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

WO2007092518A3 SYSTEM AND METHOD FOR MULTIPLE INSTANCE LEARNING FOR COMPUTER AIDED DETECTION 审中-公开
标题翻译：用于计算机辅助检测的多个实例学习的系统和方法
公开(公告)号：WO2007092518A3
公开(公告)日：2008-06-05
申请号：PCT/US2007003296
申请日：2007-02-07
申请人： SIEMENS MEDICAL SOLUTIONS , RAO BHARAT R , DUNDAR MURAT , KRISHNAPURAM BALAJI , FUNG GLENN
发明人： RAO BHARAT R , DUNDAR MURAT , KRISHNAPURAM BALAJI , FUNG GLENN
IPC分类号： G06K9/62
CPC分类号： G06K9/6277 , G06T7/0012 , G06T2207/30004
摘要： A method of training a classifier for computer aided detection of digitized medical images, includes providing a plurality of bags, each bag containinga plurality of feature samples of a single region-of-interest in a medical image, wherein said features include texture, shape, intensity, and contrast of said region-of-interest, wherein each region-of-interest has been labeled as either malignant (11) or healthy (13), and training a classifier on said plurality of bags of feature samples, subject to the constraint that at least one point (12) in a convex hull (14) of each bag, corresponding to a feature sample, is correctly classified according to the labeled of the associated region-of-interest.
摘要翻译：一种对数字化医学图像进行计算机辅助检测的分类器进行训练的方法，包括：提供多个袋，每个袋在医学图像中包含单个感兴趣区域的多个特征样本，其中所述特征包括纹理，形状，所述感兴趣区域的强度和对比度，其中每个兴趣区域已被标记为恶性（11）或健康（13），并且在所述多个特征样本袋上训练分类器，约束，每个袋的凸包（14）中的对应于特征样本的至少一个点（12）根据相关联的感兴趣区域的标记被正确地分类。

2. 发明申请

WO2008137089A2 GENE SIGNATURE OF EARLY HYPOXIA TO PREDICT PATIENT SURVIVAL 审中-公开
标题翻译：早期HYPOXIA的基因表达预测患者生存
公开(公告)号：WO2008137089A2
公开(公告)日：2008-11-13
申请号：PCT/US2008005704
申请日：2008-05-02
申请人： SIEMENS MEDICAL SOLUTIONS , SEIGNEURIC RENAUD G , STARMANS MAUD H W , FUNG GLENN , KRISHNAPURAM BALAJI , NUYTEN DIMITRY S A , VAN ERK ARIE , MAGAGNIN MICHAEL GASTON , ROUSCHOP KASPER M , KRISHNAN SRIRAM , RAO R BHARAT , EVELO CHRISTOFFEL THEODORUS ANTHONIUS , BEGG ADRIAN CAMPBELL , WOUTERS BRADLY G , LAMBIN PHILIPPE
发明人： SEIGNEURIC RENAUD G , STARMANS MAUD H W , FUNG GLENN , KRISHNAPURAM BALAJI , NUYTEN DIMITRY S A , VAN ERK ARIE , MAGAGNIN MICHAEL GASTON , ROUSCHOP KASPER M , KRISHNAN SRIRAM , RAO R BHARAT , EVELO CHRISTOFFEL THEODORUS ANTHONIUS , BEGG ADRIAN CAMPBELL , WOUTERS BRADLY G , LAMBIN PHILIPPE
IPC分类号： C12Q1/68
CPC分类号： C12Q1/6886 , C12Q2600/106 , C12Q2600/118
摘要： The present invention provides methods and compositions for predicting patient responses to cancer treatment using hypoxia gene signatures. These methods can comprise measuring in a biological sample from a patient the levels of gene expression of a group of the genes designated herein. The present invention also provides for microarrays that can detect expression from a group of genes.
摘要翻译：本发明提供了使用缺氧基因特征预测患者对癌症治疗的反应的方法和组合物。这些方法可以包括在来自患者的生物样品中测量本文指定的一组基因的基因表达水平。本发明还提供了可以检测一组基因的表达的微阵列。

