Efficient searching of globally optimal and smooth multi-surfaces with shape priors
Efficient searching of globally optimal and smooth multi-surfaces with shape priors
复制标题
利用形状先验有效搜索全局最优且平滑的多表面
DOI：
--
复制
发表时间：
2012
期刊：
影响因子：
--
通讯作者：
Jinhui Xu
中科院分区：
文献类型：
--
作者：
Lei Xu;B. Stojković;Hu Ding;Qi Song;Xiaodong Wu;M. Sonka;Jinhui Xu
尽管在过去进行了广泛的研究，但在3D体积图像中分割全局最优的多个表面的问题在医学成像中仍然具有挑战性。在高噪声和边缘弱的图像中，这个问题变得更加困难。在本文中，我们提出了一种新的和高效的图论迭代方法的基础上的体积图表示的3D图像，结合曲率和形状先验信息。与基于图形的方法相比，在特定的首选形状模型上构建图形之前应用形状可以轻松地合并广泛的形状先验信息。此外，目标函数的计算可以在x和y方向上独立完成的关键见解使得局部改进成为可能。因此，代替使用全局优化技术，例如最大流算法，基于迭代的方法快得多。此外，在目标函数中利用曲率保证了平滑性。据我们所知，这是联合收割机的第一篇论文，利用曲率的目标函数，以确保所生成的表面的光滑性，同时努力实现全局最优的形状先验处罚。为了评估我们的方法的性能，我们测试了一组14个3D OCT图像。实验结果表明，与现有的最佳方法相比，该方法将无符号表面定位误差从5.44 ± 1.07（μm）减小到4.52 ± 0.84（μm）。此外，我们的方法有一个大大改善的运行时间，产生几乎相同的全局最优性，但更好的平滑性，这使得它特别适合于分割高噪声图像。所提出的方法也适用于并行实现的GPU，这可能使我们能够分割高噪声的体积图像在真实的时间。
Despite extensive studies in the past, the problem of segmenting globally optimal multiple surfaces in 3D volumetric images remains challenging in medical imaging. The problem becomes even harder in highly noisy and edge-weak images. In this paper we present a novel and highly efficient graph-theoretical iterative method based on a volumetric graph representation of the 3D image that incorporates curvature and shape prior information. Compared with the graph-based method, applying the shape prior to construct the graph on a specific preferred shape model allows easy incorporation of a wide spectrum of shape prior information. Furthermore, the key insight that computation of the objective function can be done independently in the x and y directions makes local improvement possible. Thus, instead of using global optimization technique such as maximum flow algorithm, the iteration based method is much faster. Additionally, the utilization of the curvature in the objective function ensures the smoothness. To the best of our knowledge, this is the first paper to combine the shape-prior penalties with utilizing curvature in objective function to ensure the smoothness of the generated surfaces while striving for achieving global optimality. To evaluate the performance of our method, we test it on a set of 14 3D OCT images. Comparing to the best existing approaches, our experiments suggest that the proposed method reduces the unsigned surface positioning errors form 5.44 ± 1.07(μm) to 4.52 ± 0.84(μm). Moreover, our method has a much improved running time, yields almost the same global optimality but with much better smoothness, which makes it especially suitable for segmenting highly noisy images. The proposed method is also suitable for parallel implementation on GPUs, which could potentially allow us to segment highly noisy volumetric images in real time.