论文部分内容阅读
慢性精神分裂症患者大脑的结构和功能异常已经被广泛报道,但是首发未用药精神分裂症患者和正常人的相关研究较少。本研究采集了44名首发未用药精神分裂症患者和56名正常人的结构和静息态功能磁共振图像,基于自动解剖标签模板提取了90个感兴趣区域的灰质体积、局部一致性、低频振荡振幅和度中心度作为特征,并将这些特征作为输入,用基于递归特征消除的支持向量机对首发未用药精神分裂症患者和正常人进行分类。结果表明,局部一致性和低频振荡振幅的组合为最佳分类特征,分类准确率达到96.97%,并且分类权重最大的脑区主要位于额叶。研究结果有利于加深对精神分裂症神经病理机制的了解,有助于开发出用于临床辅助诊断的生物学标记物。
Structural and functional abnormalities in the brain of patients with chronic schizophrenia have been widely reported, but few studies have been reported on naïve and schizophrenic patients. In this study, structural and resting functional magnetic resonance images of 44 patients with first-episode unmedicated schizophrenia and 56 normal controls were collected. Gray matter volume, local consistency, low frequency Oscillation amplitude and degree of center as the features, and these features as input, using recursive feature-based support vector machine to classify the first-time non-medication schizophrenia patients and normal subjects. The results show that the combination of local consistency and low frequency oscillation amplitude is the best classification feature, the classification accuracy is 96.97%, and the brain area with the largest classification weight is located in the frontal lobe. The results are helpful to deepen the understanding of the neuropathological mechanism of schizophrenia and help to develop biomarkers for clinical diagnosis.