专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

71. 发明授权

US07792348B2 Method and apparatus of using probabilistic atlas for cancer detection 有权
标题翻译：将概率图谱用于癌症检测的方法和装置
公开(公告)号：US07792348B2
公开(公告)日：2010-09-07
申请号：US11640947
申请日：2006-12-19
申请人： Daniel Russakoff
发明人： Daniel Russakoff
IPC分类号： G06K9/00
CPC分类号： G06K9/6209 , G06K2209/053
摘要： Methods and apparatuses detect features. The method according to one embodiment accesses digital image data representing an object; accesses reference data including a shape model relating to shape variation from a baseline object, and a probabilistic atlas comprising probability for a feature in the baseline object; performs shape registration for the object by representing a shape of the object using the shape model, to obtain a registered shape; and determines probability for the feature in the object by generating a correspondence between a geometric element associated with the probabilistic atlas and a geometric element associated with the registered shape.
摘要翻译：方法和设备检测特征。根据一个实施例的方法访问表示对象的数字图像数据; 访问包括与来自基线对象的形状变化相关的形状模型的参考数据和包括基线对象中的特征的概率的概率图集; 通过使用形状模型表示对象的形状来进行对象的形状注册，以获得注册的形状; 并且通过生成与概率图集相关联的几何元素与与注册形状相关联的几何元素之间的对应关系来确定对象中的特征的概率。

72. 发明申请

US20100185079A1 AUTOMATED METHODS AND SYSTEMS FOR VASCULAR PLAQUE DETECTION AND ANALYSIS 失效
标题翻译：自动化方法和系统用于血管解剖检测和分析
公开(公告)号：US20100185079A1
公开(公告)日：2010-07-22
申请号：US12541855
申请日：2009-08-14
申请人： Joel T. Huizenga , Russell W. Anderson , Thomas Woodley Botherton
发明人： Joel T. Huizenga , Russell W. Anderson , Thomas Woodley Botherton
IPC分类号： A61B5/055 , G06K9/00
CPC分类号： G06T7/0012 , A61B5/02007 , A61B5/055 , A61B5/7235 , A61B5/726 , A61B6/00 , C23F11/08 , G06K9/6212 , G06K2209/053 , G06T2207/10088 , G06T2207/30101 , G06T2210/41
摘要： Automated methods and systems for the detection and analysis of plaque in one or more regions of a patient's vasculature are described.
摘要翻译：描述了用于检测和分析患者脉管系统的一个或多个区域中的斑块的自动化方法和系统。

73. 发明申请

US20100166267A1 COMPUTER-AIDED DIAGNOSIS AND VISUALIZATION OF TOMOSYNTHESIS MAMMOGRAPHY DATA 有权
标题翻译：计算机辅助诊断和可视化TOMOSYNTHESIS MAMMOGRAPHY数据
公开(公告)号：US20100166267A1
公开(公告)日：2010-07-01
申请号：US12344451
申请日：2008-12-26
申请人： Heidi Zhang , Patrick Heffernan
发明人： Heidi Zhang , Patrick Heffernan
IPC分类号： G06K9/00 , A61B6/00
CPC分类号： A61B6/463 , A61B6/502 , A61B6/5235 , G06K2209/053 , G06T7/0012 , G06T2207/10081 , G06T2207/30068 , Y10S128/922
摘要： The present invention provides a method and system using computer-aided detection (CAD) algorithms to aid diagnosis and visualization of tomosynthesis mammography data. The proposed CAD algorithms process two-dimensional and three-dimensional tomosynthesis mammography images and identify regions of interest in breasts. The CAD algorithms include the steps of preprocessing; candidate detection of potential regions of interest; and classification of each region of interest to aid reading by radiologists. The detection of potential regions of interest utilizes two dimensional projection images for generating candidates. The resultant candidates in two dimensional images are back-projected into the three dimensional volume images. The feature extraction for classification operates in the three dimensional image in the neighborhood of the back-projected candidate location. The forward-projection and back-projection algorithms are used for visualization of the tomosynthesis mammography data in a fashion of synchronized MPR and VR.
摘要翻译：本发明提供了一种使用计算机辅助检测（CAD）算法来帮助诊断和可视化体层摄影乳腺X线照相术数据的方法和系统。提出的CAD算法处理二维和三维断层摄影乳腺X线照相图像并识别乳房感兴趣的区域。 CAD算法包括预处理步骤; 候选人检测潜在的感兴趣区域; 并分类每个感兴趣的区域以帮助放射科医师的阅读。感兴趣的潜在区域的检测利用二维投影图像来产生候选。将二维图像中的合成候选物反投影到三维体积图像中。用于分类的特征提取在背投影候选位置附近的三维图像中操作。前投影和后投影算法用于以同步的MPR和VR的方式可视化断层摄影乳房X线照相术数据。