3. 发明申请

WO2006083569A9 CHARACTERIZATION OF CARDIAC MOTION WITH SPATIAL RELATIONSHIP 审中-公开
标题翻译：具有空间关系的心脏运动特征
公开(公告)号：WO2006083569A9
公开(公告)日：2006-10-19
申请号：PCT/US2006001931
申请日：2006-01-18
申请人： SIEMENS MEDICAL SOLUTIONS , QAZI MALEEHA , KAMASAK MUSTAFA , DUNDAR MURAT , FUNG GLENN , KRISHNAN SRIRAM , RAO R BHARAT
发明人： QAZI MALEEHA , KAMASAK MUSTAFA , DUNDAR MURAT , FUNG GLENN , KRISHNAN SRIRAM , RAO R BHARAT
IPC分类号： A61B5/00
CPC分类号： G06T7/0012 , A61B5/00 , A61B5/055 , A61B5/7267 , A61B6/03 , A61B6/5217 , A61B8/08 , G06F19/321 , G06K9/00335 , G06K2209/051 , G06T7/20 , G06T2207/30048 , G16H50/20 , G16H50/50
摘要： Cardiac motion is automatically characterized (28) based on spatial relationship to health. A classifier is trained for the characterization of cardiac motion. Regional wall motion abnormality assessment (28) may be improved by combining information from neighboring segments (S). The structure or relationship between different segments (S) and associated probabilities of different spatial locations being abnormal given another segment (S) being abnormal are used for classification.
摘要翻译：心脏运动根据与健康的空间关系自动表征（28）。训练分类器以表征心脏运动。区域性室壁运动异常评估（28）可通过结合来自邻近区段（S）的信息来改善。使用另一个片段（S）异常的不同片段（S）之间的结构或关系以及不同空间位置的相关概率被异常用于分类。

4. 发明申请

WO2007130542A3 CLASSIFICATION OF CANDIDATES USING THEIR CORRELATION INFORMATION IN COMPUTER AIDED DIAGNOSIS 审中-公开
标题翻译：使用计算机辅助诊断中的相关信息对候选人进行分类
公开(公告)号：WO2007130542A3
公开(公告)日：2008-10-09
申请号：PCT/US2007010778
申请日：2007-05-03
申请人： SIEMENS MEDICAL SOLUTIONS , FUNG GLENN , KRISHNAPURAM BALAJI , VURAL VOLKAN , RAO R BHARAT
发明人： FUNG GLENN , KRISHNAPURAM BALAJI , VURAL VOLKAN , RAO R BHARAT
IPC分类号： G06T7/00
CPC分类号： G06T7/0012 , G06K9/6269 , G06K9/6278
摘要： A method and system correlate candidate information and provide batch classification of a number of related candidates. The batch of candidates may be identified from a single data set. There may be internal correlations and/or differences among the candidates. The candidates may be classified taking into consideration the internal correlations and/or differences. The locations (104) and descriptive features (106) of a batch of candidates may be determined. In turn, the locations and/or descriptive features determined may be used to enhance the accuracy of the classification of some or all of the candidates within the batch (108). In one embodiment, the single data set analyzed is associated with an internal image of patient (102) and the distance between candidates is accounted for. Two different algorithms may each simultaneously classify all of the samples within a batch, one being based upon probabilistic analysis and the other upon a mathematical programming approach. Alternate algorithms may be used.
摘要翻译：一种方法和系统将候选信息相关联并提供多个相关候选者的批次分类。可以从单个数据集中识别该批候选。候选人之间可能存在内部相关性和/或差异。候选人可以考虑内部相关性和/或差异进行分类。可以确定一批候选的位置（104）和描述特征（106）。反过来，可以使用所确定的位置和/或描述性特征来提高批次（108）内部分或全部候选者的分类的准确性。在一个实施例中，所分析的单个数据集与患者（102）的内部图像相关联，并且考虑候选者之间的距离。两种不同的算法可以各自同时对批次中的所有样本进行分类，一种基于概率分析，另一种基于数学规划方法。可以使用替代算法。

