Zambal Sebastian, Hladůvka Jifi, Bühler Katja
VRVis Research Center for Virtual Reality and Visualization, Donau-City-Strasse 1, 1220 Vienna, Austria.
Med Image Comput Comput Assist Interv. 2006;9(Pt 1):151-8. doi: 10.1007/11866565_19.
Quality of segmentations obtained by 3D Active Appearance Models (AAMs) crucially depends on underlying training data. MRI heart data, however, often come noisy, incomplete, with respiratory-induced motion, and do not fulfill necessary requirements for building an AAM. Moreover, AAMs are known to fail when attempting to model local variations. Inspired by the recent work on split models we propose an alternative to the methods based on pure 3D AAM segmentation. We interconnect a set of 2D AAMs by a 3D shape model. We show that our approach is able to cope with imperfect data and improves segmentations by 11% on average compared to 3D AAMs.
通过三维主动外观模型（AAM）获得的分割质量关键取决于基础训练数据。然而，MRI心脏数据常常存在噪声、不完整，还伴有呼吸引起的运动，并且不满足构建AAM的必要要求。此外，已知AAM在尝试对局部变化进行建模时会失败。受近期关于分割模型的工作启发，我们提出了一种替代基于纯三维AAM分割方法的方案。我们通过一个三维形状模型将一组二维AAM相互连接起来。我们表明，我们的方法能够处理不完美的数据，并且与三维AAM相比，平均分割效果提高了11%。