74. 发明申请

US20100086188A1 Breast Tomosynthesis With Display Of Highlighted Suspected Calcifications 有权
标题翻译：乳腺组织合成显示突出怀疑钙化
公开(公告)号：US20100086188A1
公开(公告)日：2010-04-08
申请号：US12605031
申请日：2009-10-23
申请人： Chris Ruth , Jay Stein , Loren Niklason , Andrew Smith
发明人： Chris Ruth , Jay Stein , Loren Niklason , Andrew Smith
IPC分类号： G06K9/00
CPC分类号： G06T7/0012 , A61B6/025 , A61B6/12 , A61B6/461 , A61B6/502 , A61B6/5211 , A61B6/5223 , A61B6/5252 , G06K9/4638 , G06K2209/053 , G06T2207/10081 , G06T2207/30068
摘要： Systems and methods that facilitate the presentation and assessment of selected features in projection and/or reconstructed breast images, such as calcifications that meet selected criteria of size, shape, presence in selected slice images, distribution of pixels that could be indicative of calcification relative to other pixels or of other image features of clinical interest.
摘要翻译：促进投影和/或重建的乳房图像中所选特征的呈现和评估的系统和方法，例如满足所选尺寸，形状，选定切片图像中存在的钙化的钙化，可以指示钙化的像素分布相对于其他像素或其他具有临床兴趣的图像特征。

75. 发明申请

US20100067754A1 COMPUTER-AIDED DETECTION AND CLASSIFICATION OF SUSPICIOUS MASSES IN BREAST IMAGERY 有权
标题翻译：乳腺成像中计算机辅助检测和分类的可疑质量
公开(公告)号：US20100067754A1
公开(公告)日：2010-03-18
申请号：US12211593
申请日：2008-09-16
申请人： Michael J. Collins , Kevin Woods , Brent Woods , William Pierson , Ryan McGinnis
发明人： Michael J. Collins , Kevin Woods , Brent Woods , William Pierson , Ryan McGinnis
IPC分类号： G06K9/00 , G06K9/62
CPC分类号： G06K9/6292 , G06K2209/053 , G06T7/0012 , G06T2207/30068
摘要： Methods, a system, and a computer readable medium are presented that detect and classify mass-like regions exhibiting spiculated and/or dense characteristics with high sensitivity and at acceptable false positive rates. One or more suspicious masses are identified in medical imagery of the breast. In accordance with certain embodiments, for each suspicious mass located, a quantitative measure of spiculation and quantitative measure of density are computed. At least one classification scheme is then selected for each suspicious mass according to both quantitative measures. Each classification scheme is developed using true positives and false positives with similar quantitative measures.In accordance with certain other embodiments, for each suspicious mass located, a measure of breast location is computed. At least one classification scheme is then selected for each suspicious mass according to the measure of breast location. Each classification scheme is developed using true positives and false positives that appear in the same breast location. In one embodiment, the location measure determines whether a suspicious mass appears inside or outside of the parenchyma region of the breast.
摘要翻译：提出了方法，系统和计算机可读介质，其以高灵敏度和可接受的假阳性率检测和分类显示具有螺旋和/或密度特征的质量样区域。在乳房的医学图像中识别出一个或多个可疑群体。根据某些实施例，对于每个可疑的质量位置，计算密度的定量测量和密度的定量测量。然后根据这两种量化措施，为每个可疑物质选择至少一种分类方案。每个分类方案是使用具有相似量化措施的真阳性和假阳性来开发的。根据某些其他实施例，对于位于每个可疑质量块，计算乳房位置的量度。然后根据乳房位置的测量，为每个可疑质量选择至少一个分类方案。每个分类方案使用出现在同一乳房位置的真阳性和假阳性进行开发。在一个实施例中，位置测量确定可疑质量是否出现在乳房的实质区域的内部或外部。

76. 发明申请

US20100036782A1 METHODS FOR FEATURE SELECTION USING CLASSIFIER ENSEMBLE BASED GENETIC ALGORITHMS 有权
标题翻译：使用基于分类器ENSEMBLE的遗传算法进行特征选择的方法
公开(公告)号：US20100036782A1
公开(公告)日：2010-02-11
申请号：US12441956
申请日：2007-09-17
申请人： Luyin Zhao , Lilla Boroczky , Lalitha A. Agnihotri , Michael C.C. Lee
发明人： Luyin Zhao , Lilla Boroczky , Lalitha A. Agnihotri , Michael C.C. Lee
IPC分类号： G06N3/12 , G06F19/00 , G06K9/00
CPC分类号： G06N3/126 , G06F19/00 , G06K9/6217 , G06K2209/053 , G16H50/20 , G16H50/30
摘要： Methods for performing genetic algorithm-based feature selection are provided herein. In certain embodiments, the methods include steps of applying multiple data splitting patterns to a learning data set to build multiple classifiers to obtain at least one classification result; integrating the at least one classification result from the multiple classifiers to obtain an integrated accuracy result; and outputting the integrated accuracy result to a genetic algorithm as a fitness value for a candidate feature subset, in which genetic algorithm-based feature selection is performed.
摘要翻译：本文提供了基于遗传算法的特征选择的方法。在某些实施例中，所述方法包括将多个数据分割模式应用于学习数据集以构建多个分类器以获得至少一个分类结果的步骤; 整合来自多个分类器的至少一个分类结果以获得综合精度结果; 并将所述综合精度结果输出到遗传算法作为候选特征子集的适应度值，其中执行基于遗传算法的特征选择。

