Skin-Net: a novel deep residual network for skin lesions classification using multilevel feature extraction and cross-channel correlation with detection of outlier

Abstract Human Skin cancer is commonly detected visually through clinical screening followed by a dermoscopic examination. However, automated skin lesion classification remains challenging due to the visual similarities between benign and melanoma lesions. In this work, authors proposed new Artificial Intelligence-Based method classify method, we used Residual Deep Convolution Neural Network. We implemented several convolution filters for multi-layer feature extraction cross-channel correlation sliding dot product instead of along horizontal axis. The overcomes imbalanced dataset problem converting from image label vector weight. tested evaluated using datasets ISIC-2019 & ISIC-2020. It outperformed existing deep convolutional networks in multiclass Graphical