5. 发明申请

WO2005078638A3 A SYSTEM AND METHOD FOR A SPARSE KERNEL EXPANSION FOR A BAYES CLASSIFIER 审中-公开
标题翻译：一种用于贝叶类分类器的小型扩展的系统和方法
公开(公告)号：WO2005078638A3
公开(公告)日：2005-10-06
申请号：PCT/US2005003806
申请日：2005-02-04
申请人： SIEMENS MEDICAL SOLUTIONS , DUNDAR MURAT , FUNG GLENN , BI JINBO , RAO R BHARAT
发明人： DUNDAR MURAT , FUNG GLENN , BI JINBO , RAO R BHARAT
IPC分类号： G06K9/62
CPC分类号： G06K9/6256
摘要： A method and device having instructions for analyzing input data-space by learning classifiers include choosing a candidate subset from a predetermined training data-set that is used to analyze the input data-space. Candidates are temporarily added from the candidate subset to an expansion set to generate a new kernel space for the input data-space by predetermined repeated evaluations of leave-one-out errors for the candidates added to the expansion set. This is followed by removing the candidates temporarily added to the expansion set after the leave-one-out error evaluations are performed, and selecting the candidates to be permanently added to the expansion set based on the leave-one-out errors of the candidates temporarily added to the expansion set to determine the one or more classifiers
摘要翻译：具有用于通过学习分类器分析输入数据空间的指令的方法和设备包括从用于分析输入数据空间的预定训练数据集中选择候选子集。将候选者从候选子集临时添加到扩展集合，以通过对添加到扩展集合的候选者的一对一错误进行预先重复的评估来为输入数据空间生成新的内核空间。之后，在执行一次性错误评估之后，删除临时添加到扩展集的候选者，并且基于临时的候选者的一次性错误选择要永久添加到扩展集的候选项添加到扩展集以确定一个或多个分类器

6. 发明申请

WO2009091595A3 SYSTEM AND METHOD FOR PRIVACY PRESERVING PREDICTIVE MODELS FOR LUNG CANCER SURVIVAL ANALYSIS 审中-公开
标题翻译：用于肺癌预防分析的预防性预防模型的隐私保护系统和方法
公开(公告)号：WO2009091595A3
公开(公告)日：2009-11-12
申请号：PCT/US2009000313
申请日：2009-01-16
申请人： SIEMENS MEDICAL SOLUTIONS , MAASTRO CLINIC , FUNG GLENN , RAO R BHARAT , KRISHNAN SRIRAM , YU SHIPENG , DEHING-OBERIJE CARY , LAMBIN PHILLIPPE , DE RUYSSCHER DIRK
发明人： FUNG GLENN , RAO R BHARAT , KRISHNAN SRIRAM , YU SHIPENG , DEHING-OBERIJE CARY , LAMBIN PHILLIPPE , DE RUYSSCHER DIRK
IPC分类号： G06K9/62 , G06F21/00
CPC分类号： G06K9/62 , G06F21/6254 , G06K9/6215 , G06K9/6232 , G06K9/6269 , G16H50/20 , G16H50/70
摘要： A computer-implemented method for privacy-preserving data mining to determine cancer survival rates includes providing (21) a random matrix B agreed to by a plurality of entities, wherein each entity i possesses a data matrix A i of cancer survival data that is not publicly available, providing (22) a class matrix D i for each of the data matrices A i , providing (23) a kernel K(A i , B) by each of said plurality of entities to allow public computation of a full kernel, and computing a(24) binary classifier that incorporates said public full kernel, wherein said classifier is adapted to classify (25) a new data vector according to a sign of said classifier.
摘要翻译：用于隐私保护数据挖掘以确定癌症存活率的计算机实现方法包括提供（21）由多个实体同意的随机矩阵B，其中每个实体i拥有不是的癌症存活数据的数据矩阵A i 为每个数据矩阵A i提供（22）类矩阵D i，提供（23）由所述多个实体中的每一个实体的核K（A i，B），以允许公共计算完整内核，以及计算包含所述公共完整内核的（24）二进制分类器，其中所述分类器适于根据所述分类器的符号对（25）新的数据向量进行分类。

7. 发明申请

WO2008150514A2 SYSTEM AND METHOD FOR MEDICAL PREDICTIVE MODELS USING LIKELIHOOD GAMBLE PRICING 审中-公开
标题翻译：使用LIKELIHOOD GAMBLE PRICING的医学预测模型的系统和方法
公开(公告)号：WO2008150514A2
公开(公告)日：2008-12-11
申请号：PCT/US2008006970
申请日：2008-06-03
申请人： SIEMENS MEDICAL SOLUTIONS , FUNG GLENN , GIANG PHAN HONG , STECK HARALD , RAO R BHARAT
发明人： FUNG GLENN , GIANG PHAN HONG , STECK HARALD , RAO R BHARAT
IPC分类号： G06F19/00
CPC分类号： G06K9/6278 , G16H50/20
摘要： A method for predicting survival rates of medical patients includes providing a set D of survival data for a plurality of medical patients, providing a regression model having an associated parameter vector ß, providing an example x? of a medical patient whose survival probability is to be classified, calculating (71) a parameter vector (i) that maximizes a log-likelihood function of ß over the set of survival data, (ii), wherein the log likelihood (ii) is a strictly concave function of ß and is a function of the scalar xß, calculating a weight (72) w? for example x?, calculating (73) an updated parameter vector ß* that maximizes a function (iii), wherein data points (y?, x?, w?) augment set D, calculating (74) a fair log likelihood ratio ?f from (i) and ß* using (iv), and mapping (75) the fair log likelihood ratio ?f to a fair price yf ?,
摘要翻译：一种用于预测医疗患者的存活率的方法包括提供多个医疗患者的生存数据的集合D，提供具有相关参数向量ß的回归模型，提供示例x？计算（71）在生存数据集上最大化ß的对数似然函数的参数向量（i），（ii）其中对数似然度（ii）为 ß的严格凹函数是标量x的函数，计算权重（72）w？例如x 1，计算（73）最大化函数（iii）的更新参数向量∈*，其中数据点（y 1，x 2，w 3）增加集合D，计算（74）公平对数似然比 f（i）和ß*使用（iv），并将公平对数似然比Δf映射（75）为公平价格yf？

