公开(公告)号：US08781254B2

公开(公告)日：2014-07-15

申请号：US12516357

申请日：2007-11-26

申请人： Stewart Young ,  Daniel Bystrov ,  Thomas Netsch ,  Michael Kaus ,  Vladimir Pekar

发明人： Stewart Young ,  Daniel Bystrov ,  Thomas Netsch ,  Michael Kaus ,  Vladimir Pekar

IPC分类号： G06K9/36

CPC分类号： G06T7/149 ,  G06T7/12 ,  G06T7/70 ,  G06T2207/30016

摘要： A method of data processing is provided for estimating a position of an object in an image from a position of a reference object in a reference image. The method includes learning the position of the reference object in the reference image and its relation to a set of reference landmarks in the reference image, accessing the image, accessing the relation between the position of the reference object and the set of the reference landmarks, identifying a set of landmarks in the image corresponding to the set of the reference landmarks, and applying the relation to the set of landmarks in the image for estimating the position of the object in the image.

摘要翻译： 提供一种数据处理方法，用于从参考图像中的参考对象的位置估计图像中的对象的位置。 该方法包括：在参考图像中学习参考对象的位置及其与参考图像中的一组参考地标的关系，访问图像，访问参考对象的位置与参考地标集合之间的关系， 识别对应于所述参考地标集合的图像中的一组地标，以及将所述关系应用于所述图像中的所述地标集合，以估计所述图像中的对象的位置。

公开(公告)号：US20100061632A1

公开(公告)日：2010-03-11

申请号：US12516357

申请日：2007-11-26

申请人： Stewart Young ,  Daniel Bystrov ,  Thomas Netsch ,  Michael Kaus ,  Vladimir Pekar

发明人： Stewart Young ,  Daniel Bystrov ,  Thomas Netsch ,  Michael Kaus ,  Vladimir Pekar

IPC分类号： G06K9/34 ,  G06K9/46

CPC分类号： G06T7/149 ,  G06T7/12 ,  G06T7/70 ,  G06T2207/30016

摘要： The invention relates to a method for data processing. At stage 3 the position of the reference object in the reference image and its relation to a set of reference landmarks in the reference image is established at step 6. In order to enable this, the reference imaging of learning examples may be performed at step 2 and each reference image may be analyzed at step 4, the results may be stored in a suitably arranged database. In order to process the image under consideration, the image is accessed at step 11, the suitable landmark corresponding to the reference landmark in the reference image is identified at step 13 and the spatial relationship established at step 6 is applied to the landmark thereby providing the initial position of the object in the actual image. In case when for the object an imaging volume is selected, the method 1 according to the invention follows to step 7, whereby the scanning 17 is performed within the boundaries given by the thus established scanning volume. In case when for the object a model representative of the target is selected, the method 1 follows to the image segmentation step 19, whereby a suitable segmentation is performed. In case when for the model a deformable model is selected, the segmentation is performed by deforming the model thereby providing spatial boundaries of the target area. The invention further relates to an apparatus and a computer program for image processing.

摘要翻译： 本发明涉及一种数据处理方法。 在阶段3，在步骤6中建立参考图像中的参考对象的位置及其与参考图像中的一组参考标记的关系。为了实现这一点，可以在步骤2执行学习示例的参考成像 并且可以在步骤4分析每个参考图像，结果可以存储在适当布置的数据库中。 为了处理所考虑的图像，在步骤11访问图像，在步骤13识别与参考图像中的参考标记相对应的合适地标，并将在步骤6建立的空间关系应用于地标，从而提供 物体在实际图像中的初始位置。 在对于物体选择成像体积的情况下，根据本发明的方法1遵循步骤7，由此在由这样建立的扫描体积给出的边界内执行扫描17。 在针对对象的情况下，选择了表示目标的模型，则对图像分割步骤19进行方法1，由此执行适当的分割。 在为模型选择可变形模型的情况下，通过使模型变形从而提供目标区域的空间边界来执行分割。 本发明还涉及一种用于图像处理的装置和计算机程序。

