A two-level multimodality imaging Bayesian network approach for classification of partial epilepsy: preliminary data.
A two-level multimodality imaging Bayesian network approach for classification of partial epilepsy: preliminary data.
复制标题
用于部分性癫痫分类的两级多模态成像贝叶斯网络方法：初步数据。
DOI：
10.1016/j.neuroimage.2013.01.014
复制
发表时间：
2013
期刊：
影响因子：
5.7
通讯作者：
Laxer,KennethD
中科院分区：
文献类型：
--
作者：
Mueller,SusanneG;Young,Karl;Hartig,Miriam;Barakos,Jerome;Garcia,Paul;Laxer,KennethD
背景定量神经影像分析已证明不同类型非病变部分性癫痫的组比较中灰质和白质异常。目前尚不清楚这些类型特异性模式在个体患者中存在的程度以及是否可以将其用于诊断目的。在本研究中，提出了一种两级多模态成像贝叶斯网络方法，该方法使用有关个体灰质体积损失和白质完整性的信息对伴有（TLE-MTS）和不伴有（TLE-no）内侧颞叶硬化和额叶癫痫（FLE）的非病变颞叶癫痫进行分类。方法将25名对照者、19名TLE-MTS、22名TLE-no和14名FLE进行分类 研究了获得的 4T MRI 和 T1 加权结构和 DTI 图像。计算每个受试者的空间归一化灰质 (GM) 和分数各向异性 (FA) 异常图（体素低于对照平均值 1 SD 的二进制图）。在第一级，使用基于图形模型的形态分析（GAMMA）将每组的异常图与所有其他组的异常图进行比较。 GAMMA 使用贝叶斯网络和基于马尔可夫随机场的上下文聚类方法来生成体素图，提供两组之间的最大区别，并根据此信息计算概率分布和组分配。然后将信息合并到二级贝叶斯网络中，并计算每个受试者属于三种癫痫类型之一的概率。 结果 二级贝叶斯网络区分三个患者组的特异性为 TLE-MTS 和 TLE-no 为 0.87，FLE 为 0.86，相应的敏感性为 TLE-MTS 0.84，TLE-no 为 0.72，FLE 为 0.64。 FLE. 结论 尽管大多数图像在目视检查中完全正常，但两级多模态贝叶斯网络方法能够以相当高的准确度区分三种癫痫类型。
BACKGROUNDQuantitative neuroimaging analyses have demonstrated gray and white matter abnormalities in group comparisons of different types of non-lesional partial epilepsy. It is unknown to what degree these type-specific patterns exist in individual patients and if they could be exploited for diagnostic purposes. In this study, a two-level multi-modality imaging Bayesian network approach is proposed that uses information about individual gray matter volume loss and white matter integrity to classify non-lesional temporal lobe epilepsy with (TLE-MTS) and without (TLE-no) mesial-temporal sclerosis and frontal lobe epilepsy (FLE).METHODS25 controls, 19 TLE-MTS, 22 TLE-no and 14 FLE were studied on a 4T MRI and T1 weighted structural and DTI images acquired. Spatially normalized gray matter (GM) and fractional anisotropy (FA) abnormality maps (binary maps with voxels 1 SD below control mean) were calculated for each subject. At the first level, each group's abnormality maps were compared with those from all the other groups using Graphical-Model-based Morphometric Analysis (GAMMA). GAMMA uses a Bayesian network and a Markov random field based contextual clustering method to produce maps of voxels that provide the maximal distinction between two groups and calculates a probability distribution and a group assignment based on this information. The information was then combined in a second level Bayesian network and the probability of each subject to belong to one of the three epilepsy types calculated.RESULTSThe specificities of the two level Bayesian network to distinguish between the three patient groups were 0.87 for TLE-MTS and TLE-no and 0.86 for FLE, the corresponding sensitivities were 0.84 for TLE-MTS, 0.72 for TLE-no and 0.64 for FLE.CONCLUSIONThe two-level multi-modality Bayesian network approach was able to distinguish between the three epilepsy types with a reasonably high accuracy even though the majority of the images were completely normal on visual inspection.