公开(公告)号：US20160054410A1

公开(公告)日：2016-02-25

申请号：US14826468

申请日：2015-08-14

Applicant: GENERAL ELECTRIC COMPANY

Inventor： John Frederick Schenck ,  Ek Tsoon Tan ,  Dominic Michael Graziani ,  Suresh Emmanuel Devadoss Joel

IPC: G01R33/48 ,  G01R33/50 ,  A61B5/055

CPC classification number: G01R33/50 ,  A61B5/055 ,  A61B5/165 ,  A61B5/4076 ,  A61B5/4887 ,  A61B5/4893 ,  A61B2576/026 ,  G01R33/5616 ,  G01R33/56341

Abstract: In embodiments of the invention, the habenulae have been identified and localized in normal volunteers. Aspects of the invention determine the location, volume and magnetic susceptibility of the habenulae. Furthermore, diagnosing and monitoring patient disorders are enabled using the herein disclosed methodologies and techniques.

Abstract translation: 在本发明的实施方案中，已经在正常志愿者中鉴定和定位了这些。。。 本发明的方面确定了h the的位置，体积和磁化率。 此外，使用本文公开的方法和技术来实现诊断和监测患者障碍。

公开(公告)号：US20140226889A1

公开(公告)日：2014-08-14

申请号：US14177414

申请日：2014-02-11

Applicant: GENERAL ELECTRIC COMPANY

Inventor： Xiaofeng Liu ,  John Frederick Schenck ,  Ek Tsoon Tan ,  Albert Amos Montillo

IPC: G06T7/00

CPC classification number: G06T7/0081 ,  G06T7/11 ,  G06T7/143 ,  G06T7/149 ,  G06T7/174 ,  G06T2200/04 ,  G06T2207/10072 ,  G06T2207/20076 ,  G06T2207/20128 ,  G06T2207/30016

Abstract: The system and method of the invention combines target image intensity into a maximum likelihood estimate (MLE) framework as in STAPLE to take advantage of both intensity-based segmentation and statistical label fusion based on atlas consensus and performance level, abbreviated iSTAPLE. The MLE framework is then solved using a modified expectation-maximization algorithm to simultaneously estimate the intensity profiles of structures of interest as well as the true segmentation and atlas performance level. The iSTAPLE greatly extends the use of atlases such that the target image need not have the same image contrast and intensity range as the atlas images.

Abstract translation: 本发明的系统和方法将目标图像强度与STAPLE中的最大似然估计（MLE）框架相结合，以利用基于图集共识和性能水平（简称为iSTAPLE）的基于强度的分割和统计标签融合。 然后使用修改的期望最大化算法来解决MLE框架，以同时估计感兴趣的结构的强度分布以及真实的分段和图谱性能水平。 iSTAPLE大大扩展了地图集的使用，使得目标图像不需要具有与图集图像相同的图像对比度和强度范围。

公开(公告)号：US09349186B2

公开(公告)日：2016-05-24

申请号：US14177414

申请日：2014-02-11

Applicant: GENERAL ELECTRIC COMPANY

Inventor： Xiaofeng Liu ,  John Frederick Schenck ,  Ek Tsoon Tan ,  Albert Amos Montillo

IPC: G06K9/00 ,  G06T7/00

CPC classification number: G06T7/0081 ,  G06T7/11 ,  G06T7/143 ,  G06T7/149 ,  G06T7/174 ,  G06T2200/04 ,  G06T2207/10072 ,  G06T2207/20076 ,  G06T2207/20128 ,  G06T2207/30016

Abstract: The system and method of the invention combines target image intensity into a maximum likelihood estimate (MLE) framework as in STAPLE to take advantage of both intensity-based segmentation and statistical label fusion based on atlas consensus and performance level, abbreviated iSTAPLE. The MLE framework is then solved using a modified expectation-maximization algorithm to simultaneously estimate the intensity profiles of structures of interest as well as the true segmentation and atlas performance level. The iSTAPLE greatly extends the use of atlases such that the target image need not have the same image contrast and intensity range as the atlas images.

Abstract translation: 本发明的系统和方法将目标图像强度与STAPLE中的最大似然估计（MLE）框架相结合，以利用基于图集共识和性能水平（简称为iSTAPLE）的基于强度的分割和统计标签融合。 然后使用修改的期望最大化算法来解决MLE框架，以同时估计感兴趣的结构的强度分布以及真实的分段和图谱性能水平。 iSTAPLE大大扩展了地图集的使用，使得目标图像不需要具有与图集图像相同的图像对比度和强度范围。