IEEE Trans Med Imaging. 2017 Aug;36(8):1711-1721. doi: 10.1109/TMI.2017.2693182. Epub 2017 Apr 12.
This paper presents a segmentation technique to identify the medial axis and the boundary of cranial nerves. We utilize a 3-D deformable one-simplex discrete contour model to extract the medial axis of each cranial nerve. This contour model represents a collection of two-connected vertices linked by edges, where vertex position is determined by a Newtonian expression for vertex kinematics featuring internal and external forces, the latter of which include attractive forces toward the nerve medial axis. We exploit multiscale vesselness filtering and minimal path techniques in the medial axis extraction method, which also computes a radius estimate along the path. Once we have the medial axis and the radius function of a nerve, we identify the nerve surface using a two-simplex deformable model, which expands radially and can accommodate any nerve shape. As a result, the method proposed here combines the benefits of explicit contour and surface models, while also achieving a cornerstone for future work that will emphasize shape statistics, static collision with other critical structures, and tree-shape analysis.
本文提出了一种分割技术，用于识别颅神经的中轴和边界。我们利用三维可变形单单纯形离散轮廓模型来提取每个颅神经的中轴。这个轮廓模型表示由通过边缘连接的两个连通顶点组成的集合，其中顶点的位置由顶点运动学的牛顿表达式确定，该表达式具有内部和外部力，后者包括朝向神经中轴的吸引力。我们在中轴提取方法中利用多尺度血管滤波和最小路径技术，该方法还沿路径计算半径估计。一旦我们有了神经的中轴和半径函数，我们就可以使用双单纯形变形模型来识别神经表面，该模型可以径向扩展并适应任何神经形状。因此，本文提出的方法结合了显式轮廓和曲面模型的优点，同时也为未来的工作奠定了基础，这些工作将强调形状统计、与其他关键结构的静态碰撞以及树状分析。
