RCPS: Rectified Contrastive Pseudo Supervision for Semi-Supervised Medical Image Segmentation

Abstract

Medical image segmentation methods are generally designed as fully-supervised to guarantee model performance, which require a significant amount of expert annotated samples that are high-cost and laborious. Semi-supervised image segmentation can alleviate the problem by utilizing a large number of unlabeled images along with limited labeled images. However, learning a robust representation from numerous unlabeled images remains challenging due to potential noise in pseudo labels and insufficient class separability in feature space, which undermines the performance of current semi-supervised segmentation approaches. To address the issues above, we propose a novel semi-supervised segmentation method named as Rectified Contrastive Pseudo Supervision (RCPS), which combines a rectified pseudo supervision and voxel-level contrastive learning to improve the effectiveness of semi-supervised segmentation. Particularly, we design a novel rectification strategy for the pseudo supervision method based on uncertainty estimation and consistency regularization to reduce the noise influence in pseudo labels. Furthermore, we introduce a bidirectional voxel contrastive loss to the network to ensure intra-class consistency and inter-class contrast in feature space, which increases class separability in the segmentation. The proposed RCPS segmentation method has been validated on two public datasets and an in-house clinical dataset. Experimental results reveal that the proposed method yields better segmentation performance compared with the state-of-the-art methods in semi-supervised medical image segmentation. The source code is available at https://github.com/hsiangyuzhao/RCPS.

Semi-Supervised Medical Image Classification Combined with Unsupervised Deep Clustering

“…In the field of medical image segmentation, Zhao et al proposed a pseudo supervision method based on consistency regularization and uncertainty evaluation [29], which reduced the influence of the potential noise of pseudo-labels on segmentation results in semi-supervised learning. Dong et al [30] proposed an unsupervised domain adaptive framework based on an antagonistic network, and applied it to semi-supervised learning on the JSRT (Japanese Society of Radiological Technology) datasets.…”

Self-supervised segmentation and characterization of fiber bundles in anatomic tracing data

“…Semi-/self-supervised methods have been shown to work well on generic noisy data and limited labels with uncertainties (Dinsdale et al, 2022;Chen et al, 2020;Feyjie et al, 2020;Perone et al, 2019;Sundaresan et al, 2022;Fischer et al, 2023;Du et al, 2023). In particular, contrastive learning, which aims to learn image features that are similar or different between segmentation classes (Chen et al, 2020;Zhao et al, 2023), has been used to segment histopathological images (Wu et al, 2022;Lai et al, 2021). Similarly, perturbationbased self-ensembling and temporal ensembling, where average predictions from prior epochs are used as pseudo-labels for training the current epoch (Li et al, 2020;Perone et al, 2019), have been shown to perform well in segmentation tasks with minimal manual annotations for training.…”