Bogovic John A, Landman Bennett A, Bazin Pierre-Louis, Prince Jerry L
Electrical, Johns Hopkins University, Baltimore, MD, USA.
Proc SPIE Int Soc Opt Eng. 2010 Mar 1;7623. doi: 10.1117/12.844214.
Studies of the size and morphology of anatomical structures rely on accurate and reproducible delineation of the structures, obtained either by human raters or automatic segmentation algorithms. Measures of reproducibility and variability are vital aspects of such studies and are usually acquired using repeated scans and repeated delineations (in the case of human raters). Methods exist for simultaneously estimating the true structure and rater performance parameters from multiple segmentations and have been demonstrated on volumetric images. In this work, we extend the application of previous methods onto two-dimensional surfaces parameterized as triangle meshes. Label homogeneity is enforced using a Markov random field formulated with an energy that addresses the challenges introduced by the surface parameterization. The method was explored using both simulated raters and surface labels obtained from an atlas registration. Simulated raters are computed using a global error as well as a novel and more realistic boundary error model. We study the impact of raters and their accuracy based on both models, and show how effectively this method estimates the true segmentation on simulated and real surfaces.
对解剖结构的大小和形态的研究依赖于对这些结构的准确且可重复的描绘，这可以通过人工评分者或自动分割算法来实现。可重复性和变异性的度量是此类研究的重要方面，通常通过重复扫描和重复描绘（对于人工评分者而言）来获取。存在从多个分割结果中同时估计真实结构和评分者性能参数的方法，并且已经在体积图像上得到了验证。在这项工作中，我们将先前方法的应用扩展到参数化为三角形网格的二维表面上。使用基于能量的马尔可夫随机场来强制标签同质性，该能量解决了由表面参数化引入的挑战。该方法通过使用模拟评分者和从图谱配准获得的表面标签进行了探索。模拟评分者使用全局误差以及一种新颖且更现实的边界误差模型来计算。我们基于这两种模型研究评分者及其准确性的影响，并展示该方法如何有效地估计模拟表面和真实表面上的真实分割。
