Efficient Semi-supervised Multi-organ Segmentation Using Uncertainty Rectified Pyramid Consistency

To meet the problems that great dependence on fully annotated data and spatio-temporal inefficiency of remaining automatic multi-organ segmentation methods, an efficient semi-supervised framework with uncertainty rectified pyramid consistency regularization is introduced. Specifically, inspired by the fact that the predictions of the same input should be similar under different disturbance, this work uses an extending backbone to produce different-scale predictions for unlabeled images and encourage them to be consistent. In order to avoid lost of fine detail or model collapse when directly encouraging the multiscale predictions to be consistent, a rectified scale-level uncertainty-aware module is introduced to enable the framework to gradually learn from reliable prediction regions. To deal with the domain gaps among multicenter datasets, a number of prepocessing methods are utilized, such as resampling the multi-center CT volumes to the same spacing and adjusting the window level and width. Quantitative evaluation on the FLARE2022 20 validation cases given the labels, this method achieves the average dice similarity coefficient (DSC) of 0.793 and average normalized surface distance (NSD) of 0.852.