Harmonization of Multi-Site Neuroimaging Data from Complex Study Designs

协调复杂研究设计中的多部位神经影像数据

• 批准号: 10609841
• 负责人: Russell Takeshi Shinohara
• 金额: $ 60.39万
• 依托单位: UNIVERSITY OF PENNSYLVANIA
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-06-10 至 2024-04-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10609841
• 关键词: Address; Adolescent; Adopted; Adoption; Advocate; Aging; Alzheimer' s Disease; Area; Atrophic; Benchmarking; Biological; Brain; Complex; Computer software; Conceptions; Controlled Study; Cross-Sectional Studies; Data; Data Correlations; Databases; Development; Dwarfism; Federal Government; Functional Magnetic Resonance Imaging; Funding; Gene Expression; Generations; Genomics; Image; Imaging Phantoms; Institution; Intelligence; Investments; Liquid substance; Location; Longevity; Machine Learning; Magnetic Resonance Imaging; Manufacturer; Measurement; Measures; Methodology; Methods; Modeling; Modernization; Multicenter Studies; Multivariate Analysis; Pathology; Pattern; Performance; Phenotype; Privatization; Protocols documentation; Reproducibility; Research Design; Research Methodology; Sex Differences; Site; Statistical Methods; Structure; Techniques; Thick; Travel; United States National Institutes of Health; Work; cognitive development; combat; complex data; data harmonization; data integration; design; gray matter; healthy aging; image reconstruction; imaging modality; imaging study; improved; instrument; interest; mild cognitive impairment; neuroimaging; next generation; novel; personalized predictions; predictive modeling; stem; tool; white matter

PROJECT SUMMARY Over the past decade, the number of large multi-center neuroimaging studies has skyrocketed due to growing investments by federal governments and private entities interested in brain development, aging, and pathology. This has led to the accumulation of vast amounts of magnetic resonance imaging (MRI) data which have been acquired with varying amounts of technical harmonization. Such efforts, which have focused on protocol harmonization and comparisons with imaging phantoms, have shown great strides toward reducing inter- scanner differences in imaging features extracted for further study. Unfortunately, MRI show inter-instrument biases even in the most carefully controlled studies. Our group, among many others, has shown that these differences often dwarf biological differences of interest measured using both structural and functional MRI. To address this, the field has rapidly been developing tools for the harmonization of imaging data after acquisition. We have proposed several such tools, and our work has often focused on the adaptation of methods used in genomic studies for batch effect correction. Our most recent such work involved the ComBat method, which uses empirical Bayesian estimation to correct for site effects in both means and variances of imaging features under study. To date, these tools have been successfully applied in studies of cortical thickness, white matter microstructure, and functional connectivity. However, there are unfortunately several key limitations to the ComBat method for imaging studies that stem from its original conception for gene expression studies. ComBat was designed for the study of inter-scanner differences in cross-sectionally acquired data. While cross-sectional studies are of great interest and exceedingly common, much focus in the context of healthy brain development and aging has shifted to measuring longitudinal trajectories. In such cases, the naïve application of ComBat is flawed and methodological research is necessary for appropriate harmonization tools to be developed. Furthermore, more complex nested study design in which multiple scanners are used per institution, or a subset of subjects are imaged on multiple scanners for harmonization purposes, are increasingly common. Another key area of interest in modern neuroimaging studies is to focus on inter-region structural or functional connectivity and uses multivariate pattern analysis (MVPA) to improve our understanding of phenotypic associations as well as for personalized predictions. Unfortunately, the current state-of-the-art in image harmonization ignores correlation structure between measurements, and thus inter- scanner differences often persist. In this project, we propose a new generation of techniques that are applicable under complex study designs and harmonize appropriately for studies involving applications of MVPA. In our final aim of this proposal, we will apply the methods developed for more complex study designs and MVPA in the context of two of the largest NIH-funded multi-center consortia across the lifespan.

