文献速递腹部技术与安全MR

磁共振成像影像组学预测肝细胞癌切除或消融后复发:一项系统综述与荟萃分析

Magnetic resonance imaging radiomics for predicting hepatocellular carcinoma recurrence following resection or ablation: a systematic review and meta-analysis.
PubMed 文献 · Abdom Radiol (NY) · 2025-09-22

本系统综述与荟萃分析评估MRI影像组学模型预测肝细胞癌根治性治疗后复发及微血管侵犯的性能,纳入相关研究并用随机效应模型汇总。结果显示影像组学模型在训练和验证队列中的C-index分别为0.78和0.73,预测复发和微血管侵犯的敏感度、特异度及AUC均较高,优于临床-影像学模型,但未来需关注成本效益和外部验证。

要点

  • MRI影像组学模型预测HCC复发的汇总C-index训练队列0.78、验证队列0.73,优于临床-影像学模型。
  • 预测肝切除后复发:训练队列敏感度0.81、特异度0.85、AUC 0.87;验证队列敏感度0.80、特异度0.74、AUC 0.83。
  • 预测热消融后复发:训练队列AUC 0.79,验证队列AUC 0.82;预测MVI验证队列AUC 0.87。

核心结论

  • MRI影像组学模型预测HCC复发和MVI的性能优于常规临床-影像学模型,可能增强临床决策;未来研究应关注成本效益和外部验证以支持更广泛的临床整合。

研究设计与样本

  • 系统综述与荟萃分析,遵循PRISMA,系统检索预测HCC复发和微血管侵犯的研究,采用QUADAS、影像组学质量评分和METRICS工具进行质量评价,使用随机效应模型进行荟萃分析并评估异质性。

诊断标准与关键数值

  • 预测HCC复发的汇总C-index:训练队列0.78(95%CI 0.71-0.85),验证队列0.73(95%CI 0.69-0.77)。
  • 预测肝切除后复发:训练队列敏感度0.81(95%CI 0.74-0.87)、特异度0.85(95%CI 0.77-0.90)、AUC 0.87、准确率0.81(95%CI 0.76-0.86)。
  • 预测肝切除后复发验证队列:敏感度0.80(95%CI 0.73-0.86)、特异度0.74(95%CI 0.68-0.80)、AUC 0.83、准确率0.79(95%CI 0.75-0.83)。
  • 预测热消融后复发:训练队列敏感度0.80(95%CI 0.60-0.90)、特异度0.79(95%CI 0.74-0.84)、AUC 0.79、准确率0.78(95%CI 0.72-0.84)。
  • 预测热消融后复发验证队列:敏感度0.79(95%CI 0.69-0.87)、特异度0.78(95%CI 0.57-0.90)、AUC 0.82、准确率0.76(95%CI 0.67-0.84)。

临床应用与阅片要点

  • 亚组分析显示,使用PyRadiomics进行特征提取、使用LASSO进行特征选择的模型特异度显著提高。
  • MRI影像组学模型在预测HCC复发和MVI方面表现出较高性能,可能作为无创工具指导个体化治疗规划。

局限性

  • 未来研究应关注成本效益和外部验证以支持更广泛的临床整合。

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: We assessed predictive performance of MRI radiomics models for hepatocellular carcinoma (HCC) recurrence after curative treatments, aiming to inform future research on optimizing MRI-based radiomics for HCC management.

METHODS: This study followed PRISMA and we systematically searched for studies predicting HCC recurrence and microvascular invasion (MVI). Quality assessment used Quality Assessment of Diagnostic Accuracy Studies, Radiomics Quality Score, and METhodological RadiomICs Score (METRICS) tools. Meta-analyses were performed with random-effects models, assessing heterogeneity.

RESULTS: Radiomics models achieved a pooled concordance index (C-index) of 0.78(95%CI:0.71-0.85) in training and 0.73(95%CI:0.69-0.77) in validation cohorts, outperforming clinico-radiological models. For recurrence prediction after liver resection, radiomics models achieved pooled sensitivity/specificity of 0.81(0.74-0.87)/0.85(0.77-0.90) in training (AUC: 0.87; accuracy: 0.81[95%CI:0.76-0.86]) and 0.80(0.73-0.86)/0.74(0.68-0.80) in validation cohorts (AUC: 0.83; accuracy: 0.79[0.75-0.83]). For thermal ablation, sensitivity/specificity were 0.80(0.60-0.90)/0.79(0.74-0.84) in training (AUC: 0.79; accuracy: 0.78[0.72-0.84]) and 0.79(0.69-0.87)/0.78(0.57-0.90) in validation (AUC:0.82; accuracy:0.76[0.67-0.84]). For MVI prediction, radiomics models achieved 0.87(0.78-0.92)/0.88(0.80-0.93) in training (AUC: 0.93; accuracy: 0.86[0.80-0.91]), and 0.88(0.80-0.94)/0.79(0.72-0.84) in validation cohorts (AUC: 0.87; accuracy: 0.82[0.77-0.86]). Subgroup analysis revealed significantly improved specificity for models using PyRadiomics and LASSO for feature extraction and selection, respectively.

CONCLUSION: MRI radiomics models outperformed routine clinico-radiological models, with potentially enhanced clinical decision-making. Future studies should focus on cost-effectiveness and external validation to support broader clinical integration.

ADVANCES IN KNOWLEDGE: This study demonstrates that MRI radiomics models significantly enhance predictive accuracy for HCC recurrence and MVI, highlighting their potential as noninvasive tools to guide personalized treatment planning.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Maung ST, Tangkijvanich P, Chaiteerakij R, et al. Magnetic resonance imaging radiomics for predicting hepatocellular carcinoma recurrence following resection or ablation: a systematic review and meta-analysis. Abdom Radiol (NY). 2025. PMID: 40981987. doi:10.1007/s00261-025-05184-4

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。