公开(公告)号：US08000508B2

公开(公告)日：2011-08-16

申请号：US11814406

申请日：2006-01-05

申请人： Daniel Bystrov ,  Vladimir Pekar ,  Kirsten Meetz ,  Thomas Netsch ,  Stewart Young

发明人： Daniel Bystrov ,  Vladimir Pekar ,  Kirsten Meetz ,  Thomas Netsch ,  Stewart Young

IPC分类号： G06K9/00

CPC分类号： G06T13/20 ,  G06T7/246 ,  G06T2207/10076 ,  G06T2207/10088 ,  G06T2207/30048

摘要： In a diagnostic imaging system (10), a user interface (82) facilitates viewing of 4D kinematic data sets. A set of reference points is selected in a first 3D image to designate an anatomical component. An algorithm (104) calculates a propagation of the selected reference points from the first 3D image into other 3D images. Transforms which describe the propagation of the reference points between 3D images are defined. An aligning algorithm (112) applies inverse of the transforms to the 3D images to define a series of frames for the video processor (120) to display, in which frames the designated anatomical component defined by the reference points in each of the 3D images remains fixed while the other portions of the anatomical region of interest move relative to the fixed designated anatomical component.

摘要翻译： 在诊断成像系统（10）中，用户界面（82）便于观看4D运动数据集。 在第一3D图像中选择一组参考点以指定解剖组件。 算法（104）计算所选择的参考点从第一3D图像到其他3D图像的传播。 定义描述3D图像之间参考点传播的变换。 对准算法（112）将变换的逆向应用于3D图像以定义用于视频处理器（120）显示的一系列帧，其中由每个3D图像中的参考点定义的指定解剖组件保留 固定，而感兴趣的解剖区域的其他部分相对于固定的指定解剖部件移动。

公开(公告)号：US20080069418A1

公开(公告)日：2008-03-20

申请号：US11814406

申请日：2006-01-05

申请人： Daniel Bystrov ,  Vladimir Pekar ,  Kirsten Meetz ,  Thomas Netsch ,  Stewart Young

发明人： Daniel Bystrov ,  Vladimir Pekar ,  Kirsten Meetz ,  Thomas Netsch ,  Stewart Young

IPC分类号： G06K9/00

CPC分类号： G06T13/20 ,  G06T7/246 ,  G06T2207/10076 ,  G06T2207/10088 ,  G06T2207/30048

摘要： In a diagnostic imaging system (10), a user interface (82) facilitates viewing of 4D kinematic data sets. A set of reference points is selected in a first 3D image to designate an anatomical component. An algorithm (104) calculates a propagation of the selected reference points from the first 3D image into other 3D images. Transforms which describe the propagation of the reference points between 3D images are defined. An aligning algorithm (112) applies inverse of the transforms to the 3D images to define a series of frames for the video processor (120) to display, in which frames the designated anatomical component defined by the reference points in each of the 3D images remains fixed while the other portions of the anatomical region of interest move relative to the fixed designated anatomical component.

摘要翻译： 在诊断成像系统（10）中，用户界面（82）便于观看4D运动数据集。 在第一3D图像中选择一组参考点以指定解剖组件。 算法（104）计算所选择的参考点从第一3D图像到其他3D图像的传播。 定义描述3D图像之间参考点传播的变换。 对准算法（112）将变换的逆向应用于3D图像以定义用于视频处理器（120）显示的一系列帧，其中由每个3D图像中的参考点定义的指定解剖组件保留 固定，而感兴趣的解剖区域的其他部分相对于固定的指定解剖部件移动。

公开(公告)号：US20090067696A1

公开(公告)日：2009-03-12

申请号：US12279992

申请日：2007-02-12

申请人： Daniel Bystrov ,  Thomas Netsch ,  Stewart Young

发明人： Daniel Bystrov ,  Thomas Netsch ,  Stewart Young

IPC分类号： G06K9/00

CPC分类号： G01R33/543 ,  G01R33/5608

摘要： The present invention relates to a geometry planning software product for magnetic resonance system, comprising a database manager arranged to process an anatomical landmark set and a planning geometry of a current geometry planning session by forming a combination of both, and to add said combination to a database. The invention enables the learning of relevance of different anatomical structures for a specific planning geometry from user input. It also enables fully automated outlier detection.

