背景:原发性震颤(ET)和肌张力震颤(DT)是两种最常见的震颤疾病,由于类似的震颤症状,误诊非常常见。在这项研究中,我们使用脑灰质(GM)形态网络探索ET和DT的结构网络机制,并将其与机器学习模型相结合。
方法:75例ET患者的3D-T1结构图像,71例DT患者,获得79名健康对照(HCs)。我们使用基于体素的形态计量学来获得GM图像,并基于基于Kullback-Leibler散度的相似性(KLS)方法构建了GM形态网络。我们用了转基因卷,形态关系,GM-KLS形态网络的全局拓扑特性作为输入特征。我们使用了三个分类器来执行分类任务。此外,我们对鉴别特征和临床特征进行了相关分析.
结果:确定了16个形态关系特征和1个全局拓扑度量为判别特征,主要累及小脑-丘脑-皮层回路和基底节区。随机森林(RF)分类器在三分类任务中取得了最好的分类性能,达到78.7%的平均准确度(mACC),并随后用于二元分类任务。具体来说,RF分类器在区分ET与ET方面表现出强大的分类性能HC,ETvs.DT,和DTvs.HC,MCCs为83.0%,95.2%,和89.3%,分别。相关分析表明,4个鉴别特征与临床特征显著相关。
结论:这项研究为ET和DT的结构网络机制提供了新的见解。它证明了将GM-KLS形态网络与机器学习模型相结合来区分ET的有效性,DT,和HCs。
BACKGROUND: Essential tremor (ET) and dystonic tremor (DT) are the two most common tremor disorders, and misdiagnoses are very common due to similar tremor symptoms. In this study, we explore the structural network mechanisms of ET and DT using brain grey matter (GM) morphological networks and combine those with machine learning models.
METHODS: 3D-T1 structural images of 75 ET patients, 71 DT patients, and 79 healthy controls (HCs) were acquired. We used voxel-based morphometry to obtain GM images and constructed GM morphological networks based on the Kullback-Leibler divergence-based similarity (KLS) method. We used the GM volumes, morphological relations, and global topological properties of GM-KLS morphological networks as input features. We employed three classifiers to perform the classification tasks. Moreover, we conducted correlation analysis between discriminative features and clinical characteristics.
RESULTS: 16 morphological relations features and 1 global topological metric were identified as the discriminative features, and mainly involved the cerebello-thalamo-cortical circuits and the basal ganglia area. The Random Forest (RF) classifier achieved the best classification performance in the three-classification task, achieving a mean accuracy (mACC) of 78.7%, and was subsequently used for binary classification tasks. Specifically, the RF classifier demonstrated strong classification performance in distinguishing ET vs. HCs, ET vs. DT, and DT vs. HCs, with mACCs of 83.0 %, 95.2 %, and 89.3 %, respectively. Correlation analysis demonstrated that four discriminative features were significantly associated with the clinical characteristics.
CONCLUSIONS: This study offers new insights into the structural network mechanisms of ET and DT. It demonstrates the effectiveness of combining GM-KLS morphological networks with machine learning models in distinguishing between ET, DT, and HCs.