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

US20050049985A1 Input feature and kernel selection for support vector machine classification 有权
标题翻译：输入特征和内核选择，用于支持向量机分类
公开(公告)号：US20050049985A1
公开(公告)日：2005-03-03
申请号：US10650121
申请日：2003-08-28
申请人： Olvi Mangasarian , Glenn Fung
发明人： Olvi Mangasarian , Glenn Fung
IPC分类号： G06F17/00 , G06K9/62 , G06N5/00
CPC分类号： G06K9/6228 , G06K9/6269
摘要： A feature selection technique for support vector machine (SVM) classification makes use of fast Newton method that suppresses input space features for a linear programming formulation of a linear SVM classifier, or suppresses kernel functions for a linear programming formulation of a nonlinear SVM classifier. The techniques may be implemented with a linear equation solver, without the need for specialized linear programming packages. The feature selection technique may be applicable to linear or nonlinear SVM classifiers. The technique may involve defining a linear programming formulation of a SVM classifier, solving an exterior penalty function of a dual of the linear programming formulation to produce a solution to the SVM classifier using a Newton method, and selecting an input set for the SVM classifier based on the solution.
摘要翻译：用于支持向量机（SVM）分类的特征选择技术使用快速牛顿法来抑制线性SVM分类器的线性规划公式的输入空间特征，或者抑制非线性SVM分类器的线性规划公式的核函数。这些技术可以用线性方程求解器来实现，而不需要专门的线性规划包。特征选择技术可以适用于线性或非线性SVM分类器。该技术可以包括定义SVM分类器的线性规划公式，求解线性规划公式的双重的外部惩罚函数，以使用牛顿法产生对SVM分类器的解，并且基于SVM分类器选择输入集合在解决方案。

2. 发明授权

US08055593B2 Learning classifiers for multiple-label data analysis 有权
标题翻译：用于多标签数据分析的学习分类器
公开(公告)号：US08055593B2
公开(公告)日：2011-11-08
申请号：US11877066
申请日：2007-10-23
申请人： Romer E. Rosales , Glenn Fung , Mark Schmidt , Sriram Krishnan , R. Bharat Rao
发明人： Romer E. Rosales , Glenn Fung , Mark Schmidt , Sriram Krishnan , R. Bharat Rao
IPC分类号： G06F15/18
CPC分类号： G06K9/6226 , G06K9/6256 , G06N99/005 , G16H50/20
摘要： A method for multiple-label data analysis includes: obtaining labeled data points from more than one labeler; building a classifier that maximizes a measure relating the data points, labels on the data points and a predicted output label; and assigning an output label to an input data point by using the classifier.
摘要翻译：一种用于多标签数据分析的方法包括：从多于一个的贴标机获取标记的数据点; 建立一个分类器，最大化与数据点，数据点上的标签和预测输出标签相关的度量; 并通过使用分类器将输出标签分配给输入数据点。

3. 发明授权

US07986827B2 System and method for multiple instance learning for computer aided detection 有权
标题翻译：用于计算机辅助检测的多实例学习的系统和方法
公开(公告)号：US07986827B2
公开(公告)日：2011-07-26
申请号：US11671777
申请日：2007-02-06
申请人： R. Bharat Rao , Murat Dundar , Balaji Krishnapuram , Glenn Fung
发明人： R. Bharat Rao , Murat Dundar , Balaji Krishnapuram , Glenn Fung
IPC分类号： G06K9/62 , G06K9/00 , G06E1/00
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 image, includes providing a plurality of bags, each bag containing a plurality of feature samples of a single region-of-interest in a medical image, where each region-of-interest has been labeled as either malignant or healthy. The training uses candidates that are spatially adjacent to each other, modeled by a “bag”, rather than each candidate by itself. A classifier is trained on the plurality of bags of feature samples, subject to the constraint that at least one point in a convex hull of each bag, corresponding to a feature sample, is correctly classified according to the label of the associated region-of-interest, rather than a large set of discrete constraints where at least one instance in each bag has to be correctly classified.
摘要翻译：训练用于数字化医学图像的计算机辅助检测的分类器的方法包括提供多个袋，每个袋包含在医学图像中的单个感兴趣区域的多个特征样本，其中每个感兴趣的区域已被标记为恶性或健康。培训使用空间上相邻的候选人，由“包”建模，而不是每个候选人本身。在多个特征样本袋上训练分类器，受限于根据相关区域的标签对每个袋子的凸包中的至少一个点（对应于特征样本）进行正确分类，而不是大量离散约束，每个行李中的至少一个实例必须被正确分类。

