Ellis Charles A, Miller Robyn L, Calhoun Vince D
Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, GA, United States.
Tri-institutional Center for Translational Research in Neuroimaging and Data Science, Georgia State University, Atlanta, GA, United States.
Front Psychiatry. 2024 Feb 15;15:1165424. doi: 10.3389/fpsyt.2024.1165424. eCollection 2024.
Dynamic functional network connectivity (dFNC) analysis of resting state functional magnetic resonance imaging data has yielded insights into many neurological and neuropsychiatric disorders. A common dFNC analysis approach uses hard clustering methods like k-means clustering to assign samples to states that summarize network dynamics. However, hard clustering methods obscure network dynamics by assuming (1) that all samples within a cluster are equally like their assigned centroids and (2) that samples closer to one another in the data space than to their centroids are well-represented by their centroids. In addition, it can be hard to compare subjects, as in some cases an individual may not manifest a state strongly enough to enter a hard cluster. Approaches that allow a dimensional approach to connectivity patterns (e.g., fuzzy clustering) can mitigate these issues. In this study, we present an explainable fuzzy clustering framework by combining fuzzy c-means clustering with several explainability metrics and novel summary features.
We apply our framework for schizophrenia (SZ) default mode network analysis. Namely, we extract dFNC from individuals with SZ and controls, identify 5 dFNC states, and characterize the dFNC features most crucial to those states with a new perturbation-based clustering explainability approach. We then extract several features typically used in hard clustering and further present a variety of unique features specially designed for use with fuzzy clustering to quantify state dynamics. We examine differences in those features between individuals with SZ and controls and further search for relationships between those features and SZ symptom severity.
Importantly, we find that individuals with SZ spend more time in states of moderate anticorrelation between the anterior and posterior cingulate cortices and strong anticorrelation between the precuneus and anterior cingulate cortex. We further find that individuals with SZ tend to transition more rapidly than controls between low-magnitude and high-magnitude dFNC states.
We present a novel dFNC analysis framework and use it to identify effects of SZ upon network dynamics. Given the ease of implementing our framework and its enhanced insight into network dynamics, it has great potential for use in future dFNC studies.
静息态功能磁共振成像数据的动态功能网络连接性（dFNC）分析为许多神经和神经精神疾病提供了见解。一种常见的dFNC分析方法使用硬聚类方法，如k均值聚类，将样本分配到总结网络动态的状态。然而，硬聚类方法通过假设（1）一个聚类中的所有样本与其分配的质心具有同等相似性，以及（2）在数据空间中彼此比其质心更接近的样本由其质心很好地表示，从而掩盖了网络动态。此外，比较受试者可能会很困难，因为在某些情况下，个体可能没有强烈表现出足以进入硬聚类的状态。允许采用维度方法处理连接模式的方法（例如模糊聚类）可以缓解这些问题。在本研究中，我们通过将模糊c均值聚类与几种可解释性度量和新颖的汇总特征相结合，提出了一个可解释的模糊聚类框架。
我们将我们的框架应用于精神分裂症（SZ）默认模式网络分析。具体而言，我们从SZ患者和对照组个体中提取dFNC，识别5种dFNC状态，并使用一种新的基于扰动的聚类可解释性方法来表征对这些状态最关键的dFNC特征。然后，我们提取硬聚类中通常使用的几个特征，并进一步提出各种专门为模糊聚类设计的独特特征，以量化状态动态。我们检查SZ患者和对照组个体之间这些特征的差异，并进一步寻找这些特征与SZ症状严重程度之间的关系。
重要的是，我们发现SZ患者在前扣带回和后扣带回之间处于中度反相关状态以及楔前叶和前扣带回皮质之间处于强反相关状态的时间更多。我们还进一步发现，SZ患者在低强度和高强度dFNC状态之间的转换往往比对照组更快。
我们提出了一个新颖的dFNC分析框架，并使用它来识别SZ对网络动态的影响。鉴于我们的框架易于实施且对网络动态有更强的洞察力，它在未来的dFNC研究中有很大的应用潜力。
