首页> 外国专利> System and method for automatically detecting pulmonary nodules in medical images

System and method for automatically detecting pulmonary nodules in medical images

机译:在医学图像中自动检测肺结节的系统和方法

摘要

A system and method for automatically segmenting a CT image of a patient's lung. The method includes segmenting a CT image to obtain one or more lung field regions and generating a mask region including a high signal region corresponding to an anatomy in the lung field region. Thresholding the region with signal strength, calculating a Euclidean distance map of the mask region, performing watershed segmentation of the Euclidean distance map to generate one or more subregions, respectively Identifying a seed point for each sub-region, expanding a candidate region from the seed point of each sub-region, and determining one or more candidate regions for pulmonary nodules based on one or more geometric features of the candidate region Classifying as: [Selection] Figure 1
机译:一种用于自动分割患者肺部CT图像的系统和方法。该方法包括:分割CT图像以获得一个或多个肺野区域;以及生成包括与肺野区域中的解剖结构相对应的高信号区域的掩模区域。对具有信号强度的区域进行阈值计算,计算蒙版区域的欧几里德距离图,对欧几里德距离图进行分水岭分割,以生成一个或多个子区域,分别为每个子区域标识一个种子点,从种子中扩展候选区域每个子区域的点,并根据候选区域的一个或多个几何特征确定一个或多个肺结节候选区域,分类为:[选择]图1

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