U-Net-RCB7: Image Segmentation Algorithm

Abstract

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