SPEGC：通过语义提示增强图聚类实现医学图像分割的持续测试时自适应
SPEGC: Continual Test-Time Adaptation via Semantic-Prompt-Enhanced Graph Clustering for Medical Image Segmentation
针对医学图像分割中的持续测试时自适应，提出语义提示增强与可微图聚类求解器，将全局边稀疏化建模为最优传输问题，为无监督域适应提供更可靠的伪标签结构引导，可复用于其他密集预测任务的测试时自适应。
原文依据 we propose a CTTA via Semantic-Prompt-Enhanced Graph Clustering (SPEGC) for medical image segmentation
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论在医学图像分割任务中，训练数据与测试数据采集差异导致的域间差异严重阻碍了预训练模型在临床实践中的部署。持续测试时自适应（CTTA）旨在使预训练模型能够适应不断变化的无标签域，为解决该问题提供了有效途径。然而，现有CTTA方法往往依赖不可靠的监督信号，引发误差累积的自我强化循环，最终导致灾难性的性能下降。为克服这些挑战，我们提出了一种通过语义提示增强图聚类（SPEGC）实现的医学图像分割CTTA方法。首先，我们设计了一种语义提示特征增强机制，利用解耦的共性与异性提示池将全局上下文信息注入局部特征，缓解其在域偏移下易受噪声干扰的问题。其次，基于这些增强特征，我们设计了一个可微图聚类求解器。该求解器将全局边稀疏化重新表述为最优传输问题，使其能够以端到端的方式将原始相似度矩阵提炼为精炼的高阶结构表示。最后，这种鲁棒的结构表示被用于指导模型自适应，确保预测在簇级别上保持一致并动态调整决策边界。大量实验表明，SPEGC在两个医学图像分割基准上优于其他最优的CTTA方法。源代码可在 https://github.com/Jwei-Z/SPEGC-for-MIS 获取。
英文原文摘要 1679 字符
In medical image segmentation tasks, the domain gap caused by the difference in data collection between training and testing data seriously hinders the deployment of pre-trained models in clinical practice. Continual Test-Time Adaptation (CTTA) aims to enable pre-trained models to adapt to continuously changing unlabeled domains, providing an effective approach to solving this problem. However, existing CTTA methods often rely on unreliable supervisory signals, igniting a self-reinforcing cycle of error accumulation that culminates in catastrophic performance degradation. To overcome these challenges, we propose a CTTA via Semantic-Prompt-Enhanced Graph Clustering (SPEGC) for medical image segmentation. First, we design a semantic prompt feature enhancement mechanism that utilizes decoupled commonality and heterogeneity prompt pools to inject global contextual information into local features, alleviating their susceptibility to noise interference under domain shift. Second, based on these enhanced features, we design a differentiable graph clustering solver. This solver reframes global edge sparsification as an optimal transport problem, allowing it to distill a raw similarity matrix into a refined and high-order structural representation in an end-to-end manner. Finally, this robust structural representation is used to guide model adaptation, ensuring predictions are consistent at a cluster-level and dynamically adjusting decision boundaries. Extensive experiments demonstrate that SPEGC outperforms other state-of-the-art CTTA methods on two medical image segmentation benchmarks. The source code is available at https://github.com/Jwei-Z/SPEGC-for-MIS.