Tölli Tuomas, Koikkalainen Juha, Lauerma Kirsi, Lötjönen Jyrki
Laboratory of Biomedical Engineering, Helsinki University of Technology, P.O.B. 2200, FIN-02015 HUT, Finland.
Med Image Comput Comput Assist Interv. 2006;9(Pt 1):75-82. doi: 10.1007/11866565_10.
Due to small training sets, statistical shape models constrain often too much the deformation in medical image segmentation. Hence, an artificial enlargement of the training set has been proposed as a solution for the problem. In this paper, the error sources in the statistical shape model based segmentation were analyzed and the optimization processes were improved. The method was evaluated with 3D cardiac MR volume data. The enlargement method based on non-rigid movement produced good results--with 250 artificial modes, the average error for four-chamber model was 2.11 mm when evaluated using 25 subjects.
由于训练集较小，统计形状模型在医学图像分割中常常对变形的约束过多。因此，有人提出人工扩大训练集作为解决该问题的方法。本文分析了基于统计形状模型的分割中的误差来源，并改进了优化过程。该方法用三维心脏磁共振容积数据进行了评估。基于非刚性运动的扩大方法产生了良好的结果——当使用25个受试者进行评估时，对于四腔模型，在有250个人工模式的情况下，平均误差为2.11毫米。