项目总结 在过去的十年里，大型多中心神经成像研究的数量激增，原因是 联邦政府和对大脑发育、衰老和病理学感兴趣的私人实体的投资。 这导致了大量磁共振成像(MRI)数据的积累，这些数据已经 在不同程度的技术协调下获得。这些努力的重点是礼仪 与成像模体的协调和比较，已经显示出在减少相互作用方面取得了很大进展 不同扫描仪提取的影像特征有差异，以供进一步研究。不幸的是，核磁共振显示 即使在最严谨的对照研究中也存在偏见。我们的团队，以及其他许多人，已经证明了这些 差异往往使使用结构和功能MRI测量的感兴趣的生物差异相形见绌。 为解决这一问题，外地一直在迅速开发协调成像数据的工具，在此之后 收购。我们已经提出了几个这样的工具，我们的工作经常集中在对 用于基因组研究的批量效应校正方法。我们最近的这类工作涉及到战斗 方法，该方法使用经验贝叶斯估计来校正场地效应的均值和方差 影像特征正在研究中。到目前为止，这些工具已经成功地应用于大脑皮层的研究 厚度、白质微结构和功能连通性。然而，不幸的是，有几个 影像研究中战斗方法的关键限制源于其最初的基因概念 表达研究。 战斗是为研究横截面采集数据中扫描仪之间的差异而设计的。 虽然横断面研究很有兴趣，也非常常见，但在以下背景下非常关注 健康的大脑发育和衰老已经转向测量纵向轨迹。在这种情况下， 天真地使用战斗是有缺陷的，需要进行方法论研究才能适当地协调一致 待开发的工具。此外，使用多台扫描仪的更复杂的嵌套研究设计 为了协调目的，在多台扫描仪上对每个机构或受试者的子集进行成像 越来越普遍。现代神经影像研究的另一个关键领域是关注区域间 结构或功能连接，并使用多变量模式分析(MVPA)改善我们的 对表型关联以及个性化预测的理解。不幸的是，目前的情况 图像协调中的最新技术忽略了测量之间的相关性结构，因此 扫描仪的差异经常存在。 在这个项目中，我们提出了适用于复杂研究的新一代技术。 适当地设计和协调涉及MVPA应用的研究。在我们的最终目标中 建议，我们将把为更复杂的研究设计和MVPA开发的方法应用于 美国国立卫生研究院资助的两个最大的多中心财团。

项目成果

Harmonization of multi-site functional connectivity measures in tangent space improves brain age prediction.

切线空间中多站点功能连接测量的协调可以改善大脑年龄的预测。

• DOI: 10.1117/12.2611557
• 发表时间: 2022
• 期刊: Proceedings of SPIE--the International Society for Optical Engineering
• 作者: Zhou,Zhen;Srinivasan,Dhivya;Li,Hongming;Abdulkadir,Ahmed;Shou,Haochang;Davatzikos,Christos;Fan,Yong;ISTAGINGConsortium
• 通讯作者: ISTAGINGConsortium

Harmonizing functional connectivity reduces scanner effects in community detection.

协调功能连通性会降低扫描仪在社区检测中的影响。

• DOI: 10.1016/j.neuroimage.2022.119198
• 发表时间: 2022-08-01
• 期刊: NeuroImage
• 影响因子: 5.7
• 作者: Chen AA;Srinivasan D;Pomponio R;Fan Y;Nasrallah IM;Resnick SM;Beason-Held LL;Davatzikos C;Satterthwaite TD;Bassett DS;Shinohara RT;Shou H
• 通讯作者: Shou H

AI-based dimensional neuroimaging system for characterizing heterogeneity in brain structure and function in major depressive disorder: COORDINATE-MDD consortium design and rationale.

• DOI: 10.1186/s12888-022-04509-7
• 发表时间: 2023-01-23
• 期刊: BMC psychiatry
• 影响因子: 4.4

Sensitivity of portable low-field magnetic resonance imaging for multiple sclerosis lesions.

• DOI: 10.1016/j.nicl.2022.103101
• 发表时间: 2022
• 期刊: NEUROIMAGE-CLINICAL
• 影响因子: 4.2
• 作者: Arnold, Campbell;Tu, Danni;Okar, Serhat, V;Nair, Govind;By, Samantha;Kawatra, Karan D.;Robert-Fitzgerald, Timothy E.;Desiderio, Lisa M.;Schindler, Matthew K.;Shinohara, Russell T.;Reich, Daniel S.;Stein, Joel M.
• 通讯作者: Stein, Joel M.

Mitigating site effects in covariance for machine learning in neuroimaging data.

• DOI: 10.1002/hbm.25688
• 发表时间: 2022-03
• 期刊: Human brain mapping
• 影响因子: 4.8
• 作者: Chen AA;Beer JC;Tustison NJ;Cook PA;Shinohara RT;Shou H;Alzheimer's Disease Neuroimaging Initiative
• 通讯作者: Alzheimer's Disease Neuroimaging Initiative