Department of Psychology, University of Otago, 9016, New Zealand.
Department of Information Science, University of Otago, 9016, New Zealand.
Neuroimage. 2022 Nov;263:119588. doi: 10.1016/j.neuroimage.2022.119588. Epub 2022 Aug 31.
Capturing individual differences in cognition is central to human neuroscience. Yet our ability to estimate cognitive abilities via brain MRI is still poor in both prediction and reliability. Our study tested if this inability can be improved by integrating MRI signals across the whole brain and across modalities, including task-based functional MRI (tfMRI) of different tasks along with other non-task MRI modalities, such as structural MRI, resting-state functional connectivity. Using the Human Connectome Project (n = 873, 473 females, after quality control), we directly compared predictive models comprising different sets of MRI modalities (e.g., seven tasks vs. non-task modalities). We applied two approaches to integrate multimodal MRI, stacked vs. flat models, and implemented 16 combinations of machine-learning algorithms. The stacked model integrating all modalities via stacking Elastic Net provided the best prediction (r = 0.57), relatively to other models tested, as well as excellent test-retest reliability (ICC=∼.85) in capturing general cognitive abilities. Importantly, compared to the stacked model integrating across non-task modalities (r = 0.27), the stacked model integrating tfMRI across tasks led to significantly higher prediction (r = 0.56) while still providing excellent test-retest reliability (ICC=∼.83). The stacked model integrating tfMRI across tasks was driven by frontal and parietal areas and by tasks that are cognition-related (working-memory, relational processing, and language). This result is consistent with the parieto-frontal integration theory of intelligence. Accordingly, our results contradict the recently popular notion that tfMRI is not reliable enough to capture individual differences in cognition. Instead, our study suggests that tfMRI, when used appropriately (i.e., by drawing information across the whole brain and across tasks and by integrating with other modalities), provides predictive and reliable sources of information for individual differences in cognitive abilities, more so than non-task modalities.
捕捉认知个体差异是人类神经科学的核心。然而，我们通过脑 MRI 来估计认知能力的能力在预测和可靠性方面仍然很差。我们的研究测试了通过整合整个大脑和多种模态的 MRI 信号，包括不同任务的基于任务的功能 MRI（tfMRI）以及其他非任务 MRI 模态，例如结构 MRI、静息态功能连接，是否可以改善这种能力不足。使用人类连接组计划（n=873，473 名女性，经过质量控制），我们直接比较了包含不同 MRI 模态集的预测模型（例如，七种任务与非任务模态）。我们应用了两种方法来整合多模态 MRI，堆叠与平面模型，并实现了 16 种机器学习算法的组合。通过堆叠弹性网络整合所有模态的堆叠模型提供了最佳预测（r=0.57），与其他测试模型相比，以及在捕捉一般认知能力方面具有出色的测试-重测可靠性（ICC≈.85）。重要的是，与整合非任务模态的堆叠模型（r=0.27）相比，整合任务 tfMRI 的堆叠模型导致了更高的预测（r=0.56），同时仍提供了出色的测试-重测可靠性（ICC≈.83）。整合任务 tfMRI 的堆叠模型由额顶区和与认知相关的任务（工作记忆、关系处理和语言）驱动。这一结果与智力的顶-额整合理论一致。因此，我们的结果与最近流行的观点相矛盾，即 tfMRI 不足以可靠地捕捉认知个体差异。相反，我们的研究表明，tfMRI 提供了预测和可靠的信息来源，可以捕捉认知能力的个体差异，尤其是在与其他模态整合时，通过在整个大脑和任务之间提取信息。
