Semi-supervised segmentation for 3D medical image based on contrast learning

Semi-supervised segmentation, using large amounts of unlabeled data and small amounts of labeled data, has achieved great success. This paper proposes a semi-supervised segmentation method based on consistent learning and contrast learning. It mainly uses a mean-teacher framework to add consistency losses and contrast losses based on multiscale features to minimize the distance of model responses under different disturbance inputs. In addition, mean square error loss was used to alternately minimize the gap between the teacher and student models. In 3D left atrium data, a Dice coeffivient of 0.8970 was obtained, which was superior to other methods.