Machine Learning and Large-scale Imaging analytics for dimensional representations of brain trajectories in aging and preclinical Alzheimer's Disease: The brain aging chart and the iSTAGING consortium

摘要 父母补助金一直在建立一个真正独特的MRI，临床和认知数据库， 65，000人和16项不同的研究。它一直在构建机器学习模型， 生物标志物，旨在捕捉大脑老化的异质性，并推导出认知功能的预测模型。 下降目前的补充将建立基础，使这些管道非常容易 通过云计算。更具体地说，这一补充的重点将是建设基础设施 用于在AWS云上运行的基于Web的门户，这将允许MRI的无缝“拖放” 用于应用由父程序开发的管道。这将有助于广泛获得 这些管道，而无需设置本地软件和熟悉复杂的预处理， MRI数据集和机器学习管道。

Abstract The parent grant has been building a truly unique database of MRI, clinical and cognitive data from over 65,000 individuals and 16 distinct studies. It has been constructing machine learning models and biomarkers aiming to capture the heterogeneity of brain aging and derive predictive models of cognitive decline. The current supplement will build the foundation for making these pipelines available very easily through cloud computing. More specifically, the focus of this supplement will be to build the infrastructure for a web-based portal running n the AWS cloud, which will allow for seamless “drag-and-drop” of MRIs for application of the pipelines developed by the parent program. This will facilitate the wide access of these pipelines without the need to set up local software and familiarize with complex preprocessing of MRI datasets and machine learning pipelines.