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. 发明授权

US09008393B2 Vessel identification using shape and motion mapping for coronary angiogram sequences 有权
标题翻译：使用冠状动脉造影序列的形状和运动映射的血管识别
公开(公告)号：US09008393B2
公开(公告)日：2015-04-14
申请号：US13593004
申请日：2012-08-23
申请人： David J. Beymer , Hayit Greenspan , Tanveer Syeda-Mahmood , Fei Wang , Yong Zhang
发明人： David J. Beymer , Hayit Greenspan , Tanveer Syeda-Mahmood , Fei Wang , Yong Zhang
IPC分类号： G06K9/00 , G06K9/46 , G06K9/62 , G06T7/00
CPC分类号： G06T7/0085 , G06K9/4671 , G06K9/6269 , G06K9/628 , G06T7/13 , G06T2207/30101 , G06T2207/30172
摘要： Embodiments of the invention relate to automating image classification with respect to coronary vessels in an angiography sequence. Two primary elements are employed, including training and recognition. Training pertains to the pre-processing images and extracting salient features that characterize the appearance of coronary arteries under different viewpoints. Recognition pertains to extraction of features from a new image sequence and determining a classification boundary for the new image from previously classified and labeled image sequences.
摘要翻译：本发明的实施例涉及在血管造影顺序中相对于冠状动脉血管自动化图像分类。雇用了两个主要因素，包括培训和认可。训练属于预处理图像，并提取不同观点表征冠状动脉外观的突出特征。识别涉及从新图像序列中提取特征并且从先前分类和标记的图像序列确定新图像的分类边界。

2. 发明申请

US20130315458A1 Vessel Identification Using Shape and Motion Mapping for Coronary Angiogram Sequences 有权
标题翻译：血管识别使用形状和运动映射冠状动脉造影序列
公开(公告)号：US20130315458A1
公开(公告)日：2013-11-28
申请号：US13593004
申请日：2012-08-23
申请人： David J. Beymer , Hayit Greenspan , Tanveer Syeda-Mahmood , Fei Wang , Yong Zhang
发明人： David J. Beymer , Hayit Greenspan , Tanveer Syeda-Mahmood , Fei Wang , Yong Zhang
IPC分类号： G06K9/00
CPC分类号： G06T7/0085 , G06K9/4671 , G06K9/6269 , G06K9/628 , G06T7/13 , G06T2207/30101 , G06T2207/30172
摘要： Embodiments of the invention relate to automating image classification with respect to coronary vessels in an angiography sequence. Two primary elements are employed, including training and recognition. Training pertains to the pre-processing images and extracting salient features that characterize the appearance of coronary arteries under different viewpoints. Recognition pertains to extraction of features from a new image sequence and determining a classification boundary for the new image from previously classified and labeled image sequences.
摘要翻译：本发明的实施例涉及在血管造影顺序中相对于冠状动脉血管自动化图像分类。雇用了两个主要因素，包括培训和认可。训练属于预处理图像，并提取不同观点表征冠状动脉外观的突出特征。识别涉及从新图像序列中提取特征并且从先前分类和标记的图像序列确定新图像的分类边界。

3. 发明授权

US09053551B2 Vessel identification using shape and motion mapping for coronary angiogram sequences 有权
标题翻译：使用冠状动脉造影序列的形状和运动映射的血管识别
公开(公告)号：US09053551B2
公开(公告)日：2015-06-09
申请号：US13479219
申请日：2012-05-23
申请人： David J. Beymer , Hayit Greenspan , Tanveer Syeda-Mahmood , Fei Wang , Yong Zhang
发明人： David J. Beymer , Hayit Greenspan , Tanveer Syeda-Mahmood , Fei Wang , Yong Zhang
IPC分类号： G06K9/00 , G06T7/00 , G06K9/46 , G06K9/62
CPC分类号： G06T7/0085 , G06K9/4671 , G06K9/6269 , G06K9/628 , G06T7/13 , G06T2207/30101 , G06T2207/30172
摘要： Embodiments of the invention relate to a method, system, and computer program product to automate image classification with respect to coronary vessels in an angiography sequence. Two primary elements are employed, including training and recognition. Training pertains to the pre-processing images and extracting salient features that characterize the appearance of coronary arteries under different viewpoints. Recognition pertains to extraction of features from a new image sequence and determining a classification boundary for the new image from previously classified and labeled image sequences.
摘要翻译：本发明的实施例涉及在血管造影顺序中相对于冠状动脉血管自动化图像分类的方法，系统和计算机程序产品。雇用了两个主要因素，包括培训和认可。训练属于预处理图像，并提取不同观点表征冠状动脉外观的突出特征。识别涉及从新图像序列中提取特征并且从先前分类和标记的图像序列确定新图像的分类边界。

