基于近端梯度网络的脑组织微结构参数估计方法  

Brain tissue microstructure parameters estimation method based on proximal gradient network

作　　者：徐永红[1] 王朋飞 丁玲 XU Yonghong;WANG Pengfei;DING Ling(Institute of Electric Engineering,Yanshan University,Qinhuangdao,Hebei 066004,P.R.China)

机构地区：[1]燕山大学电气工程学院,河北秦皇岛066004

出　　处：《生物医学工程学杂志》2021年第2期333-341,共9页Journal of Biomedical Engineering

基　　金：国家自然科学基金资助项目(60873121)。

摘　　要：扩散张量成像技术能提供脑白质信息,可用于探究脑区组织结构变化,但缺乏对脑组织微结构信息的特异性描述。神经突起方向离散度与密度成像模型弥补了其不足,但获取脑组织微结构的准确估计参数需要大量的扩散梯度,同时通过最大似然拟合,整个过程计算复杂、消耗时间长。为此本文提出了一种基于近端梯度网络估计微结构参数的方法,进一步避免了经典的拟合范式。该方法能够在减少扩散梯度数量的情况下,仍能够准确估计参数,实现成像质量优于神经突起方向离散度与密度成像模型和通过凸优化加速微观结构成像模型的目的。Diffusion tensor imaging technology can provide information on the white matter of the brain,which can be used to explore changes in brain tissue structure,but it lacks the specific description of the microstructure information of brain tissue.The neurite orientation dispersion and density imaging make up for its shortcomings.But in order to accurately estimate the brain microstructure,a large number of diffusion gradients are needed,and the calculation is complex and time-consuming through maximum likelihood fitting.Therefore,this paper proposes a kind of microstructure parameters estimation method based on the proximal gradient network,which further avoids the classic fitting paradigm.The method can accurately estimate the parameters while reducing the number of diffusion gradients,and achieve the purpose of imaging quality better than the neurite orientation dispersion and density imaging model and accelerated microstructure imaging via convex optimization model.

关 键 词：神经突起方向离散度与密度成像 神经网络 组织微结构 扩散磁共振成像 

分 类 号：R445.2[医药卫生—影像医学与核医学]