首页> 外国专利> AUTOMATIC SEGMENTATION SYSTEM AND THE METHOD OF GROUND-GLASS OPACITY NODULE IN CHEST CT IMAGES

AUTOMATIC SEGMENTATION SYSTEM AND THE METHOD OF GROUND-GLASS OPACITY NODULE IN CHEST CT IMAGES

机译:胸部CT图像中的自动分段系统及玻璃微球结节的方法

摘要

The present invention relates to an automatic segmentation system for a ground-glass opacity (GGO) nodule in chest computed tomographic (CT) images and a segmentation method thereof, which simultaneously separating a GGO nodule component and a solid component from a background using multi-phase deformable model with intensity constraints. The automatic segmentation system for the GGO nodule in chest CT images comprises: an initial segmentation unit which segments initial GGO and solid components in the chest CT images by estimating adaptive threshold values using intensity histogram modeling; a neighbor structure elimination unit which eliminates blood vessels and a chest wall around the nodule from the initial segments using shape information and segmented lung information; and a final segmentation unit which segments final GGO and solid components using multi-phase deformable model with intensity constraints.
机译:本发明涉及一种用于胸部计算机断层摄影(CT)图像中的毛玻璃结节(GGO)结节的自动分割系统及其分割方法,其同时使用多种方法从背景中分离出GGO结节成分和固体成分。强度约束的相位可变形模型。用于胸部CT图像中的GGO结节的自动分割系统包括:初始分割单元,其通过使用强度直方图模型估计自适应阈值来分割胸部CT图像中的初始GGO和固体成分。邻居结构消除单元,其使用形状信息和肺分割信息从初始节段消除结节周围的血管和胸壁;最终分割单元使用具有强度约束的多相可变形模型对最终GGO和固体成分进行分割。

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号