4. 发明申请

US20130315457A1 Vessel Identification Using Shape and Motion Mapping for Coronary Angiogram Sequences 有权
标题翻译：血管识别使用形状和运动映射冠状动脉造影序列
公开(公告)号：US20130315457A1
公开(公告)日：2013-11-28
申请号：US13479219
申请日：2012-05-23
申请人： David J. Beymer , Hayit Greenspan , Tanveer Syeda-Mahmood , Fei Wang , Yong Zhang
发明人： David J. Beymer , Hayit Greenspan , Tanveer Syeda-Mahmood , Fei Wang , Yong Zhang
IPC分类号： G06K9/00
CPC分类号： G06T7/0085 , G06K9/4671 , G06K9/6269 , G06K9/628 , G06T7/13 , G06T2207/30101 , G06T2207/30172
摘要： Embodiments of the invention relate to a method, system, and computer program product to automate image classification with respect to coronary vessels in an angiography sequence. Two primary elements are employed, including training and recognition. Training pertains to the pre-processing images and extracting salient features that characterize the appearance of coronary arteries under different viewpoints. Recognition pertains to extraction of features from a new image sequence and determining a classification boundary for the new image from previously classified and labeled image sequences.
摘要翻译：本发明的实施例涉及在血管造影顺序中相对于冠状动脉血管自动化图像分类的方法，系统和计算机程序产品。雇用了两个主要因素，包括培训和认可。训练属于预处理图像，并提取不同观点表征冠状动脉外观的突出特征。识别涉及从新图像序列中提取特征并且从先前分类和标记的图像序列确定新图像的分类边界。

5. 发明申请

US20070156622A1 Method and system to compose software applications by combining planning with semantic reasoning 审中-公开
标题翻译：通过将规划与语义推理相结合来组合软件应用程序的方法和系统
公开(公告)号：US20070156622A1
公开(公告)日：2007-07-05
申请号：US11325902
申请日：2006-01-05
申请人： Rama Akkiraju , Richard Goodwin , Anca-Andreea Ivan , Biplav Srivastava , Tanveer Syeda-Mahmood
发明人： Rama Akkiraju , Richard Goodwin , Anca-Andreea Ivan , Biplav Srivastava , Tanveer Syeda-Mahmood
IPC分类号： G06N5/02
CPC分类号： G06N5/02
摘要： A system and method for composing application services includes an indexing module configured to index words in a request and available application descriptions to create a semantic similarity map. A semantic matcher is configured to determine semantic similarity between concepts/terms in both domain-independent and domain-specific ontologies for the semantic similarity map. A prefiltering module is configured to determine candidate compositions for the request based on the semantic similarity map and the available descriptions. A metric guided composition method is configured to run algorithms to generate a set of alternative compositions by determining which applications can be composed with which others using the semantic similarity map.
摘要翻译：用于组合应用服务的系统和方法包括索引模块，其被配置为索引请求中的字和可用的应用描述以创建语义相似性映射。语义匹配器被配置为确定语义相似性映射在与域无关和域特定本体的概念/术语之间的语义相似性。预过滤模块被配置为基于语义相似性图和可用的描述来确定针对请求的候选组合。度量指导组合方法被配置为运行算法以通过确定哪些应用可以与使用语义相似性映射的哪个应用组合来生成一组替代组合。

6. 发明申请

US20060155394A1 Method and apparatus for order-preserving clustering of multi-dimensional data 审中-公开
标题翻译：用于订单保存多维数据聚类的方法和装置
公开(公告)号：US20060155394A1
公开(公告)日：2006-07-13
申请号：US11013483
申请日：2004-12-16
申请人： Tanveer Syeda-Mahmood
发明人： Tanveer Syeda-Mahmood
IPC分类号： G05B11/01
CPC分类号： G06K9/00496
摘要： A method of clustering ordered data sets, wherein the method comprises forming n-dimensional curvilinear representations from an ordered data set; formulating a n+1-dimensional curvilinear representation from a pair of ordered data sets; computing a similarity of the pair of ordered data sets using a similarity between the n-dimensional curvilinear representations and the n+1-dimensional curvilinear representation; and clustering ordered data sets based on the similarity between the n-dimensional curvilinear representations and the n+1-dimensional curvilinear representation. In the n-dimensional curvilinear representations, a first dimension of space corresponds with a common ordering dimension and the remaining dimension of space corresponds with the ordered data set. The process of computing the similarity comprises comparing a shape of the n+1-dimensional curvilinear representation to a shape of each component n-dimensional curvilinear representation. In the computing of the similarity, the shape of the n+1-dimensional curvilinear representation corresponds with inflection points on the n+1-dimensional curvilinear representation.
摘要翻译：一种聚类有序数据集的方法，其中所述方法包括从有序数据集合形成n维曲线表示; 从一对有序数据集中形成n + 1维曲线表示; 使用n维曲线表示和n + 1维曲线表示之间的相似度计算所述一对有序数据集的相似性; 并且基于n维曲线表示和n + 1维曲线表示之间的相似性来聚类有序数据集。在n维曲线表示中，空间的第一维对应于公共排序维度，空间的剩余维数与有序数据集相对应。计算相似度的过程包括将n + 1维曲线表示的形状与每个分量n维曲线表示的形状进行比较。在相似度的计算中，n + 1维曲线表示的形状对应于n + 1维曲线表示上的拐点。

