Diagnostic Image Analysis Group, Radboud University Nijmegen Medical Centre, Geert Grooteplein Zuid 18, 6525 GA Nijmegen, The Netherlands.
Med Image Anal. 2012 Dec;16(8):1490-502. doi: 10.1016/j.media.2012.06.009. Epub 2012 Jul 31.
Automated delineation of anatomical structures in chest radiographs is difficult due to superimposition of multiple structures. In this work an automated technique to segment the clavicles in posterior-anterior chest radiographs is presented in which three methods are combined. Pixel classification is applied in two stages and separately for the interior, the border and the head of the clavicle. This is used as input for active shape model segmentation. Finally dynamic programming is employed with an optimized cost function that combines appearance information of the interior of the clavicle, the border, the head and shape information derived from the active shape model. The method is compared with a number of previously described methods and with independent human observers on a large database. This database contains both normal and abnormal images and will be made publicly available. The mean contour distance of the proposed method on 249 test images is 1.1±1.6mm and the intersection over union is 0.86±0.10.
由于胸部 X 光片中存在多个结构的重叠，因此对解剖结构进行自动勾画非常困难。在这项工作中，我们提出了一种自动分割前后位胸部 X 光片中锁骨的技术，该技术结合了三种方法。像素分类分为两个阶段，并分别应用于锁骨的内部、边界和头部。这被用作主动形状模型分割的输入。最后，使用具有优化成本函数的动态规划，该函数结合了锁骨内部、边界、头部的外观信息以及主动形状模型得出的形状信息。该方法与之前描述的多种方法以及大量正常和异常图像的独立人工观察者进行了比较。该数据库将公开提供。在 249 张测试图像上，所提出方法的平均轮廓距离为 1.1±1.6mm，交并比为 0.86±0.10。
