Skin Lesion Segmentation Based on Mask R-CNN

Dermatological segmentation has always been a hot topic in medical imaging. At present, many algorithms have achieved good results in the segmentation of skin diseases, such as super-pixel segmentation and U-Net network. The method we used in this paper is improved based on the instance segmentation model, Mask R-CNN. Firstly, we have trained the classification branch in Mask R-CNN in advanced. Secondly, we made some adjustments to the parameters of Mask R-CNN. These two changes ensure that our method has higher segmentation accuracy and detection accuracy than traditional Mask R-CNN. The data set used in this paper comes from ISIC (International Skin Imaging Collaboration). Experiment results demonstrate that the segmentation effect of our method on skin lesion images is better than the traditional Mask R-CNN.