77. 发明授权

US07630533B2 Breast tomosynthesis with display of highlighted suspected calcifications 有权
标题翻译：乳房断层合成与突出疑似钙化显示
公开(公告)号：US07630533B2
公开(公告)日：2009-12-08
申请号：US11903021
申请日：2007-09-20
申请人： Chris Ruth , Jay Stein , Loren Niklason , Andrew Smith
发明人： Chris Ruth , Jay Stein , Loren Niklason , Andrew Smith
IPC分类号： G06K9/00
CPC分类号： G06T7/0012 , A61B6/025 , A61B6/12 , A61B6/461 , A61B6/502 , A61B6/5211 , A61B6/5223 , A61B6/5252 , G06K9/4638 , G06K2209/053 , G06T2207/10081 , G06T2207/30068
摘要： Systems and methods that facilitate the presentation and assessment of selected features in projection and/or reconstructed breast images, such as calcifications that meet selected criteria of size, shape, presence in selected slice images, distribution of pixels that could be indicative of calcification relative to other pixels or of other image features of clinical interest.
摘要翻译：促进投影和/或重建的乳房图像中所选特征的呈现和评估的系统和方法，例如满足所选尺寸，形状，选定切片图像中存在的钙化的钙化，可以指示钙化的像素分布相对于其他像素或其他具有临床兴趣的图像特征。

78. 发明申请

US20090238426A1 System and Methods for Identifying an Object within a Complex Environment 审中-公开
标题翻译：在复杂环境中识别对象的系统和方法
公开(公告)号：US20090238426A1
公开(公告)日：2009-09-24
申请号：US12407671
申请日：2009-03-19
申请人： Elise Fear , Douglas Kurrant , David Westwick
发明人： Elise Fear , Douglas Kurrant , David Westwick
IPC分类号： G06K9/00 , G06K9/46
CPC分类号： G06K9/6226 , G06K9/3216 , G06K2209/053
摘要： A signal processing technique includes extracting object features, an object response classification, and a reconstruction of the object estimate. In selected embodiments, an optional step that improves the estimate of the object response is included in the signal processing technique. In one implementation of the signal processing technique, reflections from the surrounding environment are removed from the response of a target object to permit the identification, localization, and imaging of the target. In select implementations, the technique can be used to image tumors located within breast tissue.
摘要翻译：信号处理技术包括提取对象特征，对象响应分类和对象估计的重构。在选择的实施例中，改进对象响应的估计的可选步骤包括在信号处理技术中。在信号处理技术的一个实现中，来自周围环境的反射从目标对象的响应中去除，以允许目标的识别，定位和成像。在选择的实施方案中，该技术可用于成像位于乳腺组织内的肿瘤。

79. 发明申请

US20080170767A1 METHOD AND SYSTEM FOR GLEASON SCALE PATTERN RECOGNITION 审中-公开
标题翻译：格莱斯模式识别的方法和系统
公开(公告)号：US20080170767A1
公开(公告)日：2008-07-17
申请号：US11967644
申请日：2007-12-31
申请人： Spyros A. Yfantis
发明人： Spyros A. Yfantis
IPC分类号： G06K9/00
CPC分类号： G06K9/522 , G06K2209/053
摘要： A gradient is calculated for a pixel image representing a cancer area, the gradient having magnitude and direction. Local extrema of the gradients are identified, remaining pixels are zeroed. Significant gradients among the local extrema are identified, based on thresholds obtained through training. Probability distributions are calculated for the local extrema magnitudes and the significant gradient magnitudes, to form a feature vector. The feature vector is classified using a Maximum Likelihood Estimate classifier constructed from large training sets.
摘要翻译：计算表示癌症区域的像素图像的梯度，梯度具有大小和方向。识别梯度的局部极值，剩余像素为零。根据通过培训获得的阈值，确定局部极值中的显着梯度。计算局部极值和显着梯度大小的概率分布，形成特征向量。特征向量使用由大训练集构建的最大似然估计分类器进行分类。

80. 发明申请

US20080144940A1 Method and apparatus of using probabilistic atlas for feature removal/positioning 失效
标题翻译：使用概率图谱进行特征去除/定位的方法和装置
公开(公告)号：US20080144940A1
公开(公告)日：2008-06-19
申请号：US11640960
申请日：2006-12-19
申请人： Daniel Russakoff
发明人： Daniel Russakoff
IPC分类号： G06K9/46
CPC分类号： G06K9/6209 , G06K2209/053
摘要： Methods and apparatuses process images. The method according to one embodiment accesses digital image data representing an image including an object; accesses reference data including a shape model relating to shape variation of objects from a baseline object, the objects and the baseline object being from a class of the object; and removes from the image an element not related to the object, by representing a shape of the object using the shape model.
摘要翻译：方法和设备处理图像。根据一个实施例的方法访问表示包括对象的图像的数字图像数据; 访问包括与来自基线对象的对象的形状变化相关的形状模型的参考数据，对象和基线对象来自对象的类; 并通过使用形状模型表示对象的形状，从图像中除去与对象无关的元素。

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