Division of Brain, Imaging and Behaviour, Systems Neuroscience, Krembil Brain Institute, University Health Network, Toronto, ON, Canada.
Department of Surgery, Institute of Medical Science, University of Toronto, Toronto, ON, Canada.
Pain. 2018 Oct;159(10):2076-2087. doi: 10.1097/j.pain.0000000000001312.
Trigeminal neuralgia (TN) is a severe form of chronic facial neuropathic pain. Increasing interest in the neuroimaging of pain has highlighted changes in the root entry zone in TN, but also group-level central nervous system gray and white matter (WM) abnormalities. Group differences in neuroimaging data are frequently evaluated with univariate statistics; however, this approach is limited because it is based on single, or clusters of, voxels. By contrast, multivariate pattern analyses consider all the model's neuroanatomical features to capture a specific distributed spatial pattern. This approach has potential use as a prediction tool at the individual level. We hypothesized that a multivariate pattern classification method can distinguish specific patterns of abnormal WM connectivity of classic TN from healthy controls (HCs). Diffusion-weighted scans in 23 right-sided TN and matched controls were processed to extract whole-brain interregional streamlines. We used a linear support vector machine algorithm to differentiate interregional normalized streamline count between TN and HC. This algorithm successfully differentiated between TN and HC with an accuracy of 88%. The structural pattern emphasized WM connectivity of regions that subserve sensory, affective, and cognitive dimensions of pain, including the insula, precuneus, inferior and superior parietal lobules, and inferior and medial orbital frontal gyri. Normalized streamline counts were associated with longer pain duration and WM metric abnormality between the connections. This study demonstrates that machine-learning algorithms can detect characteristic patterns of structural alterations in TN and highlights the role of structural brain imaging for identification of neuroanatomical features associated with neuropathic pain disorders.
三叉神经痛（TN）是一种严重的慢性面部神经性疼痛。人们对疼痛的神经影像学研究兴趣日益增加，这突出了 TN 神经根进入区的变化，但也突显了中枢神经系统灰质和白质（WM）的整体异常。神经影像学数据的组间差异通常使用单变量统计进行评估；然而，这种方法是有限的，因为它基于单个或多个体素。相比之下，多元模式分析考虑了所有模型的神经解剖学特征，以捕捉特定的分布式空间模式。这种方法有可能作为个体水平的预测工具。我们假设多元模式分类方法可以区分经典 TN 和健康对照（HC）之间异常 WM 连接的特定模式。对 23 例右侧 TN 和匹配对照的弥散加权扫描进行处理，以提取全脑区域间流线。我们使用线性支持向量机算法来区分 TN 和 HC 之间的区域间归一化流线计数。该算法以 88%的准确率成功地区分了 TN 和 HC。结构模式强调了与疼痛的感觉、情感和认知维度相关的区域的 WM 连接，包括岛叶、楔前叶、下顶叶和上顶叶以及下眶额回和内眶额回。归一化流线计数与疼痛持续时间的延长和连接之间的 WM 指标异常有关。这项研究表明，机器学习算法可以检测出 TN 中结构改变的特征模式，并强调了结构脑成像在识别与神经性疼痛障碍相关的神经解剖学特征方面的作用。