8. 发明申请

WO2005001740A3 SYSTEMS AND METHODS FOR AUTOMATED DIAGNOSIS AND DECISION SUPPORT FOR BREAST IMAGING 审中-公开
标题翻译：用于乳腺成像的自动诊断和决策支持的系统和方法
公开(公告)号：WO2005001740A3
公开(公告)日：2005-06-09
申请号：PCT/US2004020228
申请日：2004-06-25
申请人： SIEMENS MEDICAL SOLUTIONS
发明人： KRISHNAN SRIRAM , RAO R BHARAT , DUNDAR MURAT , FUNG GLENN
IPC分类号： A61B8/00 , G06F19/00 , G06T7/00
CPC分类号： G06T7/0012 , G06F19/321 , G06T2207/10088 , G06T2207/10116 , G06T2207/20084 , G06T2207/30068 , G16H40/63 , G16H50/20 , Y10S128/92 , Y10S128/922 , Y10S128/923 , Y10S128/924
摘要： CAD (computer-aided diagnosis) systems and applications for breast imaging are provided, which implement methods to automatically extract and analyze features from a collection of patient information (including image data and/or non-image data) of a subject patient, to provide decision support for various aspects of physician workflow including, for example, automated diagnosis of breast cancer other automated decision support functions that enable decision support for, e.g., screening and staging for breast cancer. The CAD systems implement machine-learning techniques that use a set of training data obtained (learned) from a database of labeled patient cases in one or more relevant clinical domains and/or expert interpretations of such data to enable the CAD systems to "learn" to analyze patient data and make proper diagnostic assessments and decisions for assisting physician workflow.
摘要翻译：提供了用于乳房成像的CAD（计算机辅助诊断）系统和应用，其实现了从主体患者的患者信息（包括图像数据和/或非图像数据）的集合中自动提取和分析特征的方法，以提供对医师工作流程的各个方面的决策支持，包括例如对乳腺癌的自动诊断，其他自动化决策支持功能，其支持例如乳腺癌筛查和分期的决策支持。 CAD系统实现机器学习技术，该技术使用从一个或多个相关临床领域中标记的病例数据库获得（学习）的一组训练数据和/或对这些数据的专家解释，以使得CAD系统能够“学习” 分析患者数据并做出适当的诊断评估和辅助医生工作流程的决定。

9. 发明申请

WO2005017815A3 INCORPORATING SPATIAL KNOWLEDGE FOR CLASSIFICATION 审中-公开
标题翻译：纳入分类空间知识
公开(公告)号：WO2005017815A3
公开(公告)日：2005-04-07
申请号：PCT/US2004026425
申请日：2004-08-13
申请人： SIEMENS MEDICAL SOLUTIONS
发明人： KRISHNAN ARUN , FUNG GLENN , STOECKEL JONATHAN
IPC分类号： G06F19/00 , G06K9/00 , G06K9/62 , G06K9/68 , G06T7/00
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：我们建议基于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，几个分类器可以比涵盖整个特征空间的“通用”分类器更好地学习局部概念。使用本地分类器确保特定类的对象在该特定类中具有更高程度的相似度。使用本地分类器也会导致内存，存储和性能改进，特别是当分类器是基于内核的时候。如本文所使用的，术语“基于内核的分类器”是指其中已经使用映射函数（即，内核）将原始训练数据映射到更高维度空间的分类器，其中分类任务可能更容易。

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