UPMC Université Paris 6, UMR 7225, UMR_S 975, Centre de Recherche de l'Institut du Cerveau et de la Moelle épinière (CRICM), Paris F-75013, France.
Med Image Anal. 2011 Oct;15(5):729-37. doi: 10.1016/j.media.2011.05.007. Epub 2011 Jun 6.
In this paper, we propose a new method to detect differences at the group level in brain images based on spatially regularized support vector machines (SVM). We propose to spatially regularize the SVM using a graph Laplacian. This provides a flexible approach to model different types of proximity between voxels. We propose a proximity graph which accounts for tissue types. An efficient computation of the Gram matrix is provided. Then, significant differences between two populations are detected using statistical tests on the outputs of the SVM. The method was first tested on synthetic examples. It was then applied to 72 stroke patients to detect brain areas associated with motor outcome at 90 days, based on diffusion-weighted images acquired at the acute stage (median delay one day). The proposed method showed that poor motor outcome is associated to changes in the corticospinal bundle and white matter tracts originating from the premotor cortex. Standard mass univariate analyses failed to detect any difference on the same population.
在本文中，我们提出了一种基于空间正则化支持向量机（SVM）的新方法，用于检测大脑图像中的组水平差异。我们建议使用图拉普拉斯对 SVM 进行空间正则化。这为模型化体素之间不同类型的相似性提供了一种灵活的方法。我们提出了一种考虑组织类型的相似性图。提供了 Gram 矩阵的有效计算。然后，使用 SVM 的输出进行统计检验来检测两个群体之间的显著差异。该方法首先在合成示例上进行了测试，然后应用于 72 名中风患者，基于在急性期（中位数延迟一天）获得的弥散加权图像，检测与 90 天运动结果相关的脑区。所提出的方法表明，运动结果较差与皮质脊髓束和源自运动前皮质的白质束的变化有关。对同一群体进行的标准多元分析未能检测到任何差异。
