基于高序最小生成树的磁共振成像分类方法

Magnetic resonance imaging classification method based on high-order minimum spanning tree

为解决现有脑网络构建方法存在的不足,研究功能连接的动态特性,改进之前研究提出的高序功能连接网络的构建方法,提出一种构建高序最小生成树功能连接网络的方法,将时变特性考虑到固有的功能连接网络中,保证网络在神经学上的可解释性,相比传统的功能连接网络,高序最小生成树功能连接网络揭示了更高层次的和更复杂的交互关系。提出基于高序最小生成树功能连接网络的静息态功能磁共振成像分类方法,与现有的分类方法进行比较,分类结果表明,基于高序最小生成树的磁共振成像分类方法提高了抑郁症检测的准确率。

To solve the problems existing in the method of constructing the human brain network,the dynamic characteristics of the functional connectivity were studied,and the method of constructing the high-order minimum spanning tree functional connectivity network was put forward.The time-varying characteristics were taken into account in the inherent functional connectivity network,and the neurological interpretation of the network was guaranteed.Compared to traditional functional connectivity networks,the high-order minimum spanning tree functional connectivity network can reveal higher levels and more complex interactions.At the same time,a classification method of resting-state functional magnetic resonance imaging based on high-order minimum spanning tree functional connectivity network was proposed.The classification results were compared with the existing classification methods.The classification results show magnetic resonance imaging classification method based on high-order minimum spanning tree greatly improves the accuracy of depression detection.