发表机构
Northwestern Polytechnical University; Chinese Medicine Guangdong Laboratory; University of Sheffield（西北工业大学; 广东省中医药实验室; 谢菲尔德大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出CIRSeg，基于nnU-Netv2的由粗到细强度鲁棒肝脏分割框架，结合3D CutMix、随机强度转移、源域自由测试时自适应及后处理，在CARE 2026上实现域内和未见域高精度分割。
AI 中文摘要
在对比增强MRI中进行可靠的肝脏分割对于定量肝脏评估、治疗计划和纵向疾病监测至关重要。然而，有限的标注数据和扫描仪或供应商依赖的强度变化可能导致过拟合以及对未见采集域的泛化能力差。此外，同时实现鲁棒的全局定位和精确的边界描绘仍然具有挑战性，而预测可能包含主肝脏组件之外的孤立假阳性区域。为了解决这些挑战，我们提出了CIRSeg，一个基于nnU-Netv2的由粗到细、强度鲁棒的肝脏分割框架。CIRSeg结合了3D CutMix与随机强度转移，使用Nyul增强或直方图匹配来提高对异质MRI强度的鲁棒性。其级联架构将低分辨率解剖定位与全分辨率边界细化解耦。在推理时，基于置信度过滤预测和概率先验正则化的源域自由测试时自适应进一步提高了对分布外输入的鲁棒性。作为最终的确定性后处理步骤，最大连通分量过滤移除了孤立的假阳性区域。在CARE 2026测试集上，CIRSeg在域内和未见域子集上分别取得了97.13%和97.93%的Dice分数，对应的HD95值分别为20.18毫米和11.30毫米。这些结果表明在域内和未见采集设置下均具有一致准确的分割性能。代码可在https://此URL获取。
英文摘要
Reliable liver segmentation in contrast-enhanced MRI is essential for quantitative hepatic assessment, treatment planning, and longitudinal disease monitoring. However, limited annotated data and scanner- or vendor-dependent intensity variations can cause overfitting and poor generalization to unseen acquisition domains. Moreover, simultaneously achieving robust global localization and precise boundary delineation remains challenging, while predictions may contain isolated false-positive regions outside the main liver component. To address these challenges, we propose CIRSeg, a coarse-to-fine, intensity-robust liver segmentation framework based on nnU-Netv2. CIRSeg combines 3D CutMix with stochastic intensity transfer using either Nyul augmentation or histogram matching to improve robustness to heterogeneous MRI intensities. Its cascaded architecture decouples low-resolution anatomical localization from full-resolution boundary refinement. At inference, source-free test-time adaptation based on confidence-filtered predictions and probability-prior regularization further improves robustness to out-of-distribution inputs. As a final deterministic post-processing step, largest connected component filtering removes isolated false-positive regions. On the CARE 2026 test set, CIRSeg achieves Dice scores of 97.13\% and 97.93\% on the in-domain and unseen-domain subsets, with corresponding HD95 values of 20.18 mm and 11.30 mm, respectively. These results demonstrate consistently accurate segmentation across both in-domain and unseen acquisition settings. The code is available at https://github.com/jingkunchen/MICCAI_CARE_2026
CommentsAccepted at the CARE 2026 Workshop at MICCAI 2026
