文献速递腹部技术与安全CT

nnU-Net自动分割胰源性门脉高压胃周静脉曲张

nnU-Net-based CT segmentation of perigastric varices in sinistral portal hypertension: a multicenter study.
PubMed 文献 · Abdom Radiol (NY) · 2026-06-16

本研究回顾性纳入南通3家医院172例胰腺癌合并左侧门脉高压患者的门静脉期增强CT图像,训练并测试基于nnU-Net的胃周静脉自动分割模型。模型在内部和外部测试集DSC分别达0.784和0.780,预测管径与参考标准相关性良好。研究提示该模型对胃周静脉曲张具有较好的自动分割与量化潜力。

要点

  • 增强CT门静脉期图像可用于胃周静脉曲张自动分割与管径量化
  • 胃冠状静脉管径预测与参考标准相关性最高,r=0.967
  • 模型在内部与外部测试集表现接近,提示一定泛化能力

核心结论

  • nnU-Net模型对左侧门脉高压患者胃周静脉曲张的CT自动分割表现较好,内部与外部测试集DSC分别为0.784和0.780,优于对照模型。

研究设计与样本

  • 回顾性多中心研究,纳入南通3家医院172例胰腺癌合并左侧门脉高压患者的增强CT门静脉期图像。
  • 病例划分为训练集99例、模型优化集22例、内部测试集22例、外部测试集29例。
  • 模型采用自配置nnU-Net,以人工分割结果为训练标签,评价指标包括DSC、召回率、精确率和Hausdorff距离。

关键影像表现/征象

  • 模型分割胃周静脉曲张在内部测试集DSC为0.784(95%CI 0.710,0.857),外部测试集DSC为0.780(95%CI 0.705,0.856)。
  • 预测管径与参考标准相关性良好,胃冠状静脉r=0.967,所有胃周曲张静脉相关性均大于0.770(P<0.001)。

诊断标准与关键数值

  • DSC:内部测试集0.784(95%CI 0.710,0.857),外部测试集0.780(95%CI 0.705,0.856),均优于对照模型。
  • 管径相关性:胃冠状静脉r=0.967,所有胃周曲张静脉相关性均大于0.770(P<0.001)。
  • 可重复性:操作者内ICC=0.852(95%CI 0.806,0.897),操作者间ICC=0.839(95%CI 0.793,0.885)。
  • 影像组学特征可重复性:内部测试集ICC=0.853(95%CI 0.827,0.879),外部测试集ICC=0.870(95%CI 0.833,0.906)。

临床应用与阅片要点

  • 增强CT门静脉期可用于胰源性左侧门脉高压患者胃周静脉曲张的自动分割和管径量化。
  • 胃冠状静脉是预测管径相关性最高的血管,阅片和量化时可优先关注。
  • 模型在内外测试集表现稳定,提示具备多中心推广和辅助报告的潜在价值。

局限性

  • 研究为回顾性设计,纳入患者均为胰腺癌相关左侧门脉高压,结果不一定适用于其他病因。
  • 测试集样本量较小,内部22例、外部29例,可能影响稳定性评价。
  • 以人工分割为参考标准,人工标注本身存在操作者间和操作者内变异。

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

PURPOSE: To develop a deep learning model based on nnU-Net for automated segmentation of all perigastric veins on contrast-enhanced CT images in patients with sinistral portal hypertension (SPH).

METHODS: Retrospectively including contrast-enhanced computed tomography (CT) portal venous phase images from 172 pancreatic cancer patients with SPH across three hospitals in Nantong. The patients were divided into the training dataset (n = 99), model optimization dataset (n = 22), internal testing dataset (n = 22), and external testing dataset (n = 29). The self-configuring nnU-Net model was trained on the manually segmented training dataset. Evaluation metrics on the testing datasets included Dice similarity coefficient (DSC), recall, precision and Hausdorff distance (HD). Pearson correlation and Bland-Altman analyses were conducted between the reference standard and predicted diameters. Intraclass correlation coefficients (ICCs) were used to assess inter-rater agreement and reproducibility of radiomic features.

RESULTS: The nnU-Net model achieved a DSC of 0.784 (95% CI 0.710, 0.857) on the internal testing dataset and 0.780 (95% CI 0.705, 0.856) on the external testing dataset, outperforming the comparative models. Predicted diameters correlated strongly with the reference standard in both testing datasets, notably for the gastric coronary vein (r = 0.967), with all perigastric varices achieving correlations > 0.770 (p < 0.001). High intra-rater (ICC = 0.852; 95% CI 0.806, 0.897) and inter-rater agreement (ICC = 0.839; 95% CI 0.793, 0.885) were observed, and feature reproducibility remained robust in both the internal (ICC = 0.853; 95% CI 0.827, 0.879) and external testing datasets (ICC = 0.870; 95% CI 0.833, 0.906).

CONCLUSION: The nnU-Net model provides promising segmentation performance for perigastric varices in SPH.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Wei, Wu, Wang, et al. nnU-Net-based CT segmentation of perigastric varices in sinistral portal hypertension: a multicenter study. Abdom Radiol (NY). 2026. PMID: 42301285. doi:10.1007/s00261-026-05545-7

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。