专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

WO2006034366A1 HIERARCHICAL MEDICAL IMAGE VIEW DETERMINATION 审中-公开
标题翻译：分层医学图像检测
公开(公告)号：WO2006034366A1
公开(公告)日：2006-03-30
申请号：PCT/US2005/033876
申请日：2005-09-21
申请人： SIEMENS MEDICAL SOLUTIONS USA, INC. , KRISHNAN, Sriram , BI, Jinbo , RAO, R., Bharat , STOECKEL, Jonathan , OTEY, Matthew, Eric
发明人： KRISHNAN, Sriram , BI, Jinbo , RAO, R., Bharat , STOECKEL, Jonathan , OTEY, Matthew, Eric
IPC分类号： G06K9/68 , G06T7/00
CPC分类号： G06T7/0012 , G06K9/6217 , G06K9/6282 , G06T2207/30048
摘要： A cardiac view of a medical ultrasound image is automatically identified (24, 26, 28). By grouping different views into sub-categories, a hierarchal classifier identifies the views. For example, apical views are distinguished (24) from parasternal views. Specific types of apical or parasternal views are identified (26, 28) based on distinguishing between images of the geneses. Different features are used for classifying, such as gradients, functions of the gradients, statistics of an average frame of data from a clip or sequence of frames, or a number of edges along a given direction. The number of features used may be compressed (22), such as by classifying a plurality of features into a new feature. For example, alpha weights in a model of features and classes are determined and used as features for classification
摘要翻译：自动识别医学超声图像的心脏视图（24,26,28）。通过将不同的视图分组到子类别中，层级分类器标识视图。例如，顶峰视图与胸骨旁观点（24）不同。基于区分基因图像，确定了顶端或胸骨旁观察的具体类型（26,28）。不同的特征用于分类，例如梯度，梯度的功能，来自剪辑或帧序列的平均数据帧的统计，或沿给定方向的多个边缘的统计。所使用的特征的数量可以被压缩（22），例如通过将多个特征分类为新特征。例如，确定特征和类的模型中的α权重并将其用作分类的特征

2. 发明申请

WO2007044504A1 AUTOMATIC CAD ALGORITHM SELECTION 审中-公开
标题翻译：自动CAD算法选择
公开(公告)号：WO2007044504A1
公开(公告)日：2007-04-19
申请号：PCT/US2006/039102
申请日：2006-10-05
申请人： SIEMENS MEDICAL SOLUTIONS USA, INC. , KRISHNAN, Arun , STOECKEL, Jonathan
发明人： KRISHNAN, Arun , STOECKEL, Jonathan
IPC分类号： G06T7/00
CPC分类号： G06T7/0012 , G06F19/00 , G06F19/321 , G06Q50/24 , G06T2207/30004 , G16H50/20
摘要： A computer system for automatic selection of a computer-aided detection (CAD) algorithm including a database (102) storing image data, a browser (103) for navigating the data and selecting image data, an application (104) receiving image data selected by the browser, and a selector (107) selecting a CAD algorithm for processing the image data according to at least one of fixed attributes of the image data and an indication of a subject of the image data.
摘要翻译：一种用于自动选择计算机辅助检测（CAD）算法的计算机系统，包括存储图像数据的数据库（102），用于导航数据和选择图像数据的浏览器（103），接收由浏览器和选择器（107），其根据图像数据的固定属性和图像数据的对象的指示中的至少一个来选择用于处理图像数据的CAD算法。

