While deep learning has demonstrated considerable promise in computer-aided diagnosis for pulmonary embolism (PE), practical deployment in Computed Tomography Pulmonary Angiography (CTPA) is often hindered by "domain shift" and the prohibitive cost of expert annotations. To address these challenges, an unsupervised domain adaptation (UDA) framework is proposed, utilizing a Transformer backbone and a Mean-Teacher architecture for cross-center semantic segmentation. The primary focus is placed on enhancing pseudo-label reliability by learning deep structural information within the feature space. Specifically, three modules are integrated and designed for this task: (1) a Prototype Alignment (PA) mechanism to reduce category-level distribution discrepancies; (2) Global and Local Contrastive Learning (GLCL) to capture both pixel-level topological relationships and global semantic representations; and (3) an Attention-based Auxiliary Local Prediction (AALP) module designed to reinforce sensitivity to small PE lesions by automatically extracting high-information slices from Transformer attention maps. Experimental validation conducted on cross-center datasets (FUMPE and CAD-PE) demonstrates significant performance gains. In the FUMPE -> CAD-PE task, the IoU increased from 0.1152 to 0.4153, while the CAD-PE -> FUMPE task saw an improvement from 0.1705 to 0.4302. Furthermore, the proposed method achieved a 69.9% Dice score in the CT -> MRI cross-modality task on the MMWHS dataset without utilizing any target-domain labels for model selection, confirming its robustness and generalizability for diverse clinical environments.

翻译：尽管深度学习在肺栓塞（PE）的计算机辅助诊断中展现出巨大潜力，但其在CT肺动脉造影（CTPA）中的实际部署常受限于“域偏移”问题以及专家标注的极高成本。为应对这些挑战，本文提出了一种无监督域适应（UDA）框架，该框架采用Transformer主干网络和Mean-Teacher架构，用于跨中心语义分割。研究重点在于通过学习特征空间中的深层结构信息来提升伪标签的可靠性。具体而言，本文为此任务集成并设计了三个模块：（1）原型对齐（PA）机制，以减少类别层面的分布差异；（2）全局与局部对比学习（GLCL），以捕捉像素级拓扑关系和全局语义表征；（3）基于注意力的辅助局部预测（AALP）模块，旨在通过从Transformer注意力图中自动提取高信息量切片，增强对小尺寸PE病灶的敏感性。在跨中心数据集（FUMPE和CAD-PE）上进行的实验验证表明，该方法取得了显著的性能提升。在FUMPE -> CAD-PE任务中，IoU从0.1152提升至0.4153；而在CAD-PE -> FUMPE任务中，IoU从0.1705提升至0.4302。此外，在MMWHS数据集的CT -> MRI跨模态任务中，所提方法在不使用任何目标域标签进行模型选择的情况下，取得了69.9%的Dice分数，证实了其在不同临床环境中的鲁棒性和泛化能力。