摘要翻译： 本发明涉及一种用于磁共振系统的几何规划软件产品，其包括数据库管理器，其被布置为通过形成两者的组合来处理解剖学标记集和当前几何规划会话的规划几何，并将所述组合添加到 数据库。 本发明使得能够从用户输入中学习不同解剖结构与特定规划几何的相关性。 它还可以实现全自动异常值检测。

公开(公告)号：US20080281569A1

公开(公告)日：2008-11-13

申请号：US12094195

申请日：2006-11-08

申请人： Thomas Netsch ,  Daniel Bystrov ,  Stewart Young

发明人： Thomas Netsch ,  Daniel Bystrov ,  Stewart Young

IPC分类号： G06G7/60 ,  G06K9/62 ,  G06K9/48

CPC分类号： G06K9/6255 ,  A61B5/0037 ,  G06K2209/055 ,  G06T7/33 ,  G06T7/35 ,  G06T17/10 ,  G06T2207/30016

摘要： A method for creating a model of a part of the anatomy from the scan data of several subjects is described. The method comprises the steps of collecting scan data; applying a feature detector to the scan data; converted the output of the feature detector into a common reference system; and accumulating the converted data to generate the model. It is therefore possible for the method to generate a model from the scan data of several subjects automatically. The method may also include an optional step of receiving user input to select which of the accumulated data should be included in the final model. This user input requires much less effort than manual contouring and is substantially independent of the number of subjects used to create the model.

摘要翻译： 描述了从几个对象的扫描数据创建解剖结构的一部分的模型的方法。 该方法包括收集扫描数据的步骤; 将特征检测器应用于扫描数据; 将特征检测器的输出转换为公共参考系统; 并累积转换的数据以生成模型。 因此，该方法可以自动地从几个被摄对象的扫描数据生成模型。 该方法还可以包括接收用户输入以选择应该包括在最终模型中的累积数据中的哪一个的可选步骤。 该用户输入需要比手动轮廓更少的精力，并且基本上独立于用于创建模型的主体的数量。

公开(公告)号：US08369927B2

公开(公告)日：2013-02-05

申请号：US12094195

申请日：2006-11-08

申请人： Thomas Netsch ,  Daniel Bystrov ,  Stewart Young

发明人： Thomas Netsch ,  Daniel Bystrov ,  Stewart Young

IPC分类号： A61B5/05 ,  G06K9/00 ,  G06K9/34 ,  G06K9/46

CPC分类号： G06K9/6255 ,  A61B5/0037 ,  G06K2209/055 ,  G06T7/33 ,  G06T7/35 ,  G06T17/10 ,  G06T2207/30016

摘要： A method for creating a model of a part of the anatomy from the scan data of several subjects is described. The method comprises the steps of collecting scan data; applying a feature detector to the scan data; converted the output of the feature detector into a common reference system; and accumulating the converted data to generate the model. It is therefore possible for the method to generate a model from the scan data of several subjects automatically. The method may also include an optional step of receiving user input to select which of the accumulated data should be included in the final model. This user input requires much less effort than manual contouring and is substantially independent of the number of subjects used to create the model.

