Model-based segmentation methods have the advantage of incorporating a priori shape information into the segmentation process\nbut suffer from the drawback that the model must be initialized sufficiently close to the target. We propose a novel approach\nfor initializing an active shape model (ASM) and apply it to 3D lung segmentation in CT scans. Our method constructs an atlas\nconsisting of a set of representative lung features and an average lung shape.The ASM pose parameters are found by transforming\nthe average lung shape based on an affine transform computed from matching features between the new image and representative\nlung features. Our evaluation on a diverse set of 190 images showed an average dice coefficient of 0.746 �± 0.068 for initialization and\n0.974 �± 0.017 for subsequent segmentation, based on an independent reference standard.The mean absolute surface distance error\nwas 0.948 �± 1.537 mm. The initialization as well as segmentation results showed a statistically significant improvement compared\nto four other approaches. The proposed initialization method can be generalized to other applications employing ASM-based\nsegmentation.
Loading....