通过噪声注入提升医学图像分割边界鲁棒性
Implicit Fuzzification via Bounded Noise Injection for Robust Medical Image Segmentation
- 在跳接路径注入有界噪声，隐式实现模糊化以捕捉边界不确定性
- 在甲状腺超声数据集上显著提升分割精度与边界保真度
- 适合需要高可靠性分割的医疗影像场景
图像分割受限于采样导致的信息丢失和像素级标注的固有不确定性，引发边界模糊问题。尽管U-Net等编码器-解码器架构表现良好，但常产生过度自信的预测，无法捕捉过渡区域的不确定性。为此，我们提出NoiseUNet，通过在跳接连接中注入有界扰动，正则化跨尺度特征融合，增强对局部特征变化的鲁棒性，促进边界感知表征。理论上，该扰动诱导出隐式模糊化效应，生成数据驱动的软隶属度，无需显式模糊建模。我们进一步构建了真实世界甲状腺超声数据集ThyR，其边界本就模糊。实验表明，NoiseUNet在分割准确率和边界保真度上均持续提升。
原文摘要 · Abstract (English)
Image segmentation remains fundamentally limited by boundary ambiguity arising from sampling-induced information loss and inherent uncertainty in pixel-wise labeling. Although encoder-decoder architectures such as U-Net achieve strong performance, they often produce overconfident predictions that fail to capture transition-region ambiguity. To address this issue, we propose \textbf{NoiseUNet}, a simple yet effective framework that injects bounded perturbations into skip connections to regularize cross-scale feature fusion. This mechanism enforces robustness to local feature variations and promotes boundary-aware representations. Theoretically, the perturbation induces an implicit fuzzification effect, yielding soft, data-driven memberships without requiring explicit fuzzy modeling. We further introduce \textbf{ThyR}, a real-world thyroid ultrasound dataset with inherently ambiguous boundaries. Experiments demonstrate that NoiseUNet consistently improves both segmentation accuracy and boundary fidelity.
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。