Cross Image Feature Perturbation with Pseudo Label Fusion for Semi-Supervised Medical Image Segmentation

Semi-supervised medical image segmentation aims to leverage a limited set of labeled images alongside a substantial volume of unlabeled images to train semantic segmentation models. Existing studies often employ consistency regularization to maximize the utilization of unlabeled data, thereby enhancing the model's robustness and accuracy. However, the methods for constructing perturbations at image-level on unlabeled data are typically simplistic, involving techniques such as color transformations, additive noise, which do not adequately leverage the precise and reliable supervisory information available from labeled images. To address this limitation, in addition to image perturbation, we propose a cross-image feature perturbation approach for semi-supervised medical image segmentation. This method utilizes feature information from labeled images to guide the refinement of ambiguous semantic representations in unlabeled images, thereby expanding the perturbation space more effectively. Moreover, recognizing the limitations of existing consistency regularization frameworks that rely on confidence thresholds to filter pseudo-labels, we introduce an uncertainty-based pseudo-label fusion strategy. This strategy mitigates the effects of unreliable predictions caused by perturbations by calculating the uncertainty and using it as a weight during pseudo-label fusion. We have conducted extensive experiments on the 2D ACDC and 3D LA datasets. The results demonstrate that our approach achieves performance comparable to the current state-of-the-art (SOTA) methods.