公开(公告)号：US20160283657A1

公开(公告)日：2016-09-29

申请号：US14667114

申请日：2015-03-24

Applicant: General Electric Company

Inventor： Rahul Bhotika ,  Rui Li ,  Aravind Chandramouli ,  Sheng Yi ,  Ravi Kiran Reddy Palla

IPC: G06F19/00

CPC classification number: G06F19/321 ,  G16H15/00 ,  G16H50/20

Abstract: Methods and apparatus for analyzing, mapping and structuring healthcare data are disclosed. An example method includes parsing a clinical report to identify a parameter within the clinical report and associated with an image. The clinical report is associated with the image. The example method includes, when the parameter is identified in the parsing, analyzing the image to determine a value of the parameter, mapping the value, the image, and the clinical report to a model and generating an output to display one or more of the value, the image, or the clinical report.

Abstract translation: 公开了用于分析，映射和构造医疗保健数据的方法和装置。 示例性方法包括解析临床报告以识别临床报告内的参数并与图像相关联。 临床报告与图像相关。 示例性方法包括：当在解析中识别参数时，分析图像以确定参数的值，将值，图像和临床报告映射到模型并生成输出以显示一个或多个 价值，图像或临床报告。

公开(公告)号：US20140185895A1

公开(公告)日：2014-07-03

申请号：US13731140

申请日：2012-12-31

Applicant: GENERAL ELECTRIC COMPANY

Inventor： Gokul Swamy ,  Rui Li

IPC: G06K9/46

CPC classification number: A61B8/5223 ,  A61B8/0866 ,  G06K2209/05 ,  G06T7/0014 ,  G06T2207/10132 ,  G06T2207/20076 ,  G06T2207/20081 ,  G06T2207/30044

Abstract: A computer-implemented method for analyzing a fetal ultrasound image includes accessing a first statistical model calculated from training data representing shapes of conforming fetal abdominal tissue exemplars and accessing image data representing a scan plane in an ultrasound image. The method further includes identifying a region of interest including an abdomen in the scan plane using the first statistical model, accessing a second statistical model calculated from training data representing shapes of conforming fetal anatomical structure exemplars, determining whether one or more anatomical structures are present within the region of interest using the second statistical model, and assigning a rating to the scan plane based on the presence of the one or more anatomical structures in the region of interest. The anatomical structures may include a stomach and/or a portal vein. The method may include calculating an estimated circumference of the abdomen.

Abstract translation: 用于分析胎儿超声图像的计算机实现的方法包括访问由表示符合胎儿腹部组织样本的形状的训练数据计算的第一统计模型，以及访问表示超声图像中的扫描平面的图像数据。 该方法还包括使用第一统计模型来识别包括扫描平面中的腹部的感兴趣区域，访问由表示符合胎儿解剖结构样本的形状的训练数据计算的第二统计模型，确定是否存在一个或多个解剖结构 使用第二统计模型的感兴趣区域，以及基于感兴趣区域中的一个或多个解剖结构的存在，将评级分配给扫描平面。 解剖结构可以包括胃和/或门静脉。 该方法可以包括计算腹部的估计周长。

公开(公告)号：US08831311B2

公开(公告)日：2014-09-09

申请号：US13731140

申请日：2012-12-31

Applicant: General Electric Company

Inventor： Gokul Swamy ,  Rui Li

IPC: G06T7/00 ,  G06K9/46

CPC classification number: A61B8/5223 ,  A61B8/0866 ,  G06K2209/05 ,  G06T7/0014 ,  G06T2207/10132 ,  G06T2207/20076 ,  G06T2207/20081 ,  G06T2207/30044

Abstract: A computer-implemented method for analyzing a fetal ultrasound image includes accessing a first statistical model calculated from training data representing shapes of conforming fetal abdominal tissue exemplars and accessing image data representing a scan plane in an ultrasound image. The method further includes identifying a region of interest including an abdomen in the scan plane using the first statistical model, accessing a second statistical model calculated from training data representing shapes of conforming fetal anatomical structure exemplars, determining whether one or more anatomical structures are present within the region of interest using the second statistical model, and assigning a rating to the scan plane based on the presence of the one or more anatomical structures in the region of interest. The anatomical structures may include a stomach and/or a portal vein. The method may include calculating an estimated circumference of the abdomen.

Abstract translation: 用于分析胎儿超声图像的计算机实现的方法包括访问由表示符合胎儿腹部组织样本的形状的训练数据计算的第一统计模型，以及访问表示超声图像中的扫描平面的图像数据。 该方法还包括使用第一统计模型来识别包括扫描平面中的腹部的感兴趣区域，访问由表示符合胎儿解剖结构样本的形状的训练数据计算的第二统计模型，确定是否存在一个或多个解剖结构 使用第二统计模型的感兴趣区域，以及基于感兴趣区域中的一个或多个解剖结构的存在，将评级分配给扫描平面。 解剖结构可以包括胃和/或门静脉。 该方法可以包括计算腹部的估计周长。