SHAPE：结构感知的分层无监督域自适应与合理性评估用于医学图像分割
SHAPE: Structure-aware Hierarchical Unsupervised Domain Adaptation with Plausibility Evaluation for Medical Image Segmentation
针对医学分割中的无监督域自适应，提出用超图评估伪标签的全局解剖合理性，并配合跨视角稳定性剪枝异常，这种基于结构先验的伪标签验证思路可迁移到其他需要可靠伪标签的视觉任务。
原文依据 we introduce Hypergraph Plausibility Estimation (HPE), which leverages hypergraphs to assess the global anatomical plausibility
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论无监督域自适应（UDA）对于将医学分割模型部署到多样化的临床环境中至关重要。现有方法存在根本性局限，受到语义无关的特征对齐影响，导致分布保真度差，并且伪标签验证忽略了全局解剖约束，因此无法防止全局不合理结构的形成。为了解决这些问题，我们提出了SHAPE（结构感知的分层无监督域自适应与合理性评估），该框架将自适应重新聚焦于全局解剖合理性。基于DINOv3基础，其分层特征调制（HFM）模块首先生成兼具高保真度和类别感知的特征。这将核心挑战转向稳健地验证伪标签。为了增强传统的像素级验证，我们引入了超图合理性估计（HPE），它利用超图来评估标准图无法捕获的全局解剖合理性。辅以结构异常剪枝（SAP），通过跨视角稳定性清除残余伪影。SHAPE在心脏和腹部跨模态基准上显著优于先前方法，在心脏数据上达到最优平均Dice分数90.08%（MRI - CT）和78.51%（CT - MRI），在腹部数据上达到87.48%（MRI - CT）和86.89%（CT - MRI）。
英文原文摘要 1446 字符
Unsupervised Domain Adaptation (UDA) is essential for deploying medical segmentation models across diverse clinical environments. Existing methods are fundamentally limited, suffering from semantically unaware feature alignment that results in poor distributional fidelity and from pseudo-label validation that disregards global anatomical constraints, thus failing to prevent the formation of globally implausible structures. To address these issues, we propose SHAPE (Structure-aware Hierarchical Unsupervised Domain Adaptation with Plausibility Evaluation), a framework that reframes adaptation towards global anatomical plausibility. Built on a DINOv3 foundation, its Hierarchical Feature Modulation (HFM) module first generates features with both high fidelity and class-awareness. This shifts the core challenge to robustly validating pseudo-labels. To augment conventional pixel-level validation, we introduce Hypergraph Plausibility Estimation (HPE), which leverages hypergraphs to assess the global anatomical plausibility that standard graphs cannot capture.This is complemented by Structural Anomaly Pruning (SAP) to purge remaining artifacts via cross-view stability.SHAPE significantly outperforms prior methods on cardiac and abdominal cross-modality benchmarks, achieving state-of-the-art average Dice scores of 90.08% (MRI - CT) and 78.51% (CT - MRI) on cardiac data, and 87.48% (MRI - CT) and 86.89% (CT - MRI) on abdominal data.