SVM) is the most applied classifier, as it shows the best performance [ 107 , 109 , 110 , 111 , 112 , 114 , 115 , 116 , 117 , 118 ] followed by k-Nearest Neighbors (KNN) [ 65 , 106 , 107 , 108 , 109 , 110 , 111 , 116 , 117 , 118 ], Neural Networks (NN) [ 110 , 114 , 115 , 117 , 119 ], Random Forest (RF) [ 107 , 109 , 113 , 114 ] and Decision Trees (DT) [ 65 , 109 , 110 , 111 , 117 , 118 ]. SVMs are based on statistics to build hyperplanes that maximize the distance between sets of data points [ 120 , 121 ].…”