作者: Christian Bauer , Shanhui Sun , Reinhard Beichel
DOI: 10.1007/978-3-642-24028-7_20
关键词: Mathematical optimization 、 Scale-space segmentation 、 Polygon mesh 、 Robustness (computer science) 、 Active shape model 、 Algorithm 、 Vector flow 、 Mathematics 、 Folding (DSP implementation) 、 Maxima and minima 、 Segmentation
摘要: The segmentation of 3D medical images is a challenging problem that benefits from incorporation prior shape information. Optimal Surface Segmentation (OSS) has been introduced as powerful and flexible framework allows segmenting the surface an object based on rough initial with robustness against local minima. When applied to general meshes, conventional search profiles constructed for OSS may overlap resulting in defective results due mesh folding. To avoid this problem, we propose use Gradient Vector Flow field guide construction non-overlapping profiles. As shown our evaluation lung surfaces, effectively solves folding decreases average absolute distance error 0.82±0.29 mm (mean±standard deviation) 0.79 ± 0.24 mm.