Dual-scale Enhanced and Cross-generative Consistency Learning for Semi-supervised Medical Image Segmentation

TL;DR

This paper introduces DEC-Seg, a semi-supervised medical image segmentation framework that leverages cross-scale and cross-generative consistency constraints, along with dual-scale feature fusion, to improve segmentation accuracy with limited labeled data.

Contribution

The paper proposes a novel semi-supervised segmentation method combining cross-level feature aggregation, scale-enhanced consistency, and dual-scale fusion for improved robustness and accuracy.

Findings

Outperforms state-of-the-art semi-supervised methods on multiple tasks

Effectively handles lesion size and shape variations

Demonstrates robustness across different medical imaging modalities

Abstract

Medical image segmentation plays a crucial role in computer-aided diagnosis. However, existing methods heavily rely on fully supervised training, which requires a large amount of labeled data with time-consuming pixel-wise annotations. Moreover, accurately segmenting lesions poses challenges due to variations in shape, size, and location. To address these issues, we propose a novel Dual-scale Enhanced and Cross-generative consistency learning framework for semi-supervised medical image Segmentation (DEC-Seg). First, we propose a Cross-level Feature Aggregation (CFA) module that integrates cross-level adjacent layers to enhance the feature representation ability across different resolutions. To address scale variation, we present a scale-enhanced consistency constraint, which ensures consistency in the segmentation maps generated from the same input image at different scales. This constraint helps handle variations in lesion sizes and improves the robustness of the model. Furthermore, we propose a cross-generative consistency scheme, in which the original and perturbed images can be reconstructed using cross-segmentation maps. This consistency constraint allows us to mine effective feature representations and boost the segmentation performance. To further exploit the scale information, we propose a Dual-scale Complementary Fusion (DCF) module that integrates features from two scale-specific decoders operating at different scales to help produce more accurate segmentation maps. Extensive experimental results on multiple medical segmentation tasks (polyp, skin lesion, and brain glioma) demonstrate the effectiveness of our DEC-Seg against other state-of-the-art semi-supervised segmentation approaches. The implementation code will be released at https://github.com/taozh2017/DECSeg.