ComBat 协调对基于 PET 影像组学的组织分类的影响:一项双中心 PET/MRI 与 PET/CT 研究
该研究回顾性纳入 200 例接受 18F-FDG PET/MRI 或 PET/CT 检查的患者,评估 ComBat 协调能否改善合并 PET/MRI 与 PET/CT 数据集中基于影像组学的组织分类。使用多层感知器神经网络对无病肝、脾和骨髓进行分类,ComBat 协调后各类特征及多类影像组学标签的准确率均高于未协调数据。结论认为 ComBat 协调可能对使用合并 PET/MRI 与 PET/CT 数据的多中心 18F-FDG PET 影像组学研究有用。
要点
- ComBat 协调后影像组学标签在训练集和验证集的准确率分别为 86.9% 和 84.4%,未协调时为 62.9% 和 58.3%。
- 灰度共生矩阵特征协调后准确率训练集 92.1%、验证集 86.1%,未协调时为 53.6% 和 50.0%。
- 结论认为 ComBat 协调可能对合并 PET/MRI 与 PET/CT 数据的多中心 18F-FDG PET 影像组学研究有用。
核心结论
- ComBat 协调可能对使用合并 PET/MRI 与 PET/CT 数据的多中心 18F-FDG PET 影像组学研究有用。
研究设计与样本
- 计算无病肝、脾和骨髓感兴趣区的灰度直方图、灰度共生矩阵、灰度游程矩阵、灰度尺寸区域矩阵和邻域灰度差矩阵影像组学特征。
- 使用多层感知器神经网络在 ComBat 协调与未协调的合并数据上对组织进行分类。
主要发现
- 灰度直方图特征协调后训练集和验证集中位准确率分别为 69.5% 和 68.3%,未协调时分别为 59.5% 和 58.9%。
- 灰度共生矩阵特征协调后训练集和验证集中位准确率分别为 92.1% 和 86.1%,未协调时分别为 53.6% 和 50.0%。
- 灰度游程矩阵特征协调后训练集和验证集中位准确率分别为 84.8% 和 82.8%,未协调时分别为 62.4% 和 58.3%。
- 灰度尺寸区域矩阵特征协调后训练集和验证集中位准确率分别为 87.6% 和 85.6%,未协调时分别为 56.2% 和 52.8%。
- 邻域灰度差矩阵特征协调后训练集和验证集中位准确率分别为 79.5% 和 77.2%,未协调时分别为 54.8% 和 53.9%;影像组学标签协调后训练集和验证集中位准确率分别为 86.9% 和 84.4%,未协调时分别为 62.9% 和 58.3%。
关键数值与推荐
- ComBat 协调后影像组学标签训练集和验证集中位准确率分别为 86.9% 和 84.4%,未协调时分别为 62.9% 和 58.3%。
- 灰度共生矩阵特征协调后训练集和验证集中位准确率分别为 92.1% 和 86.1%,未协调时分别为 53.6% 和 50.0%。
- 灰度直方图特征协调后训练集和验证集中位准确率分别为 69.5% 和 68.3%,未协调时分别为 59.5% 和 58.9%。
临床怎么用
- 原文结论认为 ComBat 协调可能对使用合并 PET/MRI 与 PET/CT 数据的多中心 18F-FDG PET 影像组学研究有用,未据此给出具体临床推荐。
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)。
原文
Our purpose was to determine whether ComBat harmonization improves 18F-FDG PET radiomics-based tissue classification in pooled PET/MRI and PET/CT datasets. Methods: Two hundred patients who had undergone 18F-FDG PET/MRI (2 scanners and vendors; 50 patients each) or PET/CT (2 scanners and vendors; 50 patients each) were retrospectively included. Gray-level histogram, gray-level cooccurrence matrix, gray-level run-length matrix, gray-level size-zone matrix, and neighborhood gray-tone difference matrix radiomic features were calculated for volumes of interest in the disease-free liver, spleen, and bone marrow. For individual feature classes and a multiclass radiomic signature, tissue was classified on ComBat-harmonized and unharmonized pooled data, using a multilayer perceptron neural network. Results: Median accuracies in training and validation datasets were 69.5% and 68.3% (harmonized), respectively, versus 59.5% and 58.9% (unharmonized), respectively, for gray-level histogram; 92.1% and 86.1% (harmonized), respectively, versus 53.6% and 50.0% (unharmonized), respectively, for gray-level cooccurrence matrix; 84.8% and 82.8% (harmonized), respectively, versus 62.4% and 58.3% (unharmonized), respectively, for gray-level run-length matrix; 87.6% and 85.6% (harmonized), respectively, versus 56.2% and 52.8% (unharmonized), respectively, for gray-level size-zone matrix; 79.5% and 77.2% (harmonized), respectively, versus 54.8% and 53.9% (unharmonized), respectively, for neighborhood gray-tone difference matrix; and 86.9% and 84.4% (harmonized), respectively, versus 62.9% and 58.3% (unharmonized), respectively, for radiomic signature. Conclusion: ComBat harmonization may be useful for multicenter 18F-FDG PET radiomics studies using pooled PET/MRI and PET/CT data.
引用
- Leithner D, Schöder H, Haug A, et al. Impact of ComBat Harmonization on PET Radiomics-Based Tissue Classification: A Dual-Center PET/MRI and PET/CT Study. J Nucl Med. 2022. PMID: 35210300. doi:10.2967/jnumed.121.263102
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。