Leveraging Fixed and Dynamic Pseudo-labels for Semi-supervised Medical Image Segmentation

TL;DR

This paper introduces a semi-supervised medical image segmentation method that uses both fixed and dynamic pseudo-labels within a co-training framework, leading to improved accuracy and robustness over existing methods.

Contribution

The paper proposes a novel approach utilizing multiple pseudo-labels, including a dynamic one, to enhance semi-supervised segmentation performance.

Findings

Outperforms state-of-the-art methods on three benchmark datasets.

Improves model robustness and generalization with multiple pseudo-labels.

Effective across various labeled data ratios.

Abstract

Semi-supervised medical image segmentation has gained growing interest due to its ability to utilize unannotated data. The current state-of-the-art methods mostly rely on pseudo-labeling within a co-training framework. These methods depend on a single pseudo-label for training, but these labels are not as accurate as the ground truth of labeled data. Relying solely on one pseudo-label often results in suboptimal results. To this end, we propose a novel approach where multiple pseudo-labels for the same unannotated image are used to learn from the unlabeled data: the conventional fixed pseudo-label and the newly introduced dynamic pseudo-label. By incorporating multiple pseudo-labels for the same unannotated image into the co-training framework, our approach provides a more robust training approach that improves model performance and generalization capabilities. We validate our novel approach on three semi-supervised medical benchmark segmentation datasets, the Left Atrium dataset, the Pancreas-CT dataset, and the Brats-2019 dataset. Our approach significantly outperforms state-of-the-art methods over multiple medical benchmark segmentation datasets with different labeled data ratios. We also present several ablation experiments to demonstrate the effectiveness of various components used in our approach.