Lenglet Christophe, Rousson Mikaël, Deriche Rachid, Faugeras Olivier, Lehericy Stéphane, Ugurbil Kamil
INRIA, 2004 route des lucioles, 06902 Sophia-Antipolis, France.
Inf Process Med Imaging. 2005;19:591-602. doi: 10.1007/11505730_49.
We address the problem of the segmentation of cerebral white matter structures from diffusion tensor images. Our approach is grounded on the theoretically well-founded differential geometrical properties of the space of multivariate normal distributions. We introduce a variational formulation, in the level set framework, to estimate the optimal segmentation according to the following hypothesis: Diffusion tensors exhibit a Gaussian distribution in the different partitions. Moreover, we must respect the geometric constraints imposed by the interfaces existing among the cerebral structures and detected by the gradient of the diffusion tensor image. We validate our algorithm on synthetic data and report interesting results on real datasets. We focus on two structures of the white matter with different properties and respectively known as the corpus callosum and the corticospinal tract.
我们研究了从扩散张量图像中分割脑白质结构的问题。我们的方法基于多元正态分布空间中理论基础扎实的微分几何特性。我们在水平集框架中引入了一种变分公式，以根据以下假设估计最优分割：扩散张量在不同分区中呈现高斯分布。此外，我们必须尊重脑结构之间存在的、由扩散张量图像的梯度检测到的界面所施加的几何约束。我们在合成数据上验证了我们的算法，并在真实数据集上报告了有趣的结果。我们关注白质中具有不同特性的两种结构，分别称为胼胝体和皮质脊髓束。