摘要翻译： 描述了从几个对象的扫描数据创建解剖结构的一部分的模型的方法。 该方法包括收集扫描数据的步骤; 将特征检测器应用于扫描数据; 将特征检测器的输出转换为公共参考系统; 并累积转换的数据以生成模型。 因此，该方法可以自动地从几个被摄对象的扫描数据生成模型。 该方法还可以包括接收用户输入以选择应该包括在最终模型中的累积数据中的哪一个的可选步骤。 该用户输入需要比手动轮廓更少的精力，并且基本上独立于用于创建模型的主体的数量。

公开(公告)号：US08144955B2

公开(公告)日：2012-03-27

申请号：US12279992

申请日：2007-02-12

申请人： Daniel Bystrov ,  Thomas Netsch ,  Stewart Young

发明人： Daniel Bystrov ,  Thomas Netsch ,  Stewart Young

IPC分类号： G06K900/200601

CPC分类号： G01R33/543 ,  G01R33/5608

摘要： A function generator (MFG) formulates a query to a mapping database (DBM) based on a received planning geometry type (PGT) and receives corresponding function data (MFD) which is processed to create a function (MF). An evaluator (ELV) receives the function (MF) and an anatomical landmark set (LMS) and determines a computed planning geometry (CPG). A user interface (UI) displays a survey image (IMG), the landmark set (LMS), and the computer planning geometry (CPG) and allows the user to adjust the landmark set and/or the computer program geometry. A record generator (RG) creates a new record from the user adjusted landmarks (ULMS) and the user adjusted computer planning geometries (UPG) and loads the new records (NR) into the mapping database (DBM).

摘要翻译： 函数发生器（MFG）基于接收到的规划几何类型（PGT）向映射数据库（DBM）制定查询，并接收被处理以创建功能（MF）的相应功能数据（MFD）。 评估者（ELV）接收功能（MF）和解剖学地标集（LMS）并确定计算出的计划几何（CPG）。 用户界面（UI）显示调查图像（IMG），地标集（LMS）和计算机规划几何（CPG），并允许用户调整地标集和/或计算机程序几何。 记录发生器（RG）从用户调整的地标（ULMS）和用户调整的计算机规划几何（UPG）创建新记录，并将新记录（NR）加载到映射数据库（DBM）中。

公开(公告)号：US20080285821A1

公开(公告)日：2008-11-20

申请号：US12067842

申请日：2006-09-07

申请人： Christian Adrian Cocosco ,  Thomas Netsch ,  Daniel Bystrov ,  Stewart Young

发明人： Christian Adrian Cocosco ,  Thomas Netsch ,  Daniel Bystrov ,  Stewart Young

IPC分类号： G06K9/00

CPC分类号： G06T7/0012 ,  G06T7/11 ,  G06T7/149 ,  G06T2207/10072 ,  G06T2207/20081 ,  G06T2207/30004

摘要： The invention relates to a method 1 of image segmentation where in step 2 a prior model representative of a structure conceived to be segmented in an image is accessed. Preferably, the image comprises a medical diagnostic image. Still preferably, the medical diagnostic image is prepared in a DICOM format, whereby supplementary information is stored besides diagnostic data. In these cases the method 1 according to the invention advantageously proceeds to step 3, where the supplementary information is extracted from electronic file 5, comprising for example suitable patient-related information 5a and/or suitable structure-related information 5b. Examples of the patient-related information comprise a patient's age, sex, group, etc., whereas examples of the structure-related information may comprise an anatomic location of the structure, such as rectum, bladder, lung etc, or the suspected/diagnosed pathology of the patient. In an alternative embodiment of the method 1 according to the invention, the supplementary information is provided by a human operator in step 7, where he can enter suitable supplementary information 9a, 9b using a user interface 9. When the supplementary information is loaded, the method 1 according to the invention proceeds to step 4 in which the prior model is being changed using the supplementary information yielding a further model. In step 6 the method 1 performs the image segmentation using the thus obtained further model and in step 8 the results of the segmentation step may be visualized on a suitable viewer.

