用几何与结构双重引导，提升医学图像分割对标注噪声的鲁棒性。
From Noisy Labels to Intrinsic Structure: A Geometric-Structural Dual-Guided Framework for Noise-Robust Medical Image Segmentation
- 融合几何与结构先验，动态加权像素以抑制噪声区域。
- 在四类模拟噪声数据上表现超越当前最优，最高提升22.76%。
- 适合标注质量不高的医学图像分割任务，尤其多专家标注场景。
卷积神经网络在医学图像分割中的有效性依赖大规模高质量标注，而获取此类标注成本高、耗时长。即使由专家标注的数据也难免存在主观性与粗略勾画带来的噪声，干扰特征学习并影响模型性能。为此，本文提出几何-结构双引导网络（GSD-Net），融合几何与结构线索以增强对标注噪声的鲁棒性。其包含几何感知模块，利用几何特征动态调整像素级权重，强化可靠区域监督并抑制噪声；结构引导标签优化模块引入结构先验细化标签；知识迁移模块丰富监督信号，提升对局部细节的敏感性。我们在六个公开数据集上评估该方法：四个含三类模拟标注噪声的数据集，两个含多位专家标注的真实噪声数据集。实验表明，GSD-Net 在噪声条件下达到当前最优性能，在模拟随机噪声下于Kvasir提升1.58%、深圳数据集提升22.76%、BU-SUC提升8.87%、BraTS2020提升1.77%。代码已开源。
原文摘要 · Abstract (English)
The effectiveness of convolutional neural networks in medical image segmentation relies on large-scale, high-quality annotations, which are costly and time-consuming to obtain. Even expert-labeled datasets inevitably contain noise arising from subjectivity and coarse delineations, which disrupt feature learning and adversely impact model performance. To address these challenges, this study propose a Geometric-Structural Dual-Guided Network (GSD-Net), which integrates geometric and structural cues to improve robustness against noisy annotations. It incorporates a Geometric Distance-Aware module that dynamically adjusts pixel-level weights using geometric features, thereby strengthening supervision in reliable regions while suppressing noise. A Structure-Guided Label Refinement module further refines labels with structural priors, and a Knowledge Transfer module enriches supervision and improves sensitivity to local details. To comprehensively assess its effectiveness, we evaluated GSD-Net on six publicly available datasets: four containing three types of simulated label noise, and two with multi-expert annotations that reflect real-world subjectivity and labeling inconsistencies. Experimental results demonstrate that GSD-Net achieves state-of-the-art performance under noisy annotations, achieving improvements of 1.58% on Kvasir, 22.76% on Shenzhen, 8.87% on BU-SUC, and 1.77% on BraTS2020 under SR simulated noise. The codes of this study are available at https://github.com/ortonwang/GSD-Net.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。