公开(公告)号：US08973010B2

公开(公告)日：2015-03-03

申请号：US12789981

申请日：2010-05-28

申请人： Benjamin Haas ,  Thomas Coradi

发明人： Benjamin Haas ,  Thomas Coradi

IPC分类号： G06F9/46 ,  G06F9/50 ,  G06K9/00

CPC分类号： G06F9/5066 ,  G06K9/00993 ,  G06K2209/05

摘要： Embodiments of the present invention are directed to techniques for providing an environment for the efficient execution of recognition tasks. A novel environment is provided which automatically and efficiently executes a recognition program on as many computer processors as available. This program, deconstructed into separate tasks, may be executed by constructing a dependency network from known inputs and outputs of the tasks, applying project planning methods for scheduling these tasks into multiple processing threads, and dynamically assigning tasks within these threads to processors. Therefore, an efficient schedule of tasks to complete a recognition program can be created and executed automatically, for any type of recognition problem. The system will not only allow for the ability to leverage multiple processors for efficiently generating variable and customizable automatically created schedules, but will also still maintain the flexibility to use serial programming in recognition algorithms for individual objects, properties, or features.

摘要翻译： 本发明的实施例涉及提供用于有效执行识别任务的环境的技术。 提供了一种新颖的环境，其在尽可能多的计算机处理器上自动且有效地执行识别程序。 该程序被解构为单独的任务，可以通过从已知的任务的输入和输出构建依赖网络来执行，将用于将这些任务调度到多个处理线程中的应用项目规划方法，以及将这些线程内的任务动态地分配给处理器。 因此，对于任何类型的识别问题，可以自动创建和执行完成识别程序的任务的有效计划。 该系统不仅能够利用多个处理器来有效地生成可变和可自定义的自动创建的计划，而且还将保持在单个对象，属性或特征的识别算法中使用串行编程的灵活性。

公开(公告)号：US20120051607A1

公开(公告)日：2012-03-01

申请号：US12862365

申请日：2010-08-24

申请人： Janne Nord ,  Benjamin Haas ,  Thomas Coradi

发明人： Janne Nord ,  Benjamin Haas ,  Thomas Coradi

IPC分类号： G06K9/00

CPC分类号： G06F19/321 ,  G06F19/00 ,  G06T7/0016 ,  G06T2207/10081 ,  G06T2207/10088 ,  G06T2207/10104 ,  G06T2207/10116 ,  G06T2207/10132

摘要： A medical-imaging digital-computing platform serves to access a plurality of data objects and to execute an iterative process with respect to these data objects. The data objects themselves each at least generally pertain to portions of the human anatomy and may comprise, for example, both a source data object and a target data object. The platform executes the iterative process to determine at least one of a labeling of a portion of one of the data objects and a geometric relationship between at least portions of at least two of the data objects. This can be done, for example, by automatically employing both a segmentation module and a registration module as steps within the iterative process. This can also comprise determining when to automatically generate an intermediate data object to provide as input to at least one of these modules.

摘要翻译： 医学成像数字计算平台用于访问多个数据对象并执行关于这些数据对象的迭代过程。 数据对象本身各自至少通常涉及人体解剖结构的部分，并且可以包括例如源数据对象和目标数据对象。 该平台执行迭代过程以确定数据对象之一的一部分的标记和至少两个数据对象的至少部分之间的几何关系中的至少一个。 这可以通过例如自动采用分段模块和注册模块来实现，作为迭代过程中的步骤。 这还可以包括确定何时自动生成中间数据对象以提供作为这些模块中的至少一个的输入。

公开(公告)号：US07831079B2

公开(公告)日：2010-11-09

申请号：US12550274

申请日：2009-08-28

申请人： Patrik Kunz ,  Martin Scholz ,  Benjamin Haas ,  Thomas Coradi

发明人： Patrik Kunz ,  Martin Scholz ,  Benjamin Haas ,  Thomas Coradi

IPC分类号： G06K9/00

CPC分类号： G06K9/4638 ,  G06K2209/05

摘要： A method of constructing a navigation table relating a set of images representative of a region of interest in a subject to a reference system with reference positions indicating known anatomic landmarks of a reference subject comprising providing reference positions for two or more images identified with two or more anatomic landmarks indicative of the region of interest with reference positions of known anatomic landmarks corresponding to the identified anatomic landmarks, and determining reference positions for the remaining images by interpolation.

