Skin Lesion Segmentation Combining Boundary Enhancement and Multi-scale Attention

Abstract

In view of the various types of skin lesions in shape,color and size,which pose a huge challenge to the accurate segmentation of skin lesions,a skin lesion segmentation network that combines boundary enhancement and multi-scale attention is proposed(BEMA U-Net).It consists of two modules,one is called spatial multi-scale attention module,which is used to extract spatial global features,and the other is called boundary enhancement module,which is used to enhance the edge features of the lesion area.BEMA U-Net adds the two modules to the U-Net network with encoding and decoding structure,which can effectively suppress the interference of background noise in the image of lesions and enhance the edge details of lesions.In addition,the mixed loss function is designed,Dice loss and Boundary loss are combined,and the dynamic weight adjustment of the mixed loss function is realized in the training process,so that the network could carry out multiple supervision on the extraction of the overall features and edge details of the pathological images,and the problems of hair interference and edge blur in the segmentation of skin pathological images are alleviated.Experimental results on ISIC2017 and ISIC2018 public data sets show that the proposed algorithm has better segmentation effect for skin lesions with continuous edges and clear contours.

Keywords

• skin lesion segmentation|spatial multi-scale attention|global feature|boundary enhancement|u-net