Toews Matthew, Collins D Louis, Arbel Tal
Centre for Intelligent Machines, McGili University, Montréal, Canada.
Med Image Comput Comput Assist Interv. 2006;9(Pt 1):232-40. doi: 10.1007/11866565_29.
In this article, we present a general statistical parts-based model for representing the appearance of an image set, applied to the problem of inter-subject MR brain image matching. In contrast with global image representations such as active appearance models, the parts-based model consists of a collection of localized image parts whose appearance, geometry and occurrence frequency are quantified statistically. The parts-based approach explicitly addresses the case where one-to-one correspondence does not exist between subjects due to anatomical differences, as parts are not expected to occur in all subjects. The model can be learned automatically, discovering structures that appear with statistical regularity in a large set of subject images, and can be robustly fit to new images, all in the presence of significant inter-subject variability. As parts are derived from generic scale-invariant features, the framework can be applied in a wide variety of image contexts, in order to study the commonality of anatomical parts or to group subjects according to the parts they share. Experimentation shows that a parts-based model can be learned from a large set of MR brain images, and used to determine parts that are common within the group of subjects. Preliminary results indicate that the model can be used to automatically identify distinctive features for inter-subject image registration despite large changes in appearance.
在本文中，我们提出了一种用于表示图像集外观的通用统计基于部件的模型，并将其应用于个体间磁共振脑图像匹配问题。与诸如主动外观模型等全局图像表示不同，基于部件的模型由一组局部图像部件组成，其外观、几何形状和出现频率通过统计进行量化。基于部件的方法明确解决了由于解剖差异导致个体间不存在一一对应关系的情况，因为部件并非预期出现在所有个体中。该模型可以自动学习，发现大量个体图像中以统计规律出现的结构，并且能够在存在显著个体间变异性的情况下稳健地拟合新图像。由于部件源自通用的尺度不变特征，该框架可以应用于各种图像情境，以研究解剖部件的共性或根据个体共享的部件对个体进行分组。实验表明，可以从大量磁共振脑图像中学习基于部件的模型，并用于确定个体组内共有的部件。初步结果表明，尽管外观变化很大，该模型仍可用于自动识别个体间图像配准的独特特征。
