发表机构
College of Automation, Nanjing University of Posts and Telecommunications; Department of Electrical and Computer Engineering, National University of Singapore; the Affiliated Stomatological Hospital of Nanjing Medical University（南京邮电大学自动化学院; 新加坡国立大学电气与计算机工程系; 南京医科大学附属口腔医院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对骨盆骨分割模型跨中心域偏移导致的性能下降问题，提出ReGA框架，结合SICE准则、信任加权细化模块、对比学习与TS方案，在三个数据集上优于现有TTA方法，实现有效适应。
AI 中文摘要
从CT中进行可靠的骨盆骨分割（PBS）对机器人辅助骨盆创伤手术至关重要，但将源训练模型部署到新医院时，因跨中心域偏移会出现严重的性能下降。测试时适应（TTA）可在不访问源数据的情况下实现在线模型适应，然而现有方法对PBS的有效性有限，面临边界退化、域偏移下的解剖结构不一致及体素级类别不平衡等挑战。为解决这些问题，本文提出一种新颖的闭环动态可靠性引导TTA框架（ReGA）用于PBS。具体而言，引入伪标签可靠性准则，称为分割推理一致性评估（SICE），其通过基于dropout的集成预测联合测量区域重叠与边界偏差；基于SICE，一个信任加权细化模块自适应更新特征以减轻伪标签中的边界误差。此外，提出一种置信度加权区域级对比学习策略以强制解剖结构一致性。最后，ReGA遵循教师-学生（TS）方案以缓解体素级类别不平衡。在三个异构3D骨盆CT数据集上的实验表明，ReGA始终优于最先进的TTA方法，可实现源训练PBS模型对未见临床域的有效适应。代码可在该httpsURL获取。
英文摘要
Reliable pelvic bone segmentation (PBS) from CT is essential for robot-assisted pelvic trauma surgery, yet deploying a source-trained model to a new hospital suffers from severe performance degradation due to cross-center domain shifts. While test-time adaptation (TTA) enables online model adaptation without accessing source data, existing methods show limited effectiveness for PBS, facing challenges including boundary degradation, anatomical inconsistency under domain shifts, and voxel-level class imbalance. To address these challenges, we propose a novel closed-loop dynamic Reliability-Guided TTA framework (ReGA) for PBS. Specifically, we introduce a pseudo-label reliability criterion termed Segmentation Inference Consistency Evaluation (SICE), which jointly measures region overlap and boundary deviation via dropout-based ensemble predictions. Based on SICE, a trust-weighted refinement module adaptively updates features to mitigate boundary errors in pseudo-labels. Furthermore, a confidence-weighted region-level contrastive learning strategy is proposed to enforce anatomical consistency. Finally, ReGA follows the teacher-student (TS) scheme to alleviate voxel-level class imbalance. Experiments on three heterogeneous 3D pelvic CT datasets demonstrate that ReGA consistently outperforms state-of-the-art TTA methods, enabling effective adaptation of the source-trained PBS model to unseen clinical domains. The code is available at https://github.com/Ren-ling/ReGA.
CommentsProvisionally accepted for presentation at MICCAI 2026
