利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

47 条记录 (耗时 0.033 秒)

    System and method for multiple instance learning for computer aided detection
    11.
    发明授权
    System and method for multiple instance learning for computer aided detection 有权
    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。

    Using candidates correlation information during computer aided diagnosis
    12.
    发明授权
    Using candidates correlation information during computer aided diagnosis 有权
    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。

    System and method for learning rankings via convex hull separation
    14.
    发明申请
    System and method for learning rankings via convex hull separation 审中-公开

    公开(公告)号：US20070011121A1

    公开(公告)日：2007-01-11

    申请号：US11444606

    申请日：2006-06-01

    申请人： Jinbo Bi ,  Glenn Fung ,  Sriram Krishnan ,  Balaji Krishnapuram ,  R. Rao ,  Romer Rosales

    发明人： Jinbo Bi ,  Glenn Fung ,  Sriram Krishnan ,  Balaji Krishnapuram ,  R. Rao ,  Romer Rosales

    IPC分类号： G06F15/18

    CPC分类号： G06K9/6269

    摘要： A method for finding a ranking function ƒ that classifies feature points in an n-dimensional space includes providing a plurality of feature points xk derived from tissue sample regions in a digital medical image, providing training data A comprising training samples Aj where A = ⋃ j = 1 S ⁢ ( A j = { x i j } i = 1 m j ) , providing an ordering E={(P,Q)|APAQ} of at least some training data sets where all training samples xiεAP are ranked higher than any sample xjεAQ, solving a mathematical optimization program to determine the ranking function ƒ that classifies said feature points x into sets A. For any two sets Ai, Aj, AiAj, and the ranking function ƒ satisfies inequality constraints ƒ(xi)≦ƒ(xj) for all xiεconv(Ai) and xjεconv(Aj), where conv(A) represents the convex hull of the elements of set A.

    System and Method for Multiple Instance Learning for Computer Aided Detection
    16.
    发明申请
    System and Method for Multiple Instance Learning for Computer Aided Detection 有权
    计算机辅助检测多实例学习系统与方法

    公开(公告)号：US20070189602A1

    公开(公告)日：2007-08-16

    申请号：US11671777

    申请日：2007-02-06

    申请人： R. Rao ,  Murat Dundar ,  Balaji Krishnapuram ,  Glenn Fung

    发明人： R. Rao ,  Murat Dundar ,  Balaji Krishnapuram ,  Glenn Fung

    IPC分类号： G06K9/62 ,  G06K9/00

    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 images, includes providing a plurality of bags, each bag containing a 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 or healthy, and training a classifier on said 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 labeled of the associated region-of-interest.

    摘要翻译： 一种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，其中每个感兴趣区域已被标记为恶性或健康的，并且在所述多个特征样本袋上训练分类器，受限于至少一个 对应于特征样本的每个袋的凸包中的点被根据相关联的感兴趣区域的标记进行正确分类。

    Modeling lung cancer survival probability after or side-effects from therapy
    19.
    发明授权
    Modeling lung cancer survival probability after or side-effects from therapy 有权
    建立肺癌存活概率或治疗后副作用

    公开(公告)号：US08032308B2

    公开(公告)日：2011-10-04

    申请号：US12399274

    申请日：2009-03-06

    申请人： Shipeng Yu ,  Glenn Fung ,  Cary Dehing-Oberije ,  Dirk de Ruysscher ,  Sriram Krishnan ,  R. Bharat Rao ,  Philippe Lambin

    发明人： Shipeng Yu ,  Glenn Fung ,  Cary Dehing-Oberije ,  Dirk de Ruysscher ,  Sriram Krishnan ,  R. Bharat Rao ,  Philippe Lambin

    IPC分类号： G01N33/48 ,  G01N33/50

    CPC分类号： G06N99/005 ,  A61N5/1031 ,  A61N2005/1041 ,  G06F19/00 ,  G16H50/50

    摘要： Modeling of prognosis of survivability, side-effect, or both is provided. For example, RILI is predicted using bullae information. The amount, volume or ratio of Bullae, even alone, may indicate the likelihood of complication, such as the likelihood of significant (e.g., stage 3) pneumonitis. As another example, RILI is predicted using uptake values of an imaging agent. Standardized uptake from a functional image (e.g., FDG uptake from a positron emission image), alone or in combination with other features, may indicate the likelihood of side-effect. In another example, survivability, such as two-year survivability, is predicted using blood biomarkers. The characteristics of a patient's blood may be measured and, alone or in combination with other features, may indicate the likelihood of survival. The modeling may be for survivability, side-effect, or both and may use one or more of the blood biomarker, uptake value, and bullae features.

    摘要翻译： 提供了对生存能力，副作用或两者的预后的建模。 例如，使用大疱信息预测RILI。 Bullae的数量，体积或比例，甚至单独可能表明并发症的可能性，例如显着（例如阶段3）肺炎的可能性。 作为另一个例子，使用成像剂的摄取值来预测RILI。 来自功能图像的标准摄取（例如，来自正电子发射图像的FDG摄取）单独或与其它特征组合可以指示副作用的可能性。 在另一个例子中，使用血液生物标志物来预测存活能力，例如两年生存能力。 可以测量患者血液的特征，单独或与其它特征组合可能表明存活的可能性。 建模可以是存活性，副作用或两者，并且可以使用一种或多种血液生物标志物，摄取值和大疱特征。

    Knowledge-Based Interpretable Predictive Model for Survival Analysis
    20.
    发明申请
    Knowledge-Based Interpretable Predictive Model for Survival Analysis 有权
    基于知识的解释性生存分析预测模型

    公开(公告)号：US20100057651A1

    公开(公告)日：2010-03-04

    申请号：US12506583

    申请日：2009-07-21

    申请人： Glenn Fung ,  Cary Dehing-Oberije ,  Andreas Lubbertus Aloysius Johannes Dekker ,  Philippe Lambin ,  Shipeng Yu ,  Kartik Jayasurya Komati

    发明人： Glenn Fung ,  Cary Dehing-Oberije ,  Andreas Lubbertus Aloysius Johannes Dekker ,  Philippe Lambin ,  Shipeng Yu ,  Kartik Jayasurya Komati

    IPC分类号： G06F15/18 ,  G06N5/02

    CPC分类号： G06N7/005 ,  A61N2005/1041

    摘要： Knowledge-based interpretable predictive modeling is provided. Expert knowledge is used to seed training of a model by a machine. The expert knowledge may be incorporated as diagram information, which relates known causal relationships between predictive variables. A predictive model is trained. In one embodiment, the model operates even with a missing value for one or more variables by using the relationship between variables. For application, the model outputs a prediction, such as the likelihood of survival for two years of a lung cancer patient. A graphical representation of the model is also output. The graphical representation shows the variables and relationships between variables used to determine the prediction. The graphical representation is interpretable by a physician or other to assist in understanding.

    摘要翻译： 提供基于知识的可解释预测模型。 专家知识用于通过机器对模型进行种子培训。 专家知识可以作为图表信息并入，其涉及预测变量之间的已知因果关系。 一个预测模型被训练。 在一个实施例中，通过使用变量之间的关系，该模型甚至通过一个或多个变量的缺失值来运行。 为了应用，该模型输出预测，例如两年的肺癌患者的生存可能性。 还会输出模型的图形表示。 图形表示显示用于确定预测的变量和变量之间的关系。 图形表示可由医生或其他人解释，以协助理解。