用不确定性加权的多通道分数匹配，提升医学图像无监督域适应中的分割精度。
Multi-Channel Uncertainty-Weighted Score Matching for Conditional Diffusion in Medical UDA
- 基于像素置信度加权融合多级伪标签，降低噪声影响。
- 在多个数据集上实现优于主流无监督域自适应方法的分割性能。
- 适合需要高鲁棒性医学图像分割的科研与临床应用。
跨模态医学图像分割因严重的领域偏移和目标域标签缺失而面临挑战。尽管扩散模型已被用于跨域生成与数据增强，但传统的目标域条件扩散训练依赖高度噪声的伪掩码；直接使用单一最大置信度伪标签会破坏扩散训练并影响下游分割效果。本文提出UPDiff-UDA，一个统一的无监督域自适应框架，核心为一种不确定性引导的条件扩散训练目标。给定一个不完美的源域训练分割器，我们利用其每个像素的softmax分布生成排序后的伪标签图（第一、第二、第三……最大值），每张图对应一个条件分数估计，再通过像素级置信度加权聚合得到不确定性重加权分数，用于分数匹配，从而在保留不确定区域中其他合理标签的同时增强对伪标签噪声的鲁棒性。我们进一步从理论上证明，在分割器诱导的代理标签分布下，置信度加权聚合符合最小均方误差的凸组合原则。为进一步提升伪条件质量，引入特征引导的低自由度贝塞尔曲线调整，减少外观差异。在多个公开数据集和模态迁移场景下的实验表明，UPDiff-UDA能生成高质量的目标域风格样本用于数据增强，并持续超越强基线方法。代码已开源：https://github.com/superlc1995/Multi-Channel-Uncertainty-Diffusion-UDA
原文摘要 · Abstract (English)
Robust medical image segmentation across modalities remains challenging due to severe domain shifts and the lack of target-domain labels. While diffusion models have been explored for cross-domain generation and augmentation, target-domain conditional diffusion training typically relies on highly noisy pseudo masks; naively conditioning on a single Arg-Max pseudo-label can corrupt diffusion training and downstream segmentation. We propose UPDiff-UDA, a unified UDA framework whose core is an uncertainty-guided training objective for target-domain conditional diffusion. Given an imperfect source-trained segmenter, we use its per-pixel softmax distribution to form ranked pseudo-label maps (Arg-Max, Arg-2nd, Arg-3rd, ...). Each map yields a conditional score estimate, and we aggregate them via pixel-wise confidence weighting to obtain an uncertainty-reweighted score for score matching, improving robustness to pseudo-label noise while leveraging alternative plausible labels in uncertain regions. We further provide a theoretical justification showing that confidence-weighted aggregation follows a minimum-MSE convex-combination principle under the segmenter-induced surrogate label distribution. To improve pseudo-condition quality, we also introduce a feature-guided, low-degree-of-freedom Bézier curve adaptation to reduce appearance gaps. Experiments on multiple public datasets and modality shifts show that UPDiff-UDA generates high-fidelity labeled target-style samples for augmentation and consistently outperforms strong UDA baselines. The code for this project is available at: https://github.com/superlc1995/Multi-Channel-Uncertainty-Diffusion-UDA
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。