ERANet: Edge Replacement Augmentation for Semi-Supervised Meniscus Segmentation with Prototype Consistency Alignment and Conditional Self-Training

2025-02-11

AI Summary

To address substantial anatomical variability, low tissue contrast, and high annotation cost in automatic meniscus segmentation from knee MRI, this paper proposes ERANet, a semi-supervised framework. Methodologically: (1) Edge Replacement Augmentation (ERA) is introduced to explicitly model anatomical structural variation; (2) Prototype Consistency Alignment (PCA) enforces intra-class feature compactness via contrastive prototype learning; (3) Conditional Self-Training (CST) mitigates pseudo-label noise through confidence-aware refinement. Built upon the Mean Teacher paradigm, ERANet integrates geometric-aware augmentation, contrastive prototype alignment, dynamic-threshold pseudo-labeling, and 3D multi-sequence joint modeling. On DESS and FSE/TSE datasets, ERANet significantly outperforms state-of-the-art methods, achieving full-supervision performance using only 10% labeled data. Ablation studies confirm synergistic gains from the three core modules.

Technology Category

• Machine Learning: Semi-Supervised Learning
• Computer Vision: Segmentation
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Manual segmentation is labor-intensive, and automatic segmentation remains challenging due to the inherent variability in meniscal morphology, partial volume effects, and low contrast between the meniscus and surrounding tissues. To address these challenges, we propose ERANet, an innovative semi-supervised framework for meniscus segmentation that effectively leverages both labeled and unlabeled images through advanced augmentation and learning strategies. ERANet integrates three key components: edge replacement augmentation (ERA), prototype consistency alignment (PCA), and a conditional self-training (CST) strategy within a mean teacher architecture. ERA introduces anatomically relevant perturbations by simulating meniscal variations, ensuring that augmentations align with the structural context. PCA enhances segmentation performance by aligning intra-class features and promoting compact, discriminative feature representations, particularly in scenarios with limited labeled data. CST improves segmentation robustness by iteratively refining pseudo-labels and mitigating the impact of label noise during training. Together, these innovations establish ERANet as a robust and scalable solution for meniscus segmentation, effectively addressing key barriers to practical implementation. We validated ERANet comprehensively on 3D Double Echo Steady State (DESS) and 3D Fast/Turbo Spin Echo (FSE/TSE) MRI sequences. The results demonstrate the superior performance of ERANet compared to state-of-the-art methods. The proposed framework achieves reliable and accurate segmentation of meniscus structures, even when trained on minimal labeled data. Extensive ablation studies further highlight the synergistic contributions of ERA, PCA, and CST, solidifying ERANet as a transformative solution for semi-supervised meniscus segmentation in medical imaging.

Problem

• Semi-supervised meniscus segmentation challenges
• Edge replacement augmentation for MRI data
• Prototype consistency alignment improves accuracy

Innovation

• Edge Replacement Augmentation technique
• Prototype Consistency Alignment strategy
• Conditional Self-Training method