4. 发明授权

US07912278B2 Using candidates correlation information during computer aided diagnosis 有权
标题翻译：在计算机辅助诊断期间使用候选相关信息
公开(公告)号：US07912278B2
公开(公告)日：2011-03-22
申请号：US11742781
申请日：2007-05-01
申请人： Glenn Fung , Balaji Krishnapuram , Volkan Vural , R. Bharat Rao
发明人： Glenn Fung , Balaji Krishnapuram , Volkan Vural , R. Bharat Rao
IPC分类号： G06K9/46 , G06K9/62
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 and descriptive features of a batch of candidates may be determined. In turn, the locations and/or descriptive features determined may used to enhance the accuracy of the classification of some or all of the candidates within the batch. In one embodiment, the single data set analyzed is associated with an internal image of patient 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一些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。可以确定一批候选人的位置和描述性特征。反过来，所确定的位置和/或描述性特征可以用于提高批次内的一些或所有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. 发明授权

US07634120B2 Incorporating spatial knowledge for classification 有权
标题翻译：结合空间知识进行分类
公开(公告)号：US07634120B2
公开(公告)日：2009-12-15
申请号：US10915076
申请日：2004-08-10
申请人： Arun Krishnan , Glenn Fung , Jonathan Stoeckel
发明人： Arun Krishnan , Glenn Fung , Jonathan Stoeckel
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，其中分类任务可以更容易。

6. 发明申请

US20090006055A1 Automated Reduction of Biomarkers 审中-公开
标题翻译：自动降低生物标志物
公开(公告)号：US20090006055A1
公开(公告)日：2009-01-01
申请号：US12135313
申请日：2008-06-09
申请人： Glenn Fung , Renaud G. Seigneuric , Sriram Krishnan , R. Bharat Rao , Philippe Lambin
发明人： Glenn Fung , Renaud G. Seigneuric , Sriram Krishnan , R. Bharat Rao , Philippe Lambin
IPC分类号： G06G7/60
CPC分类号： G16B25/00 , G16B40/00
摘要： A list of biomarkers indicative of patient outcome is reduced. A computer program is applied to a set of biomarkers indicative of a patient outcome (e.g., prognosis, diagnosis, or treatment result). The computer program models the set of biomarkers with a subset of the biomarkers. The subset is identified without labeling based on the patient outcome. Instead, biomarker scores (e.g., sequence score) are used to identify the subset of biomarkers.
摘要翻译：减少了指示患者结果的生物标志物的列表。将计算机程序应用于指示患者结果的一组生物标志物（例如，预后，诊断或治疗结果）。计算机程序用生物标志物的一个子集建模该组生物标志物。基于患者结果，该子集被识别而没有标记。相反，生物标志物评分（例如，序列评分）用于鉴定生物标志物的子集。

7. 发明申请

US20050105794A1 Greedy support vector machine classification for feature selection applied to the nodule detection problem 审中-公开
标题翻译：贪心支持向量机分类功能选择应用于结节检测问题
公开(公告)号：US20050105794A1
公开(公告)日：2005-05-19
申请号：US10924136
申请日：2004-08-23
申请人： Glenn Fung
发明人： Glenn Fung
IPC分类号： G06K9/62 , G06K9/00
CPC分类号： G06K9/6269 , G06K9/6228
摘要： An incremental greedy method to feature selection is described. This method results in a final classifier that performs optimally and depends on only a few features. Generally, a small number of features is desired because it is often the case that the complexity of a classification method depends on the number of features. It is very well known that a large number of features may lead to overfitting on the training set, which then leads to a poor generalization performance in new and unseen data. The incremental greedy method is based on feature selection of a limited subset of features from the feature space. By providing low feature dependency, the incremental greedy method 100 requires fewer computations as compared to a feature extraction approach, such as principal component analysis.
摘要翻译：描述了增量贪婪方法来进行特征选择。这种方法导致一个最终的分类器，其执行最佳并仅依赖于几个特征。通常，需要少量特征，因为分类方法的复杂性常常取决于特征的数量。众所周知，大量的特征可能导致训练集上的过度拟合，这导致新的和未知的数据中的泛化性能差。增量贪心方法基于特征空间中特征选择的有限子集。通过提供低特征依赖性，与特征提取方法（诸如主成分分析）相比，增量贪心方法100需要较少的计算。

