Acquisition-independent machine learning for morphometric analysis of underrepresented aging populations with clinical and low-field brain MRI

独立于采集的机器学习，通过临床和低场脑 MRI 对代表性不足的老龄化人群进行形态计量分析

• 批准号: 10739049
• 负责人: Juan Eugenio Iglesias Gonzalez
• 金额: $ 243.5万
• 依托单位: MASSACHUSETTS GENERAL HOSPITAL
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-09-01 至 2026-08-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10739049
• 关键词: Aging; Alzheimer' s Disease; Alzheimer' s disease related dementia; Alzheimer' s disease risk; Archives; Artificial Intelligence; Asian population; Atrophic; Biology; Black Populations; Black race; Brain; Brain imaging; Brain scan; Clinic; Clinical; Clinical Data; Clinical Research; Code; Companions; Computational algorithm; Computer software; Data; Data Set; Dedications; Dementia; Democracy; Detection; Developing Countries; Disease; Disparity; Documentation; Enrollment; General Hospitals; Hispanic; Hispanic Populations; Hospitals; Human; Image; Joints; Lesion; Licensing; MRI Scans; Machine Learning; Magnetic Resonance Imaging; Massachusetts; Measurement; Medically Underserved Area; Metadata; Methods; Minority; Modeling; Modernization; Nerve Degeneration; Nigeria; Noise; Outcome; Pathology; Physicians; Physiologic pulse; Play; Policies; Population; Population Heterogeneity; Positioning Attribute; Process; Randomized; Reduce health disparities; Research; Research Personnel; Resolution; Retrospective Studies; Role; Safety; Sample Size; Sampling; Scanning; Signal Transduction; Site; Slice; Socioeconomic Factors; Source; System; Thick; Training; Uncertainty; Underrepresented Populations; Visual; Work; biobank; brain magnetic resonance imaging; cohort; cost; data sharing; deep learning; disorder subtype; diverse data; ethnic diversity; ethnoracial; health care availability; healthy aging; heterogenous data; high resolution imaging; improved; in vivo; longitudinal analysis; low and middle-income countries; machine learning algorithm; machine learning method; medically underserved; medically underserved population; meetings; morphometry; multimodal data; neural network; neuroimaging; normal aging; open source; portability; prevent; prospective; quantitative imaging; research study; rural area; tool; ultra high resolution; underserved area; usability; white matter

Project Summary Title: Acquisition-independent machine learning for morphometric analysis of underrepresented aging populations with clinical and low-field brain MRI Summary: Magnetic resonance imaging (MRI) has revolutionized research of the human brain, by providing a window to the living brain in healthy aging and disease. A key aspect of this revolution has been the ability to obtain precise morphometric measurements from brain MRI using software packages like FreeSurfer (developed by our lab), FSL, AFNI, or SPM. These packages rely on computer algorithms that work best with isotropic data, 1 mm MP-RAGE scans. Unfortunately, clinical scans are generally highly anisotropic (e.g., 6 mm spacing between slices), precluding automatic morphometric analysis with the aforementioned packages. Images acquired with portable and non-portable low-field scanners also suffer from the same limitation. The inability to process clinical MRI prevents the extraction of precise morphometric measurements from MRI studies in the clinic (quantitative imaging), as well as from low-field scans that may be the only imaging alternative in medically underserved regions, e.g., rural areas or developing countries. Crucially, this inability also precludes the analysis of millions of scans that are sitting in the PACS of hospitals around the world, including large amounts of images and associated clinical metadata from populations that are typically underrepresented in neuroimaging studies (e.g., Black, Hispanic), thus hindering progress in aging research. In this project, we propose to develop AI methods that can turn clinical or low-field MRI into isotropic scans of reference contrast (a 1 mm MP-RAGE). Importantly, the methods will: (i) be adaptive to the number of input MR sequences, as well as their orientation, contrast and resolution; (ii) be robust against aging-related pathology (atrophy, white matter lesions); and (iii) not require retraining. These features will enable application any MR dataset without specialized hardware or machine learning expertise. The resulting synthetic scans can be used for a wide array of existing morphometrics analyses, e.g., segmentation, volumetry, registration, longitudinal analysis, cortical thickness and parcellation, and many more. Another key feature of the framework is the fact that it yields harmonized images, which reduces bias across sites and pulse sequences. We will validate the tools with: (i) synthetically downsampled scans from a number of public datasets covering a diverse population; and (ii) a dedicated, diverse, comprehensive dataset of multi-modal MRI, comprising paired research, clinical and low-field scans, acquired specifically for this project. We will carefully assess the biases in our developed tools and try to mitigate them. We will apply the final version of the tools to a large-scale study of a clinical aging cohort from Massachusetts General Hospital, as well as to two clinical studies with portable MRI. Both the tools and the new dataset will be made publicly through FreeSurfer (60,000 worldwide licenses), thus enabling researchers worldwide to analyze large clinical datasets with sample sizes much higher than those achieved in current research studies. Therefore, our tools promise to increase our understanding of the human brain in normal aging and in disease, particularly in underrepresented populations.

