Scale-aware Adaptive Supervised Network with Limited Medical Annotations

TL;DR

SASNet is a novel scale-aware adaptive supervised network designed for medical image segmentation with limited annotations, employing multi-scale feature integration, confidence-based reweighting, and boundary refinement to improve semi-supervised segmentation accuracy.

Contribution

The paper introduces SASNet, a dual-branch architecture with innovative scale-aware adaptive reweighting, view variance enhancement, and segmentation-regression consistency learning for improved semi-supervised medical image segmentation.

Findings

Outperforms existing semi-supervised methods on multiple datasets.

Achieves near fully supervised performance with limited labeled data.

Demonstrates robustness across different anatomical structures.

Abstract

Medical image segmentation faces critical challenges in semi-supervised learning scenarios due to severe annotation scarcity requiring expert radiological knowledge, significant inter-annotator variability across different viewpoints and expertise levels, and inadequate multi-scale feature integration for precise boundary delineation in complex anatomical structures. Existing semi-supervised methods demonstrate substantial performance degradation compared to fully supervised approaches, particularly in small target segmentation and boundary refinement tasks. To address these fundamental challenges, we propose SASNet (Scale-aware Adaptive Supervised Network), a dual-branch architecture that leverages both low-level and high-level feature representations through novel scale-aware adaptive reweight mechanisms. Our approach introduces three key methodological innovations, including the Scale-aware Adaptive Reweight strategy that dynamically weights pixel-wise predictions using temporal confidence accumulation, the View Variance Enhancement mechanism employing 3D Fourier domain transformations to simulate annotation variability, and segmentation-regression consistency learning through signed distance map algorithms for enhanced boundary precision. These innovations collectively address the core limitations of existing semi-supervised approaches by integrating spatial, temporal, and geometric consistency principles within a unified optimization framework. Comprehensive evaluation across LA, Pancreas-CT, and BraTS datasets demonstrates that SASNet achieves superior performance with limited labeled data, surpassing state-of-the-art semi-supervised methods while approaching fully supervised performance levels. The source code for SASNet is available at https://github.com/HUANGLIZI/SASNet.