3. 发明申请

WO2007016280A2 SYSTEM AND METHOD FOR BODY EXTRACTION IN MEDICAL IMAGE VOLUMES 审中-公开
标题翻译：医学图像体内体内提取的系统和方法
公开(公告)号：WO2007016280A2
公开(公告)日：2007-02-08
申请号：PCT/US2006/029269
申请日：2006-07-27
申请人： SIEMENS MEDICAL SOLUTIONS USA, INC. , GUÉTAT, Grégoire , STOECKEL, Jonathan , WOLF, Matthias
发明人： GUÉTAT, Grégoire , STOECKEL, Jonathan , WOLF, Matthias
CPC分类号： A61B6/5252 , G06T7/12 , G06T7/149 , G06T2207/10081 , G06T2207/30004
摘要： A method for identifying non-body structures in digitized medical images including the steps of providing a digitized image comprising a plurality of intensities corresponding to a domain of points on an N-dimensional grid, wherein said image includes a representation of a body and of non-body structures separate from said body, initializing (11) a surface in said image on a side of said non-body structures opposite from said body, defining (13) a plurality of forces acting on said surface, and displacing (14) said surface through said non-body structures using said forces until said body is encountered.
摘要翻译：一种用于识别数字化医学图像中的非身体结构的方法，包括以下步骤：提供包括与N维网格上的点的区域相对应的多个强度的数字化图像，其中所述图像包括身体和非身体结构的表示，与所述主体分开的主体结构，初始化（11）所述图像中与所述主体相对的所述非体部结构的一侧上的表面，限定（13）多个作用在所述表面上的力，并且移位（14）所述通过使用所述力的所述非身体结构的表面，直到遇到所述身体。

4. 发明申请

WO2006055031A2 METHOD AND SYSTEM FOR LOCAL VISUALIZATION FOR TUBULAR STRUCTURES 审中-公开
标题翻译：用于管状结构局部可视化的方法和系统
公开(公告)号：WO2006055031A2
公开(公告)日：2006-05-26
申请号：PCT/US2005/014728
申请日：2005-05-02
申请人： SIEMENS MEDICAL SOLUTIONS USA, INC. , CATHIER, Pascal , STOECKEL, Jonathan
发明人： CATHIER, Pascal , STOECKEL, Jonathan
IPC分类号： G06T7/00
CPC分类号： G06T19/00 , G06T7/62 , G06T7/70 , G06T2207/30101 , G06T2210/41
摘要： A method of visualizing an object in an image includes presenting an image, selecting (50) a point in an object of interest in said image, estimating (51) a gradient of the image in a region about the selected point, calculating (52) a structure tensor from the image gradient, analyzing (53) said structure tensor to determine a main orientation of said object of interest, and presenting (54) a visualization of said object of interest based on the main orientation of the object. Various techniques can be used to increase the robustness of the gradient estimation with respect to noise, and to enhance the visualization of the object-of-interest presented to a user.
摘要翻译：一种使图像中的对象可视化的方法包括呈现图像，选择（50）所述图像中的感兴趣对象中的点，估计（51）图像中关于（52）从图像梯度计算（52）结构张量，分析（53）所述结构张量以确定所述感兴趣对象的主要取向，以及基于主要图像呈现（54）所述感兴趣对象的可视化对象的方向。可以使用各种技术来增加关于噪声的梯度估计的稳健性，并且增强呈现给用户的感兴趣对象的可视化。

5. 发明申请

WO2007019257A1 SYSTEM AND METHOD FOR QUALITY ASSURANCE FOR DISTRIBUTED COMPUTER AIDED DIAGNOSIS 审中-公开
标题翻译：用于分布式计算机辅助诊断的质量保证的系统和方法
公开(公告)号：WO2007019257A1
公开(公告)日：2007-02-15
申请号：PCT/US2006/030341
申请日：2006-07-31
申请人： SIEMENS MEDICAL SOLUTIONS USA, INC. , STOECKEL, Jonathan
发明人： STOECKEL, Jonathan
IPC分类号： G06T7/00 , G06T1/00
CPC分类号： G06T7/0012 , G06F19/00 , G06F19/321
摘要： A method for associating a computer aided detection/diagnosis result with an image including the steps of providing (10) one or more digitized images, each image comprising a plurality of intensities corresponding to a domain of points on an N-dimensional grid, performing (11) a computer-aided detection/diagnosis of intensity data of a first image, calculating (12) a hash signature of intensity of a second input image, storing (13) said computer-aided diagnosis results, and storing (13) said hash signature, wherein said hash signature verifies said second image when said second image is displayed (19) with said computer-aided diagnosis result.
摘要翻译：一种用于将计算机辅助检测/诊断结果与图像相关联的方法，包括以下步骤：提供（10）一个或多个数字化图像，每个图像包括对应于N维网格上的点的域的多个强度，执行（ 11）计算机辅助检测/诊断第一图像的强度数据，计算（12）第二输入图像的强度的散列签名，存储（13）所述计算机辅助诊断结果，并存储（13）所述散列签名，其中当利用所述计算机辅助诊断结果显示所述第二图像（19）时，所述散列签名验证所述第二图像。

