Age-related changes in brain connectivity and cognition studied through machine learning

通过机器学习研究与年龄相关的大脑连接和认知变化

• 批准号: 2746405
• 金额: --
• 依托单位: University of Nottingham
• 依托单位国家: 英国
• 项目类别: Studentship
• 财政年份: 2022
• 资助国家: 英国
• 起止时间: 2022 至 无数据
• 项目状态: 未结题
• 来源: https://gtr.ukri.org/projects?ref=studentship-2746405
• 关键词: Age; related; changes; brain; connectivity

The PhD project aims to study how the brain/cognition relationship changes across the lifespan, using an open data archive containing neuroimaging data from 600+ participants (http://www.cam-can.org/). The project will combine information obtained with multiple brain imaging methods: (1) functional MRI (fMRI), which measures brain activity indirectly through its effects on blood vessels; (2) magnetoencephalography (MEG), which measures the magnetic field around the head generated by brain activity as a direct measure of neural activation; and (3) diffusion-weighted MRI (DWI), which measures the anatomical "wiring" of the brain. Due to the combination of methods, the planned approach goes beyond earlier - mostly (f)MRI-based - research on age-related brain changes (Sowell et al. Nature Neurosci 2003; Salat al. Cereb Cortex 2004; Dosenbach et al. Science 2010). The inclusion of MEG adds a method with high temporal resolution that can reveal co-existing resting-state networks in multiple frequency ranges (Hillebrand et al. 2012). Machine learning will be used to determine which aspects of brain networks (across all imaging modalities studied) best predict individual cognitive ability. Finally, we will use this approach to test existing theories of how brain networks reorganize with age, with hypotheses about age-related changes of brain lateralization (Cabeza et al. Psychol Ageing 2002) and about shifts between anterior and posterior brain activation (Davis et al. Cereb Cortex 2008). For the PhD candidate, basic Matlab or Python programming skills and a quantitative background (physics, mathematics, computer science or engineering) are desirable. The supervisory team combines expertise in MEG/EEG analysis, structural and functional MRI analysis, and machine learning on large datasets obtained from open data archives.Suggested reading: Geerligs et al., (2018) Neurobiol Aging. 72:106-120 doi: 10.1016/j.neurobiolaging.2018.07.025 Mandke et al. (2017) Neuroimage 166:371-384 https://doi.org/10.1016/j.neuroimage.2017.11.016

博士项目旨在研究大脑/认知关系在整个生命周期中的变化，使用包含600多名参与者(http://www.cam-can.org/).)的神经成像数据的开放数据档案该项目将结合多种脑成像方法获得的信息：(1)功能磁共振成像(FMRI)，通过其对血管的影响间接测量大脑活动；(2)脑磁图(MEG)，测量大脑活动产生的头部周围磁场，作为神经激活的直接测量；以及(3)弥散加权磁共振成像(DWI)，测量大脑的解剖“线路”。由于方法的结合，计划中的方法超越了早期-主要是(F)基于磁共振的-年龄相关脑变化的研究(Sowell等人。自然神经科学，2003年；萨拉特等人。大脑皮层，2004年；Dosenbach等人。科学2010年)。脑磁图的加入增加了一种具有高时间分辨率的方法，可以在多个频率范围内揭示共存的休眠状态网络(Hillebrand等人。2012年)。机器学习将被用来确定大脑网络的哪些方面(在所有研究的成像方式中)最能预测个人的认知能力。最后，我们将使用这种方法来测试现有的关于大脑网络如何随着年龄重组的理论，以及关于大脑偏侧化与年龄相关的变化的假设(Cabeza等人。心理老化2002)和大脑前部和后部活动之间的转换(Davis等人。大脑皮层2008年)。对于博士生来说，需要具备基本的MatLab或Python语言编程技能和量化背景(物理、数学、计算机科学或工程学)。监管团队结合了脑磁图/脑电分析、结构和功能核磁共振分析以及对从开放数据档案获得的大数据集进行机器学习的专业知识。建议阅读：Geerrigs等人，(2018)Neurobiol Aging。72：106-120DOI：10.1016/j.urobioling.2018.07.025 Mandke et al.(2017)神经影像166：371-384 https://doi.org/10.1016/j.neuroimage.2017.11.016