U-Net-RCB7: Image Segmentation Algorithm

The incidence of skin cancer is increasing. Early detection cases vital for treatment. Recently, computerized methods have been widely used in diagnosis. These important advantages such as no human error, short diagnosis time, and low cost. We can segment images using deep learning image processing. Properly segmented help doctors predict the type cancer. However, contain noise hair. noises affect accuracy segmentation. In our study, we created a dataset. It contains 3000 masks. performed removal lesion segmentation by utilizing ISIC PH2. developed new model called U-Net-RCB7. U-Net-RCB7 EfficientNetB7 encoder ResNetC before last layer. This paper uses modified U-Net model. Images were divided into 36 layers to prevent loss pixel values images. As result, 96% 98.36% successful, respectively.