文献速递腹部技术与安全US

整合超声多模态影像组学特征与临床指标的列线图模型诊断自身免疫性肝病患者显著肝纤维化

A nomogram model integrating ultrasound-based multimodal radiomics features and clinical indexes for diagnosing significant hepatic fibrosis in AILD patients.
PubMed 文献 · Abdom Radiol (NY) · 2025-12-19

本研究纳入147例经活检证实的自身免疫性肝病患者,基于Scheuer分类分为S0-1组44例和S2-4组103例,随机分为训练集102例和验证集45例。从二维超声和剪切波弹性成像提取影像组学特征,结合临床指标构建列线图模型。联合列线图在训练集和验证集的AUC分别为0.860和0.912,显著优于单一影像组学模型、FIB-4指数和APRI指数(P<0.05)。

要点

  • 联合列线图诊断S2-4期肝纤维化的AUC在训练集为0.860、验证集为0.912。
  • 血小板计数(OR=0.992)和剪切波速度(OR=3.855)是诊断S2-4期纤维化的独立预测因子(P<0.05)。
  • 联合列线图诊断性能显著优于单一影像组学模型、FIB-4指数和APRI指数(P<0.05)。

核心结论

  • 联合二维超声和剪切波弹性成像的影像组学特征与临床指标构建的列线图模型,可有效实现自身免疫性肝病肝纤维化的无创诊断并准确识别显著纤维化,为个体化评估和临床决策提供更可靠的定量工具。

研究设计与样本

  • 回顾性研究,纳入147例经活检证实的自身免疫性肝病患者,按Scheuer分类分为S0-1组44例和S2-4组103例,随机分为训练集102例和验证集45例;采用二维超声和剪切波弹性成像提取影像组学特征,以活检病理为参考标准。

诊断标准与关键数值

  • 基于Scheuer分类定义显著肝纤维化为S2-4期;选择组内相关系数>0.75的影像组学特征,经LASSO回归筛选出10个非零系数特征;联合列线图诊断S2-4期的AUC在训练集为0.860、验证集为0.912,显著优于单一影像组学模型、FIB-4指数和APRI指数(P<0.05)。

临床应用与阅片要点

  • 作者认为该列线图模型可有效实现自身免疫性肝病肝纤维化的无创诊断并准确识别显著纤维化,为个体化评估和临床决策提供更可靠的定量工具。

局限性

  • 原文未报告局限性。

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

OBJECTIVE: To develop a prediction model combining radiomics features from 2D ultrasound (2D-US) and shear wave elastography (SWE) with clinical indicators for assessing significant hepatic fibrosis (S2-4) in autoimmune liver diseases (AILDs).

METHODS: A total of 147 biopsy-confirmed AILD patients were classified into non-significant (S0-1, n = 44) and significant fibrosis (S2-4, n = 103) groups based on Scheuer's classification, and randomly divided into training (n = 102) and validation (n = 45) cohorts. Radiomics features with interclass correlation coefficient > 0.75 were selected. Ten non-zero coefficient features were identified using least absolute shrinkage and selection operator (LASSO) regression. Six machine learning algorithms were evaluated. A nomogram integrating optimal radiomics features and clinical indexes was developed and assessed via ROC, calibration curve, and decision curve analysis.

RESULTS: Logistic regression demonstrated the best performance among all algorithms. Platelet count (PLT, OR = 0.992) and shear wave velocity (Vs, OR = 3.855) were identified as independent predictors for diagnosing S2-4 stage fibrosis (P < 0.05). The combined nomogram achieved AUCs of 0.860 in the training set and 0.912 in the validation set, demonstrating significantly superior diagnostic performance compared to the single radiomics model, FIB-4 index, and APRI index (P < 0.05). In subgroup analyses across various AILD subtypes and different ALT levels, the nomogram model consistently showed the best diagnostic performance.

CONCLUSION: This study combined the radiomics of two-dimensional ultrasound and shear wave elastography and clinical indicators to construct a nomogram model, which can effectively achieve non-invasive diagnosis of AILDs fibrosis and accurately identify significant fibrosis, providing a more reliable quantitative tool for individualized assessment and clinical decision-making.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Wang Z, Yu Q, Sun Y, et al. A nomogram model integrating ultrasound-based multimodal radiomics features and clinical indexes for diagnosing significant hepatic fibrosis in AILD patients. Abdom Radiol (NY). 2025. PMID: 41417081. doi:10.1007/s00261-025-05342-8

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。