用于多中心研究的神经黑色素敏感MRI的跨扫描仪协调
Cross-Scanner Harmonization of Neuromelanin-Sensitive MRI for Multisite Studies.
作者信息
Wengler Kenneth, Cassidy Clifford, van der Pluijm Marieke, Weinstein Jodi J, Abi-Dargham Anissa, van de Giessen Elsmarieke, Horga Guillermo
机构信息
Department of Psychiatry, New York State Psychiatric Institute, Columbia University, New York, USA.
University of Ottawa Institute of Mental Health Research, affiliated with The Royal, Ottawa, Ontario, Canada.
出版信息
J Magn Reson Imaging. 2021 Oct;54(4):1189-1199. doi: 10.1002/jmri.27679. Epub 2021 May 6.
BACKGROUND
Neuromelanin-sensitive magnetic resonance imaging (NM-MRI) is a validated measure of neuromelanin concentration in the substantia nigra-ventral tegmental area (SN-VTA) complex and is a proxy measure of dopaminergic function with potential as a noninvasive biomarker. The development of generalizable biomarkers requires large-scale samples necessitating harmonization approaches to combine data collected across sites.
PURPOSE
To develop a method to harmonize NM-MRI across scanners and sites.
STUDY TYPE
Prospective.
POPULATION
A total of 128 healthy subjects (18-73 years old; 45% female) from three sites and five MRI scanners.
FIELD STRENGTH/SEQUENCE: 3.0 T; NM-MRI two-dimensional gradient-recalled echo with magnetization-transfer pulse and three-dimensional T1-weighted images.
ASSESSMENT
NM-MRI contrast (contrast-to-noise ratio [CNR]) maps were calculated and CNR values within the SN-VTA (defined previously by manual tracing on a standardized NM-MRI template) were determined before harmonization (raw CNR) and after ComBat harmonization (harmonized CNR). Scanner differences were assessed by calculating the classification accuracy of a support vector machine (SVM). To assess the effect of harmonization on biological variability, support vector regression (SVR) was used to predict age and the difference in goodness-of-fit (Δr) was calculated as the correlation (between actual and predicted ages) for the harmonized CNR minus the correlation for the raw CNR.
STATISTICAL TESTS
Permutation tests were used to determine if SVM classification accuracy was above chance level and if SVR Δr was significant. A P-value <0.05 was considered significant.
RESULTS
In the raw CNR, SVM MRI scanner classification was above chance level (accuracy = 86.5%). In the harmonized CNR, the accuracy of the SVM was at chance level (accuracy = 29.5%; P = 0.8542). There was no significant difference in age prediction using the raw or harmonized CNR (Δr = -0.06; P = 0.7304).
DATA CONCLUSION
ComBat harmonization removes differences in SN-VTA CNR across scanners while preserving biologically meaningful variability associated with age.
LEVEL OF EVIDENCE
2 TECHNICAL EFFICACY: 1.
背景
神经黑色素敏感磁共振成像（NM-MRI）是一种经过验证的测量黑质-腹侧被盖区（SN-VTA）复合体中神经黑色素浓度的方法，是多巴胺能功能的替代指标，具有作为非侵入性生物标志物的潜力。通用生物标志物的开发需要大规模样本，因此需要采用协调方法来整合跨站点收集的数据。
目的
开发一种在不同扫描仪和站点之间协调NM-MRI的方法。
研究类型
前瞻性研究。
研究对象
来自三个站点和五台MRI扫描仪的128名健康受试者（年龄18 - 73岁；45%为女性）。
场强/序列：3.0 T；NM-MRI二维梯度回波序列，带有磁化传递脉冲和三维T1加权图像。
评估
计算NM-MRI对比度（对比度噪声比[CNR]）图，并在协调前（原始CNR）和ComBat协调后（协调后的CNR）确定SN-VTA内（先前通过在标准化NM-MRI模板上手动追踪定义）的CNR值。通过计算支持向量机（SVM）的分类准确率来评估扫描仪差异。为了评估协调对生物变异性的影响，使用支持向量回归（SVR）预测年龄，并计算拟合优度差异（Δr），即协调后的CNR的相关性（实际年龄与预测年龄之间）减去原始CNR的相关性。
统计检验
采用置换检验来确定SVM分类准确率是否高于随机水平以及SVR Δr是否显著。P值<0.05被认为具有统计学意义。
结果
在原始CNR中，SVM对MRI扫描仪的分类高于随机水平（准确率 = 86.5%）。在协调后的CNR中，SVM的准确率处于随机水平（准确率 = 29.5%；P = 0.8542）。使用原始或协调后的CNR进行年龄预测没有显著差异（Δr = -0.06；P = 0.7304）。
数据结论
ComBat协调消除了不同扫描仪之间SN-VTA CNR的差异，同时保留了与年龄相关的生物学上有意义的变异性。
证据水平
2 技术效能：1。
Zotero 插件