摘要翻译： 一种将表示受试者感兴趣区域的一组图像与参考系统相关联的导航表的方法​​，其具有指示参考对象的已知解剖标志的参考位置，该参考位置提供用两个或更多个识别的两个或多个图像的参考位置 指示与所识别的解剖标志相对应的已知解剖学标记的参考位置的感兴趣区域的解剖标志，以及通过插值确定剩余图像的参考位置。

公开(公告)号：US07599539B2

公开(公告)日：2009-10-06

申请号：US11494860

申请日：2006-07-28

申请人： Patrik Kunz ,  Martin Scholz ,  Benjamin Haas ,  Thomas Coradi

发明人： Patrik Kunz ,  Martin Scholz ,  Benjamin Haas ,  Thomas Coradi

IPC分类号： G06K9/00

CPC分类号： G06K9/4638 ,  G06K2209/05

摘要： A method of constructing a navigation table relating a set of images representative of a region of interest in a subject to a reference system with reference positions indicating known anatomic landmarks of a reference subject comprising providing reference positions for two or more images identified with two or more anatomic landmarks indicative of the region of interest with reference positions of known anatomic landmarks corresponding to the identified anatomic landmarks, and determining reference positions for the remaining images by interpolation.

摘要翻译： 一种将表示受试者感兴趣区域的一组图像与参考系统相关联的导航表的方法​​，其具有指示参考对象的已知解剖标志的参考位置，该参考位置提供用两个或更多个识别的两个或多个图像的参考位置 指示与所识别的解剖标志相对应的已知解剖学标记的参考位置的感兴趣区域的解剖标志，以及通过插值确定剩余图像的参考位置。

公开(公告)号：US20080025584A1

公开(公告)日：2008-01-31

申请号：US11494860

申请日：2006-07-28

申请人： Patrik Kunz ,  Martin Scholz ,  Benjamin Haas ,  Thomas Coradi

发明人： Patrik Kunz ,  Martin Scholz ,  Benjamin Haas ,  Thomas Coradi

IPC分类号： G06K9/00

CPC分类号： G06K9/4638 ,  G06K2209/05

摘要： A method of constructing a navigation table relating a set of images representative of a region of interest in a subject to a reference system with reference positions indicating known anatomic landmarks of a reference subject comprising providing reference positions for two or more images identified with two or more anatomic landmarks indicative of the region of interest with reference positions of known anatomic landmarks corresponding to the identified anatomic landmarks, and determining reference positions for the remaining images by interpolation.

摘要翻译： 一种将表示受试者感兴趣区域的一组图像与参考系统相关联的导航表的方法​​，其具有指示参考对象的已知解剖标志的参考位置，该参考位置提供用两个或更多个识别的两个或多个图像的参考位置 指示与所识别的解剖标志相对应的已知解剖学标记的参考位置的感兴趣区域的解剖标志，以及通过插值确定剩余图像的参考位置。

公开(公告)号：US08744148B2

公开(公告)日：2014-06-03

申请号：US12862365

申请日：2010-08-24

申请人： Janne Nord ,  Benjamin Haas ,  Thomas Coradi

发明人： Janne Nord ,  Benjamin Haas ,  Thomas Coradi

IPC分类号： G06K9/00

CPC分类号： G06F19/321 ,  G06F19/00 ,  G06T7/0016 ,  G06T2207/10081 ,  G06T2207/10088 ,  G06T2207/10104 ,  G06T2207/10116 ,  G06T2207/10132

摘要： A medical-imaging digital-computing platform serves to access a plurality of data objects and to execute an iterative process with respect to these data objects. The data objects themselves each at least generally pertain to portions of the human anatomy and may comprise, for example, both a source data object and a target data object. The platform executes the iterative process to determine at least one of a labeling of a portion of one of the data objects and a geometric relationship between at least portions of at least two of the data objects. This can be done, for example, by automatically employing both a segmentation module and a registration module as steps within the iterative process. This can also comprise determining when to automatically generate an intermediate data object to provide as input to at least one of these modules.

