Medical image is a powerful tool to assist doctors in the diagnosis and treatment planning.Nowadays,the segmentation of medical images is no longer limited to manual segmentation methods.Traditional methods and deep learning methods have been used to achieve more accurate results in medical image segmentation.Herein some innovative medical image segmentation methods in recent years are reviewed.By elaborating on the innovations of deep learning methods(SAM,SegNet,Mask R-CNN,and U-NET)and traditional methods(active contour model and threshold segmentation model),the differences and similarities between them are compared.The summary of medical image segmentation methods and the prospect is expected to help researchers better grasp and familiarize themselves with research status and development trend.

Medical images can provide clinicans with accurate and comprehensive patients’ information. Morphological or functional abnormalities caused by various diseases can be manifested in many aspects. Although MR images and CT images can highlight the medical image data of different tissue structures of patients, single MR images or CT images cannot fully reflect the complexity of diseases. Using MR image to predict CT image is one of the cross-modal prediction of medical images. In this paper, the methods of MR image prediction for CTmage are classified into four categoriesincluding registration based on atlas, based on image segmentationmethod, based on learning method and based on deep learning method. In our research, we concluded that the method based on deep learning should bemore promoted in the future by compering the existing problems and future development of MR image predicting CT image method.