Aljabar P, Wolz R, Srinivasan L, Counsell S, Boardman J P, Murgasova M, Doria V, Rutherford M A, Edwards A D, Hajnal J V, Rueckert D
Department of Computing, Imperial College London, UK.
Med Image Comput Comput Assist Interv. 2010;13(Pt 3):1-8. doi: 10.1007/978-3-642-15711-0_1.
MR image data can provide many features or measures although any single measure is unlikely to comprehensively characterize the underlying morphology. We present a framework in which multiple measures are used in manifold learning steps to generate coordinate embeddings which are then combined to give an improved single representation of the population. An application to neonatal brain MRI data shows that the use of shape and appearance measures in particular leads to biologically plausible and consistent representations correlating well with clinical data. Orthogonality among the correlations suggests the embedding components relate to comparatively independent morphological features. The rapid changes that occur in brain shape and in MR image appearance during neonatal brain development justify the use of shape measures (obtained from a deformation metric) and appearance measures (obtained from image similarity). The benefit of combining separate embeddings is demonstrated by improved correlations with clinical data and we illustrate the potential of the proposed framework in characterizing trajectories of brain development.
磁共振图像数据可以提供许多特征或测量值，尽管任何单一测量值都不太可能全面地表征潜在的形态。我们提出了一个框架，在这个框架中，多种测量值被用于流形学习步骤中，以生成坐标嵌入，然后将这些嵌入组合起来，以给出群体的改进后的单一表示。对新生儿脑磁共振成像数据的应用表明，特别是形状和外观测量值的使用会产生与临床数据相关性良好的、具有生物学合理性和一致性的表示。相关性之间的正交性表明嵌入组件与相对独立的形态特征相关。新生儿脑发育过程中脑形状和磁共振图像外观发生的快速变化证明了使用形状测量值（从变形度量中获得）和外观测量值（从图像相似性中获得）的合理性。通过与临床数据的改进相关性证明了组合单独嵌入的好处，并且我们展示了所提出框架在表征脑发育轨迹方面的潜力。
