文献速递技术与安全腹部MR

ComBat协调在MRI影像组学中的应用:对机器学习非二分类组织分类的影响

ComBat Harmonization for MRI Radiomics: Impact on Nonbinary Tissue Classification by Machine Learning.
PubMed 文献 · Invest Radiol · 2023-01-01

本研究回顾性纳入100例接受T1加权3D梯度回波Dixon MRI的患者,在肝、脾和椎旁肌三个视觉相似的无病组织中提取影像组学特征,评估ComBat协调对多类组织分类准确性的影响。线性判别分析平均分类准确率在未协调、ComBat-B协调和ComBat-NB协调数据分别为52.3%、66.3%和92.7%。结论认为ComBat协调可能对多中心MRI影像组学非二分类研究有用,改善程度因特征类别、分类器和ComBat变体而异。

要点

  • ComBat协调可提高多中心MRI影像组学非二分类组织分类的准确率。
  • 线性判别分析中ComBat-NB协调准确率92.7%,高于ComBat-B的66.3%和未协调的52.3%。
  • 多层感知器神经网络中GLSZM特征经ComBat-NB协调后准确率89.4%,优于ComBat-B的81.1%和未协调的48.1%。

核心结论

  • ComBat协调可能对多中心MRI影像组学非二分类分类任务有用,改善程度因影像组学特征类别、分类器和ComBat变体而异。

研究设计与样本

  • 回顾性纳入100例接受T1加权3D梯度回波Dixon MRI的患者,来自2个中心/供应商(各50例),在肝、脾和椎旁肌放置2.5 cm³感兴趣区,提取灰度直方图、灰度共生矩阵、灰度游程矩阵和灰度尺寸区域矩阵影像组学特征。

关键影像表现/征象

  • 在T1 Dixon水图像上视觉相似的肝、脾和椎旁肌三个无病组织中放置2.5 cm³感兴趣区。

诊断标准与关键数值

  • 线性判别分析平均组织分类准确率:未协调52.3%,ComBat-B协调66.3%,ComBat-NB协调92.7%。
  • 多层感知器神经网络测试数据平均分类准确率:GLH未协调46.8%、ComBat-B 55.1%、ComBat-NB 57.5%;GLCM未协调42.0%、ComBat-B 65.3%、ComBat-NB 71.0%;GLRLM未协调45.3%、ComBat-B 78.3%、ComBat-NB 78.0%;GLSZM未协调48.1%、ComBat-B 81.1%、ComBat-NB 89.4%。
  • 所有特征类别中,ComBat-B和ComBat-NB协调数据准确率均显著高于未协调数据(P=0.005)。
  • GLCM(P=0.001)和GLSZM(P=0.005)中,ComBat-NB协调准确率略高于ComBat-B协调。

临床应用与阅片要点

  • 在多中心MRI影像组学非二分类任务中,可考虑使用ComBat协调以提高组织分类准确率。
  • ComBat协调的改善程度因影像组学特征类别、分类器和ComBat变体而异。

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

OBJECTIVES: The aims of this study were to determine whether ComBat harmonization improves multiclass radiomics-based tissue classification in technically heterogeneous MRI data sets and to compare the performances of 2 ComBat variants.

MATERIALS AND METHODS: One hundred patients who had undergone T1-weighted 3D gradient echo Dixon MRI (2 scanners/vendors; 50 patients each) were retrospectively included. Volumes of interest (2.5 cm 3 ) were placed in 3 disease-free tissues with visually similar appearance on T1 Dixon water images: liver, spleen, and paraspinal muscle. Gray-level histogram (GLH), gray-level co-occurrence matrix (GLCM), gray-level run-length matrix (GLRLM), and gray-level size-zone matrix (GLSZM) radiomic features were extracted. Tissue classification was performed on pooled data from the 2 centers (1) without harmonization, (2) after ComBat harmonization with empirical Bayes estimation (ComBat-B), and (3) after ComBat harmonization without empirical Bayes estimation (ComBat-NB). Linear discriminant analysis with leave-one-out cross-validation was used to distinguish among the 3 tissue types, using all available radiomic features as input. In addition, a multilayer perceptron neural network with a random 70%:30% split into training and test data sets was used for the same task, but separately for each radiomic feature category.

RESULTS: Linear discriminant analysis-based mean tissue classification accuracies were 52.3% for unharmonized, 66.3% for ComBat-B harmonized, and 92.7% for ComBat-NB harmonized data. For multilayer perceptron neural network, mean classification accuracies for unharmonized, ComBat-B-harmonized, and ComBat-NB-harmonized test data were as follows: 46.8%, 55.1%, and 57.5% for GLH; 42.0%, 65.3%, and 71.0% for GLCM; 45.3%, 78.3%, and 78.0% for GLRLM; and 48.1%, 81.1%, and 89.4% for GLSZM. Accuracies were significantly higher for both ComBat-B- and ComBat-NB-harmonized data than for unharmonized data for all feature categories (at P = 0.005, respectively). For GLCM ( P = 0.001) and GLSZM ( P = 0.005), ComBat-NB harmonization provided slightly higher accuracies than ComBat-B harmonization.

CONCLUSIONS: ComBat harmonization may be useful for multicenter MRI radiomics studies with nonbinary classification tasks. The degree of improvement by ComBat may vary among radiomic feature categories, among classifiers, and among ComBat variants.

来源:Invest Radiol,查看原文。版权归原作者所有。

引用

  1. Leithner D, Nevin RB, Gibbs P, et al. ComBat Harmonization for MRI Radiomics: Impact on Nonbinary Tissue Classification by Machine Learning. Invest Radiol. 2023. PMID: 36897814. doi:10.1097/RLI.0000000000000970

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。