6. 发明申请

WO2006052516A1 SYSTEM AND METHOD FOR A CONTIGUOUS SUPPORT VECTOR MACHINE 审中-公开
标题翻译：一种连续支持向量机的系统与方法
公开(公告)号：WO2006052516A1
公开(公告)日：2006-05-18
申请号：PCT/US2005/039335
申请日：2005-11-01
申请人： SIEMENS MEDICAL SOLUTIONS USA, INC. , STOECKEL, Jonathan , FUNG, Glenn
发明人： STOECKEL, Jonathan , FUNG, Glenn
IPC分类号： G06K9/68 , G06T7/00
CPC分类号： G06K9/6292 , G06T7/0012 , G06T7/33 , G06T2207/30016
摘要： A method of classifying features in digitized images includes providing a plurality of feature points in an n-dimensional space, wherein said feature points have been extracted (23) from a digitized medical image, formulating (24) a support vector machine to classify said feature point into one of two sets, wherein each said feature classification vector is transformed (25) by an adjacency matrix defined by those points that are nearest neighbors of said feature, and solving (26) said support vector machine by a linear optimization algorithm to determine a classifying plane that separates the feature vectors into said two sets.
摘要翻译：对数字化图像中的特征进行分类的方法包括在n维空间中提供多个特征点，其中所述特征点已经从数字化医学图像中提取（23），制定（24）支持向量机以将所述特征指向两组中的一组，其中每个所述特征分类矢量由由所述特征的最近邻的那些点定义的相邻矩阵变换（25），并且通过线性优化算法求解（26）所述支持向量机以确定将特征向量分离成所述两组的分类平面。

7. 发明申请

WO2007117506A3 SYSTEM AND METHOD FOR AUTOMATIC DETECTION OF INTERNAL STRUCTURES IN MEDICAL IMAGES 审中-公开
公开(公告)号：WO2007117506A3
公开(公告)日：2007-10-18
申请号：PCT/US2007/008397
申请日：2007-04-03
申请人： SIEMENS MEDICAL SOLUTIONS USA, INC. , MYSORE SIDDU, Dinesh , ACHARYYA, Mausumi , STOECKEL, Jonathan
发明人： MYSORE SIDDU, Dinesh , ACHARYYA, Mausumi , STOECKEL, Jonathan
IPC分类号： G06K9/46 , G06T5/00
摘要： A medical imaging system is used to recognize an internal structure from a three-dimensional image. A medical image is acquired (Step S10). The image includes image sub-volumes. An image sub-volume is selected using a non-linear search pattern (Step S11). The selected image sub-volume is analyzed for the presence of the internal structure (Step S12). The steps of selecting an image sub-volume using the non-linear search pattern and analyzing the selected sub-volume for the presence of the internal structure are repeated until the internal structure is found in an image sub-volume (Step S12). The internal structure is identified (Step S13). Bounds of the internal structure are found based on the location of the image sub-volume within which the internal structure is found (Step S14).

8. 发明申请

WO2006062540A2 SHAPE INDEX WEIGHTED VOTING FOR DETECTION OF OBJECTS 审中-公开
标题翻译：形状指标用于检测物体的加权投票
公开(公告)号：WO2006062540A2
公开(公告)日：2006-06-15
申请号：PCT/US2005/015608
申请日：2005-05-05
申请人： SIEMENS MEDICAL SOLUTIONS USA, INC. , CATHIER, Pascal , ZHANG, Xiangwei , STOECKEL, Jonathan , WOLF, Matthias
发明人： CATHIER, Pascal , ZHANG, Xiangwei , STOECKEL, Jonathan , WOLF, Matthias
CPC分类号： G06T7/0012 , G06K9/4671 , G06T2207/30061 , Y10S128/922
摘要： In one aspect of the present invention, a method for calculating a response value at a first voxel indicative of a global shape in an image is provided. The method includes the steps of (a) determining at least one local shape descriptor associated with each of the at least one local shape descriptor; (b) determining a spread function associated with the each of the at least one local shape descriptor; (c) determining second voxels around the first voxel; (d) calculating values for each the at least one local shape descriptor at each of the second voxels; (e) determining a contribution of each of the second voxels at the first voxel based on the spread functions; and (f) using a combination function to combine the contributions to determine the response value indicative of the global shape
摘要翻译：在本发明的一个方面，提供了一种用于计算在图像中指示全局形状的第一体素处的响应值的方法。该方法包括以下步骤：（a）确定与所述至少一个局部形状描述符中的每一个相关联的至少一个局部形状描述符; （b）确定与所述至少一个局部形状描述符中的每一个相关联的扩展函数; （c）确定第一体素周围的第二体素; （d）在每个第二体素处计算每个所述至少一个局部形状描述符的值; （e）基于扩展函数确定第一体素中的每个第二体素的贡献; 和（f）使用组合函数来组合贡献以确定指示全局形状的响应值