8. 发明授权

US08751495B2 Automated patient/document identification and categorization for medical data 有权
标题翻译：自动病人/文件识别和医疗数据分类
公开(公告)号：US08751495B2
公开(公告)日：2014-06-10
申请号：US12891983
申请日：2010-09-28
申请人： Stanley Chung , Faisal Farooq , Glenn Fung , Balaji Krishnapuram , R. Bharat Rao , Romer E. Rosales , John Weis , Shipeng Yu
发明人： Stanley Chung , Faisal Farooq , Glenn Fung , Balaji Krishnapuram , R. Bharat Rao , Romer E. Rosales , John Weis , Shipeng Yu
IPC分类号： G06F7/00 , G06F17/00 , G06F17/30
CPC分类号： G06F17/30616 , G06F19/00 , G16H50/70
摘要： A method, including receiving a data source selection from a user or software application, the data source including medical information of a plurality of patients, receiving, from the user or software application, a data pattern that is related to a concept to be explored in the data source, querying the data source to find information that approximately matches the data pattern; and receiving the information from the data source, wherein the information includes unstructured data, assigning a classification to individual parts of the information based on the part's relationship to the data pattern, and outputting the classified information to the user or software application.
摘要翻译：一种方法，包括从用户或软件应用接收数据源选择，所述数据源包括多个患者的医学信息，从用户或软件应用程序接收与将要探索的概念相关的数据模式数据源，查询数据源以查找与数据模式近似匹配的信息; 以及从所述数据源接收所述信息，其中，所述信息包括非结构化数据，基于所述部分与所述数据模式的关系，将所述信息的各个部分分配给所述信息，并将所述分类信息输出到所述用户或软件应用。

9. 发明申请

US20110078145A1 Automated Patient/Document Identification and Categorization For Medical Data 有权
标题翻译：医疗数据自动化患者/文件识别和分类
公开(公告)号：US20110078145A1
公开(公告)日：2011-03-31
申请号：US12891983
申请日：2010-09-28
申请人： Stanley Chung , Faisal Farooq , Glenn Fung , Balaji Krishnapuram , R. Bharat Rao , Romer E. Rosales , John Weis , Shipeng Yu
发明人： Stanley Chung , Faisal Farooq , Glenn Fung , Balaji Krishnapuram , R. Bharat Rao , Romer E. Rosales , John Weis , Shipeng Yu
IPC分类号： G06F17/30 , G06F3/048
CPC分类号： G06F17/30616 , G06F19/00 , G16H50/70
摘要： A method, including receiving a data source selection from a user or software application, the data source including medical information of a plurality of patients, receiving, from the user or software application, a data pattern that is related to a concept to be explored in the data source, querying the data source to find information that approximately matches the data pattern; and receiving the information from the data source, wherein the information includes unstructured data, assigning a classification to individual parts of the information based on the part's relationship to the data pattern, and outputting the classified information to the user or software application.
摘要翻译：一种方法，包括从用户或软件应用接收数据源选择，所述数据源包括多个患者的医学信息，从用户或软件应用程序接收与将要探索的概念相关的数据模式数据源，查询数据源以查找与数据模式近似匹配的信息; 以及从所述数据源接收所述信息，其中，所述信息包括非结构化数据，基于所述部分与所述数据模式的关系，将所述信息的各个部分分配给所述信息，并将所述分类信息输出到所述用户或软件应用。

10. 发明申请

US20100121178A1 Systems and Methods for Automated Diagnosis and Decision Support for Breast Imaging 审中-公开
标题翻译：乳腺成像自动诊断和决策支持的系统和方法
公开(公告)号：US20100121178A1
公开(公告)日：2010-05-13
申请号：US12621363
申请日：2009-11-18
申请人： Sriram Krishnan , R. Bharat Rao , Murat Dundar , Glenn Fung
发明人： Sriram Krishnan , R. Bharat Rao , Murat Dundar , Glenn Fung
IPC分类号： A61B5/055 , A61B8/14
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：提供了用于乳腺成像的CAD（计算机辅助诊断）系统和应用，其实现了从受试患者的患者信息（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，以提供对医生工作流程的各个方面的决策支持，包括例如乳腺癌的自动诊断其他自动化决策支持功能，其能够为乳腺癌的筛选和分期提供决策支持。 CAD系统实施机器学习技术，其使用从一个或多个相关临床领域的标记的患者病例的数据库获得（学习）的一组训练数据和/或对这些数据的专家解释，使得CAD系统能够“学习” 分析患者数据，进行适当的诊断评估和决策，以协助医师的工作流程。

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