[论文解读] The Reconfiguration Pattern of Individual Brain Metabolic Connectome for Parkinson's Disease Identification

Weikai Li, Yongxiang Tang+3 more|arXiv (Cornell University)|Apr 29, 2021

Parkinson's Disease Mechanisms and Treatments参考文献 49被引用 11

一句话总结

本研究提出了一种基于18F-FDG PET数据和Jensen-Shannon散度相似性估计（JSSE）的新型个体水平脑代谢连接组方法，用于在个体水平上识别帕金森病（PD）。该方法揭示了代谢网络中的特定重组模式，特别是在PUT-PCG、THA-PCG、SMA、ACG-PCL、DCG-PHG和ACG通路中，并利用MK-SVM分类方法在区分PD患者与健康对照组时实现了91.84%的准确率。

ABSTRACT

Background: Positron Emission Tomography (PET) with 18F-fluorodeoxyglucose (18F-FDG) reveals metabolic abnormalities in Parkinson's disease (PD) at a systemic level. Previous metabolic connectome studies derived from groups of patients have failed to identify the individual neurophysiological details. We aim to establish an individual metabolic connectome method to characterize the aberrant connectivity patterns and topological alterations of the individual-level brain metabolic connectome and their diagnostic value in PD. Methods: The 18F-FDG PET data of 49 PD patients and 49 healthy controls (HCs) were recruited. Each individual's metabolic brain network was ascertained using the proposed Jensen-Shannon Divergence Similarity Estimation (JSSE) method. The intergroup difference of the individual's metabolic brain network and its global and local graph metrics were analyzed to investigate the metabolic connectome's alterations. The identification of the PD from HC individuals was used by the multiple kernel support vector machine (MK-SVM) to combine the information from connection and topological metrics. The validation was conducted using the nest leave-one-out cross-validation strategy to confirm the performance of the methods. Results: The proposed JSSE metabolic connectome method showed the most involved metabolic motor networks were PUT-PCG, THA-PCG, and SMA pathways in PD, which was similar to the typical group-level method, and yielded another detailed individual pathological connectivity in ACG-PCL, DCG-PHG and ACG pathways. These aberrant functional network measures exhibited an ideal classification performance in the identifying of PD individuals from HC individuals at an accuracy of up to 91.84%.

研究动机与目标

• 为克服群体水平代谢连接组研究的局限性，实现帕金森病（PD）个体水平脑代谢网络的分析。
• 利用18F-FDG PET数据识别个体PD患者中的异常连接模式和拓扑结构改变。
• 开发一种整合连接水平和拓扑度量的稳健诊断框架，用于个体PD的识别。
• 通过严格的交叉验证验证该方法的性能，并评估其在早期PD检测中的临床潜力。

提出的方法

• 采用Jensen-Shannon散度相似性估计（JSSE）方法，从18F-FDG PET数据构建个体脑代谢连接组。
• 将每个个体的代谢网络建模为图结构，脑区作为节点，脑区间代谢相似性作为加权边。
• 计算图度量——包括全局度量（如效率、模块性）和局部度量（如度数、介数）——以量化拓扑结构的改变。
• 采用多核支持向量机（MK-SVM）整合连接水平和拓扑特征，以提升分类性能。
• 采用嵌套留一法交叉验证策略，以验证模型的诊断准确率和泛化能力。
• 该方法强调个体特异性重组模式，而非群体平均效应，从而增强对细微病理改变的敏感性。

实验结果

研究问题

• RQ1 与健康对照相比，帕金森病患者中哪些个体水平的代谢网络重组模式最为显著？
• RQ2 PD患者与健康对照在个体脑代谢网络的拓扑度量上存在哪些差异？
• RQ3 结合个体代谢连接组的连接水平和拓扑特征，能否可靠地区分PD患者与健康个体？
• RQ4 该方法在使用交叉验证分类个体PD病例时的诊断性能如何？
• RQ5 哪些特定代谢通路在PD中表现出最显著的重组？它们与已知的运动和认知环路有何关联？

主要发现

• 基于JSSE的个体代谢连接组方法成功识别出PD中的关键病理重组模式，包括PUT-PCG、THA-PCG和SMA通路。
• 在ACG-PCL、DCG-PHG和ACG通路中还检测到个体特异性的异常连接，提示此前未被充分认识的网络破坏。
• MK-SVM分类器在利用个体连接组特征区分PD患者与健康对照时，实现了91.84%的分类准确率。
• 全局和局部图度量显示出显著的组间差异，PD患者表现出网络效率和整合模式的改变。
• 嵌套留一法交叉验证证实了该诊断模型在个体受试者中的稳健性和泛化能力。
• 结果表明，个体水平的代谢连接组分析比群体水平方法能捕捉到更细微的病理特征。