基于nnU-Net的急性胰腺炎严重程度CT影像组学自动化流程多中心验证
内部测试队列中,两种流程的AUC差异无统计学意义(0.799 vs 0.733,FDR校正p=0.360),自动流程在两个外部中心保持中等判别能力,支持减少对人工分割依赖的可行性。
要点
- nnU-Net自动分割与手动分割的影像组学模型在内部测试集判别能力无显著差异。
- 自动流程在外部中心AUC分别为0.784和0.715,显示一定泛化能力。
- 所选2D nnU-Net平均Dice系数交叉验证0.798,独立测试集0.726。
核心结论
- nnU-Net自动分割-影像组学流程与专家手动流程在内部测试队列中判别急性胰腺炎严重程度无显著差异,且在两个外部队列中保持中等判别能力。
研究设计与样本
- 回顾性多中心研究,纳入中心A 214例、中心B 56例、中心C 42例急性胰腺炎患者。
- 以专家手动胰腺掩膜作为nnU-Net训练参考标注及影像组学流程比较对象。
- 选择最优nnU-Net配置后,分别从手动和自动ROI提取影像组学特征,使用相同分析框架构建严重程度分类器。
- 在独立内部测试队列中使用AUC和配对DeLong检验比较两种流程的判别能力,P值经Benjamini-Hochberg FDR和Bonferroni校正。
诊断标准与关键数值
- 内部测试队列中,LightGBM分类器手动分割AUC为0.799(95%CI 0.683-0.915),自动分割AUC为0.733(95%CI 0.593-0.873)。
- AUC绝对差值为0.066,配对DeLong比较经FDR校正后无统计学意义(FDR校正p=0.360;Z=1.1755,未校正p=0.2398)。
- 自动流程在中心B的AUC为0.784(95%CI 0.653-0.915),在中心C的AUC为0.715(95%CI 0.559-0.871)。
- 所选2D nnU-Net在五折交叉验证中平均Dice系数为0.798,在独立内部测试队列中为0.726。
临床应用与阅片要点
- 在急性胰腺炎CT影像组学分析中,可考虑使用nnU-Net自动分割替代手动胰腺分割以提升流程效率。
- 自动分割流程的外部判别能力为中等,用于临床决策前需在本地数据验证。
- 本研究未确立两种流程的正式等效性或可互换性,报告时应谨慎解读。
局限性
- 本分析未确立自动与手动流程的正式等效性或可互换性。
- 回顾性多中心设计,外部中心样本量较小(中心B 56例,中心C 42例)。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
RATIONALE AND OBJECTIVES: Computed tomography radiomics has shown potential for predicting acute pancreatitis (AP) severity, but conventional workflows depend on labor-intensive expert pancreatic segmentation. This study evaluated a no-new-Net (nnU-Net)-based automated segmentation-radiomics workflow against an expert manual-segmentation workflow, using AP severity classification as the downstream task, and assessed the automated workflow externally.
MATERIALS AND METHODS: This retrospective multicenter study included patients with AP from Center A (n = 214), Center B (n = 56), and Center C (n = 42). Expert manual pancreatic masks served as reference annotations for nnU-Net training and as the comparator for the radiomics workflow. After selecting the optimal nnU-Net configuration, radiomics features were extracted separately from manual and automated regions of interest, and AP severity classifiers were developed using the same analytical framework. Discrimination between the two workflows was compared in the independent internal test cohort using the area under the curve (AUC) and the paired DeLong test, with Benjamini-Hochberg false discovery rate (FDR) and Bonferroni corrections applied to P values.
RESULTS: In the internal test cohort, the Light Gradient Boosting Machine classifier achieved AUCs of 0.799 (95% confidence interval (CI), 0.683-0.915) and 0.733 (95% CI, 0.593-0.873) with manual and automated segmentations, respectively. The absolute AUC difference was 0.066, and the paired DeLong comparison was not statistically significant after FDR correction (FDR-adjusted p = 0.360; Z = 1.1755, unadjusted p = 0.2398). The automated workflow achieved AUCs of 0.784 (95% CI, 0.653-0.915) in Center B and 0.715 (95% CI, 0.559-0.871) in Center C. The selected 2D nnU-Net achieved a mean Dice coefficient of 0.798 during five-fold cross-validation and 0.726 in the independent internal test cohort.
CONCLUSION: The nnU-Net-based automated segmentation-radiomics workflow showed no significant difference in discrimination compared with the expert manual workflow in the internal test cohort. It also maintained moderate discrimination across two external cohorts. These findings support the feasibility of reducing dependence on manual pancreatic segmentation, although the present analysis does not establish formal equivalence or interchangeability.
引用
- Hou B, Feng W, Li W, et al. Multicenter Comparative Validation of an nnU-Net-Based Automated CT Radiomics Workflow for Acute Pancreatitis Severity Prediction. Acad Radiol. 2026. PMID: 42869670. doi:10.1016/j.acra.2026.09.040
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。