7. 发明申请

US20050027460A1 Method, program product and apparatus for discovering functionally similar gene expression profiles 审中-公开
标题翻译：用于发现功能相似的基因表达谱的方法，程序产品和装置
公开(公告)号：US20050027460A1
公开(公告)日：2005-02-03
申请号：US10629448
申请日：2003-07-29
申请人： Bhooshan Kelkar , Tanveer Syeda-Mahmood , Gregor Meyer
发明人： Bhooshan Kelkar , Tanveer Syeda-Mahmood , Gregor Meyer
IPC分类号： G01N33/48 , G01N33/50 , G06F19/00
CPC分类号： G16B40/00 , G16B25/00
摘要： Genes to be compared are listed by their gene expression profiles and processed with a similar sequences algorithm that is a time and intensity invariant correlation function to obtain a data set of gene expression pairs and a match fraction for each pair. A threshold match fraction is chosen and a null set is created to hold indices of genes accounted for. Genes are then assigned to clusters by match fraction value if they have a match fraction greater than the threshold. Genes are then removed from clusters if they are represented in more than one cluster by removing a first gene from a cluster when another cluster has another gene with a higher match fraction with the first gene. When the difference between maximum match fraction values for pairs including a first gene in a first cluster and the first gene a second cluster is small, the first gene may be removed from the first cluster even when another gene in the first cluster has a higher match fraction with the first gene than the first gene has with a third gene in a second cluster. This occurs when the number of similar subsequences for the pair including the first gene in the first cluster is higher than the number of similar subsequences for the pair including the first gene in the second cluster.
摘要翻译：要比较的基因通过其基因表达谱列出并用类似的序列算法进行处理，该算法是时间和强度不变相关函数，以获得每对基因表达对的数据集和匹配分数。选择阈值匹配分数，创建一个空值集合来保存基因的索引。然后，如果基因具有大于阈值的匹配分数，则通过匹配分数值将基因分配给群集。然后如果基因在多于一个簇中表示，则当从另一个簇具有与第一个基因具有较高匹配分数的另一个基因时，从簇中去除第一个基因，然后将基因除去。当包括第一簇的第一个基因和第一个基因第二个簇的对的最大匹配分数值之间的差异小时，即使第一个簇中的另一个基因具有较高的匹配，第一个基因也可以从第一个簇中移除具有第一基因的第一个基因的分数与第二个簇中的第三个基因相同。当包括第一簇中的第一个基因的对的相似亚序列的数目高于包括第二个簇中的第一个基因的对的相似亚序列的数量时，就发生这种情况。

8. 发明申请

US20090175544A1 FINDING STRUCTURES IN MULTI-DIMENSIONAL SPACES USING IMAGE-GUIDED CLUSTERING 失效
标题翻译：使用图像聚类在多维空间中寻找结构
公开(公告)号：US20090175544A1
公开(公告)日：2009-07-09
申请号：US12143131
申请日：2008-06-20
申请人： Tanveer Syeda-Mahmood , Peter J. Haas , John M. Lake , Guy Lohman
发明人： Tanveer Syeda-Mahmood , Peter J. Haas , John M. Lake , Guy Lohman
IPC分类号： G06K9/62
CPC分类号： G06K9/6219 , Y10S707/99933 , Y10S707/99945
摘要： A data processing system is provided that comprises a processor, a random access memory for storing data and programs for execution by the processor, and computer readable instructions stored in the random access memory for execution by the processor to perform a method for clustering data points in a multidimensional dataset in a multidimensional image space. The method comprises generating a multidimensional image from the multidimensional dataset; generating a pyramid of multidimensional images having varying resolution levels by successively performing a pyramidal sub-sampling of the multidimensional image; identifying data clusters at each resolution level of the pyramid by applying a set of perceptual grouping constraints; and determining levels of a clustering hierarchy by identifying each salient bend in a variation curve of a magnitude of identified data clusters as a function of pyramid resolution level.
摘要翻译：提供了一种数据处理系统，其包括处理器，用于存储用于由处理器执行的数据和程序的随机存取存储器，以及存储在随机存取存储器中的计算机可读指令，用于由处理器执行以执行将数据点聚类的方法多维图像空间中的多维数据集。该方法包括从多维数据集生成多维图像; 通过连续执行所述多维图像的锥体子采样来生成具有不同分辨率水平的多维图像的金字塔; 通过应用一组感知分组约束来识别金字塔的每个分辨率级别的数据集群; 以及通过将所识别的数据簇的幅度的变化曲线中的每个显着弯曲值确定为金字塔分辨率级别的函数来确定聚类层级的水平。