9. 发明申请

WO2006057663A2 METHOD AND SYSTEM FOR INTERACTIVE VISUALIZATION OF LOCALLY ORIENTED STRUCTURES 审中-公开
标题翻译：用于局部取向结构的交互式可视化的方法和系统
公开(公告)号：WO2006057663A2
公开(公告)日：2006-06-01
申请号：PCT/US2005/015010
申请日：2005-04-29
申请人： SIEMENS MEDICAL SOLUTIONS USA, INC. , CATHIER, Pascal , STOECKEL, Jonathan
发明人： CATHIER, Pascal , STOECKEL, Jonathan
IPC分类号： G06T7/00
CPC分类号： G06T7/60 , G06T7/0012 , G06T2207/30101
摘要： A method of visualizing an object in an image includes presenting (10) an image, selecting (11) a point in an object of interest in said image, determining (12) a main orientation of said object of interest, presenting (13) a first visualization of said object of interest, wherein said first visualization has a first display orientation characterized by the direction of a vector normal to the first visualization plane, and selecting (14) a new point as a center of a new visualization and presenting (15) said new visualization, wherein said new visualization has a new display orientation characterized by the direction of a vector normal to the new visualization plane
摘要翻译：在图像中可视化对象的方法包括呈现（10）图像，选择（11）所述图像中的感兴趣对象中的点，确定所述感兴趣对象的主方向，呈现（13）a 所述第一可视化具有第一显示取向，其特征在于垂直于第一可视平面的向量的方向，并且选择（14）新点作为新可视化的中心并呈现（15））所述新的可视化，其中所述新的可视化具有以垂直于新的可视化平面的向量的方向为特征的新的显示方向

10. 发明申请

WO2005017815A2 INCORPORATING SPATIAL KNOWLEDGE FOR CLASSIFICATION 审中-公开
标题翻译：结合分类的空间知识
公开(公告)号：WO2005017815A2
公开(公告)日：2005-02-24
申请号：PCT/US2004/026425
申请日：2004-08-13
申请人： SIEMENS MEDICAL SOLUTIONS USA, INC.
发明人： KRISHNAN, Arun , FUNG, Glenn , STOECKEL, Jonathan
IPC分类号： G06K9/00
CPC分类号： G06T7/0012 , G06K9/6807 , G06T2207/10072 , G06T2207/20012 , G06T2207/30064
摘要： We propose using different classifiers based on the spatial location of the object. The intuitive idea behind this approach is that several classifiers may learn local concepts better than a "universal" classifier that covers the whole feature space. The use of local classifiers ensures that the objects of a particular class have a higher degree of resemblance within that particular class. The use of local classifiers also results in memory, storage and performance improvements, especially when the classifier is kernel-based. As used herein, the term "kernel-based classifier" refers to a classifier where a mapping function (i.e., the kernel) has been used to map the original training data to a higher dimensional space where the classification task may be easier.
摘要翻译：
我们建议根据对象的空间位置使用不同的分类器。这种方法背后的直观思想是几个分类器可以比“通用”分类器更好地学习本地概念。分类器覆盖整个特征空间。使用本地分类器可确保特定类的对象在该特定类中具有更高的相似度。使用本地分类器还会导致内存，存储和性能改进，特别是当分类器基于内核时。如本文所使用的，术语“基于内核的分类器” 指的是其中映射函数（即，内核）已被用于将原始训练数据映射到分类任务可能更容易的更高维空间的分类器。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式