摘要翻译： 本发明涉及一种图像分割的方法1，其中在步骤2中，访问了代表在图像中被分割的结构的先前模型。 优选地，图像包括医学诊断图像。 更优选地，以DICOM格式准备医疗诊断图像，除了诊断数据之外还存储补充信息。 在这些情况下，根据本发明的方法1有利地进行到步骤3，其中从电子文件5中提取补充信息，包括例如适合的患者相关信息5a和/或合适的结构相关信息5b。 患者相关信息的示例包括患者的年龄，性别，组等，而结构相关信息的实例可以包括结构的解剖位置，例如直肠，膀胱，肺等或疑似/诊断的 患者病理。 在根据本发明的方法1的替代实施例中，补充信息由人类操作者在步骤7中提供，在那里他可以使用用户界面9输入合适的补充信息9a，9b。 当加载补充信息时，根据本发明的方法1进行到步骤4，在步骤4中，使用产生另外的模型的补充信息来改变现有模型。 在步骤6中，方法1使用由此获得的另外的模型执行图像分割，并且在步骤8中，分割步骤的结果可以在合适的观看者上可视化。

公开(公告)号：US20090060319A1

公开(公告)日：2009-03-05

申请号：US11911128

申请日：2006-04-13

申请人： Christian Adrian Cocosco ,  Stewart Young ,  Thomas Netsch ,  Michael Kaus

发明人： Christian Adrian Cocosco ,  Stewart Young ,  Thomas Netsch ,  Michael Kaus

IPC分类号： G06K9/00 ,  G06K9/34

CPC分类号： G06T7/149 ,  G06T7/12 ,  G06T2207/10072 ,  G06T2207/30048

摘要： The method according to the invention is arranged to segment a surface in a multi-dimensional dataset comprising a plurality of images, which may be acquired using a suitable data-acquisition unit at a preparatory step 2. It is possible that data processing and data acquisition steps are temporally or geographically distanced, so that at step 4 the results of a suitable data segmentation step 6 are accessed, whereby said results comprise portions of the image which are subsequently used to segment the surface using the method of the invention. Next, at step 8 a suitable plurality of image features resembling possible spatial positions of the surface conceived to be segmented are selected and accessed. The features are subsequently matched for all image portions at step 10, whereby for each feature a matching error is assigned. At step 14 a pre-defined selectivity factor is accessed defining a maximum allowable variable fraction of the features having largest matching errors which can be discarded. The segmentation of the sought surface is performed at step 16, whereby the discarded features are not taken into account for evaluating the quality of fit of a candidate deformation of the. The resulting surface is being displayed on a suitable display means at step 18, whereby it is preferably overlaid on original, notably diagnostic data for user's analysis. In case when the user is satisfied with the result of the segmentation, the segmented surface is stored at step 18. Otherwise, the process is returned to step 14, where a further selectivity factor is accessed. It is possible that the further selectivity factor is altered at step 11 by a user's input, or, alternatively it may be provided by a certain alteration algorithm 13. The invention further relates to a system, a computer program, a workstation, a viewing station, a computer program and a user interface.

摘要翻译： 根据本发明的方法被布置为在包括多个图像的多维数据集中分割表面，所述多个图像可以在准备步骤2使用合适的数据获取单元获取。可能的是，数据处理和数据采集 步骤在时间上或地理上是间距的，使得在步骤4中，访问合适的数据分割步骤6的结果，由此所述结果包括随后用于使用本发明的方法分割表面的图像的部分。 接下来，在步骤8中，选择并访问类似于被分割的表面的可能的空间位置的合适的多个图像特征。 随后在步骤10对所有图像部分匹配特征，由此为每个特征分配匹配误差。 在步骤14，访问预定义的选择性因子，定义可以丢弃具有最大匹配误差的特征的最大允许可变分数。 在步骤16执行所寻求的表面的分割，由此不考虑丢弃的特征来评估候选变形的拟合质量。 在步骤18，所得到的表面被显示在合适的显示装置上，由此优选地覆盖在原始的，特别是用于用户分析的诊断数据上。 在用户对分割结果满意的情况下，在步骤18存储分割曲面。否则，该过程返回到步骤14，其中进一步选择性因子被访问。 在步骤11，用户的输入可以改变另外的选择性因素，或者也可以由某个改变算法13提供。本发明还涉及系统，计算机程序，工作站，观察台 ，计算机程序和用户界面。