9. 发明授权

US07542954B1 Data classification by kernel density shape interpolation of clusters 有权
标题翻译：通过核心密度形状插值进行数据分类
公开(公告)号：US07542954B1
公开(公告)日：2009-06-02
申请号：US12164532
申请日：2008-06-30
申请人： Tanveer Syeda-Mahmood , Peter J. Haas , John M. Lake , Guy M. Lohman
发明人： Tanveer Syeda-Mahmood , Peter J. Haas , John M. Lake , Guy M. Lohman
IPC分类号： G06F17/00 , G06F15/00 , G06F15/18 , G06N5/00
CPC分类号： G06K9/6273 , G06K9/6226 , G06N99/005
摘要： A method for representing a dataset comprises clustering the dataset using an unsupervised, non-parametric clustering method to generate a set of clusters each comprising a set of data points in an image; clustering the data points of each cluster using a supervised, partitional clustering method to partition each cluster into a specified number of sub-clusters; generating a density estimate value of each grid point of a set of grid points sampled from the image at a specified resolution for each sub-cluster using a kernel density function; identifying a maximum density estimate value and a sub-cluster associated with the maximum density estimate value for the grid point; adding each grid point for which the maximum density estimate value exceeds a specified threshold to the sub-cluster associated with the maximum density estimate value; and, for each cluster, merging the sub-clusters of the cluster into a corresponding cluster region in the image.
摘要翻译：一种用于表示数据集的方法包括使用无监督的非参数聚类方法对所述数据集进行聚类，以生成每组包括图像中的一组数据点的一组聚类; 使用受监督的分段聚类方法对每个集群的数据点进行聚类，以将每个集群分成指定数量的子集群; 使用核密度函数生成以每个子群体以指定分辨率从图像采样的一组网格点的每个网格点的密度估计值; 识别最大密度估计值和与所述网格点的最大密度估计值相关联的子簇; 将最大密度估计值超过特定阈值的每个网格点添加到与最大密度估计值相关联的子簇; 并且对于每个集群，将集群的子集合合并到图像中的相应集群区域中。

10. 发明授权

US07406200B1 Method and system for finding structures in multi-dimensional spaces using image-guided clustering 失效
标题翻译：使用图像引导聚类在多维空间中寻找结构的方法和系统
公开(公告)号：US07406200B1
公开(公告)日：2008-07-29
申请号：US11970946
申请日：2008-01-08
申请人： Tanveer Syeda-Mahmood , Peter J. Haas , John M. Lake , Guy M. Lohman
发明人： Tanveer Syeda-Mahmood , Peter J. Haas , John M. Lake , Guy M. Lohman
IPC分类号： G06K9/62 , G06F7/00 , G06F17/30 , G06F17/00
CPC分类号： G06K9/6219 , Y10S707/99933 , Y10S707/99945
摘要： A method is provided clustering data points in a multidimensional dataset in a multidimensional image space that comprises generating a multidimensional image from the multidimensional dataset; generating a pyramid of multidimensional images having varying resolution levels by successively performing a pyramidal sub-sampling of the multidimensional image; identifying data clusters at each resolution level of the pyramid by applying a set of perceptual grouping constraints; and determining levels of a clustering hierarchy by identifying each salient bend in a variation curve of a magnitude of identified data clusters as a function of pyramid resolution level.
摘要翻译：提供了一种在多维图像空间中的多维数据集中聚类数据点的方法，其包括从多维数据集生成多维图像; 通过连续执行所述多维图像的锥体子采样来生成具有不同分辨率水平的多维图像的金字塔; 通过应用一组感知分组约束来识别金字塔的每个分辨率级别的数据集群; 以及通过将所识别的数据簇的幅度的变化曲线中的每个显着弯曲值确定为金字塔分辨率级别的函数来确定聚类层级的水平。

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