摘要翻译： 医学成像数字计算平台用于访问多个数据对象并执行关于这些数据对象的迭代过程。 数据对象本身各自至少通常涉及人体解剖结构的部分，并且可以包括例如源数据对象和目标数据对象。 该平台执行迭代过程以确定数据对象之一的一部分的标记和至少两个数据对象的至少部分之间的几何关系中的至少一个。 这可以通过例如自动采用分段模块和注册模块来实现，作为迭代过程中的步骤。 这还可以包括确定何时自动生成中间数据对象以提供作为这些模块中的至少一个的输入。

公开(公告)号：US20110292056A1

公开(公告)日：2011-12-01

申请号：US12789981

申请日：2010-05-28

申请人： Benjamin HAAS ,  Thomas CORADI

发明人： Benjamin HAAS ,  Thomas CORADI

IPC分类号： G06F15/80 ,  G06K9/00

CPC分类号： G06F9/5066 ,  G06K9/00993 ,  G06K2209/05

摘要： Embodiments of the present invention are directed to techniques for providing an environment for the efficient execution of recognition tasks. A novel environment is provided which automatically and efficiently executes a recognition program on as many computer processors as available. This program, deconstructed into separate tasks, may be executed by constructing a dependency network from known inputs and outputs of the tasks, applying project planning methods for scheduling these tasks into multiple processing threads, and dynamically assigning tasks within these threads to processors. Therefore, an efficient schedule of tasks to complete a recognition program can be created and executed automatically, for any type of recognition problem. The system will not only allow for the ability to leverage multiple processors for efficiently generating variable and customizable automatically created schedules, but will also still maintain the flexibility to use serial programming in recognition algorithms for individual objects, properties, or features.

摘要翻译： 本发明的实施例涉及提供用于有效执行识别任务的环境的技术。 提供了一种新颖的环境，其在尽可能多的计算机处理器上自动且有效地执行识别程序。 该程序被解构为单独的任务，可以通过从已知的任务的输入和输出构建依赖网络来执行，将用于将这些任务调度到多个处理线程中的应用项目规划方法，以及将这些线程内的任务动态地分配给处理器。 因此，对于任何类型的识别问题，可以自动创建和执行完成识别程序的任务的有效计划。 该系统不仅能够利用多个处理器来有效地生成可变和可自定义的自动创建的计划，而且还将保持在单个对象，属性或特征的识别算法中使用串行编程的灵活性。

公开(公告)号：US20090316975A1

公开(公告)日：2009-12-24

申请号：US12550274

申请日：2009-08-28

申请人： Patrik Kunz ,  Martin Scholz ,  Benjamin HAAS ,  Thomas Coradi

发明人： Patrik Kunz ,  Martin Scholz ,  Benjamin HAAS ,  Thomas Coradi

IPC分类号： G06K9/00

CPC分类号： G06K9/4638 ,  G06K2209/05

摘要： A method of constructing a navigation table relating a set of images representative of a region of interest in a subject to a reference system with reference positions indicating known anatomic landmarks of a reference subject comprising providing reference positions for two or more images identified with two or more anatomic landmarks indicative of the region of interest with reference positions of known anatomic landmarks corresponding to the identified anatomic landmarks, and determining reference positions for the remaining images by interpolation.

摘要翻译： 一种将表示受试者感兴趣区域的一组图像与参考系统相关联的导航表的方法​​，其具有指示参考对象的已知解剖标志的参考位置，该参考位置提供用两个或更多个识别的两个或多个图像的参考位置 指示与所识别的解剖标志相对应的已知解剖学标记的参考位置的感兴趣区域的解剖标志，以及通过插值确定剩余图像的参考位置。