作者: Aaron E. Lefohn , Joshua E. Cates , Ross T. Whitaker
DOI: 10.1007/978-3-540-39899-8_70
关键词: OpenGL 、 Machine learning 、 Graphics 、 Segmentation 、 Artificial intelligence 、 Computer science 、 Image segmentation 、 Scale-space segmentation 、 Computer vision 、 Level set 、 Image processing
摘要: While level sets have demonstrated a great potential for 3D medical image segmentation, their usefulness has been limited by two problems. First, are relatively slow to compute. Second, formulation usually entails several free parameters which can be very difficult correctly tune specific applications. This paper presents tool segmentation that relies on level-set surface models computed at interactive rates commodity graphics cards (GPUs). The solving the PDE give user immediate feedback parameter settings, and thus users three separate control shape of model in real time. We found this interactivity enables produce good, reliable as supported qualitative quantitative results.