文献速递骨肌MR

磁共振影像组学与机器学习在软组织肉瘤分级中的诊断价值:现状述评

Diagnostic Value of Magnetic Resonance Imaging Radiomics and Machine-learning in Grading Soft Tissue Sarcoma: A Mini-review on the Current State.
PubMed 文献 · Acad Radiol · 2024-09-10

本文为小型综述,介绍基于MRI的影像组学、机器学习和深度学习预测软组织肉瘤恶性分级的现状。纳入研究在T2加权、增强T1加权及DWI/ADC图上构建模型,结果具有前景;融合语义影像特征、影像组学特征与深度学习标签的机器学习模型预测性能优于单一特征来源,联合瘤体与瘤周区域特征亦有帮助。随机森林与支持向量机分类器常联合LASSO和/或SMOTE,在既有研究中显示出较高AUC和准确率。

要点

  • 融合语义影像特征、影像组学特征与深度学习标签的模型,预测性能优于单一特征来源。
  • 联合肿瘤体积与瘤周区域特征对分级有益。
  • 随机森林与支持向量机分类器(常联合LASSO和/或SMOTE)在既有研究中显示较高AUC和准确率。

核心结论

  • 基于MRI的影像组学、机器学习与深度学习在预测软组织肉瘤恶性分级方面已有多项研究,结果具有前景;多特征来源融合及瘤体加瘤周特征的模型预测性能更优。

研究设计与样本

  • 小型综述,汇总在T2加权图像、增强T1加权图像及DWI/ADC图上采用机器学习与深度学习方法的软组织肉瘤分级研究;未报告检索范围、纳入文献数量或参考标准。

诊断标准与关键数值

  • 各研究多在T2加权、增强T1加权及DWI/ADC图上建模;随机森林与支持向量机分类器常联合LASSO和/或SMOTE,在既有研究中报告较高AUC与准确率,原文未给出具体数值。

临床应用与阅片要点

  • 阅片与建模时可关注T2加权、增强T1加权及DWI/ADC多序列特征,并将语义影像特征、影像组学特征与深度学习标签联合,同时纳入瘤体与瘤周区域特征。

局限性

  • 原文为小型综述(mini-review),未系统报告检索策略与纳入文献范围。
  • 原文未报告所汇总研究的具体样本量、AUC、准确率数值及置信区间。

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

Soft tissue sarcomas (STS) are a heterogeneous group of rare malignant tumors. Tumor grade might be underestimated in biopsy due to intratumoral heterogeneity. This mini-review aims to present the current state of predicting malignancy grades of STS through radiomics, machine learning, and deep learning on magnetic resonance imaging (MRI). Several studies investigated various machine-learning and deep-learning approaches in T2-weighted (w) images, contrast-enhanced (CE) T1w images, and DWI/ADC maps with promising results. Combining semantic imaging features, radiomics features, and deep-learning signatures in machine-learning models has demonstrated superior predictive performances compared to individual feature sources. Furthermore, incorporating features from both tumor volume and peritumor region is beneficial. Especially random forest and support vector machine classifiers, often combined with the least absolute shrinkage and selection operator (LASSO) and/or synthetic minority oversampling technique (SMOTE), did show high area under the curve (AUC) values and accuracies in existing studies.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Schmitz F, Sedaghat S. Diagnostic Value of Magnetic Resonance Imaging Radiomics and Machine-learning in Grading Soft Tissue Sarcoma: A Mini-review on the Current State. Acad Radiol. 2024. PMID: 39261231. doi:10.1016/j.acra.2024.08.035

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。