项目概要 标题： 用于对代表性不足的老龄化人群进行形态计量分析的独立于采集的机器学习 临床和低场脑部 MRI 概括： 磁共振成像 (MRI) 彻底改变了人类大脑的研究，提供了一个窗口 健康衰老和疾病中的活大脑。这场革命的一个关键方面是能够获得 使用 FreeSurfer（由 我们的实验室）、FSL、AFNI 或 SPM。这些软件包依赖于最适合各向同性数据的计算机算法， 1 毫米 MP-RAGE 扫描。不幸的是，临床扫描通常具有高度各向异性（例如，6 毫米间距 切片之间），排除使用上述软件包进行自动形态分析。图片 使用便携式和非便携式低场扫描仪采集的图像也受到同样的限制。 无法处理临床 MRI 阻碍了从患者中提取精确的形态测量值 临床中的 MRI 研究（定量成像）以及可能是唯一成像的低场扫描 医疗服务匮乏地区的替代方案，例如农村地区或发展中国家。至关重要的是，这种无能 还无法对世界各地医院 PACS 中的数百万张扫描进行分析， 包括来自通常人群的大量图像和相关临床元数据 在神经影像学研究中代表性不足（例如黑人、西班牙裔），从而阻碍了衰老研究的进展。 在这个项目中，我们建议开发人工智能方法，将临床或低场 MRI 转化为各向同性扫描 参考对比度（1 mm MP-RAGE）。重要的是，这些方法将：（i）适应输入的数量 MR 序列及其方向、对比度和分辨率； (ii) 有效应对与衰老相关的问题 病理学（萎缩、白质病变）； (iii) 不需要再培训。这些功能将使应用程序 无需专门硬件或机器学习专业知识的任何 MR 数据集。生成的合成扫描可以 可用于各种现有的形态测量分析，例如分割、体积分析、配准、 纵向分析、皮质厚度和分割等等。该框架的另一个关键特性 事实上，它可以产生协调的图像，从而减少站点和脉冲序列之间的偏差。 我们将通过以下方式验证这些工具：（i）从多个公共数据集中进行综合下采样扫描 覆盖不同的人群； (ii) 专用、多样化、综合的多模态 MRI 数据集， 包括专门为本项目获取的配对研究、临床和低场扫描。我们会用心 评估我们开发的工具中的偏差并尝试减轻它们。我们将应用该工具的最终版本 来自马萨诸塞州总医院的一项针对临床老龄化队列的大规模研究，以及两项临床研究 使用便携式 MRI 进行研究。这些工具和新数据集都将通过 FreeSurfer 公开（60,000 全球许可证），从而使世界各地的研究人员能够分析具有样本量的大型临床数据集 远高于当前研究取得的成果。因此，我们的工具有望提高我们的 了解人类大脑在正常衰老和疾病中的作用，特别是在代表性不足的人群中。