利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

7 条记录 (耗时 0.012 秒)

    Segment-preserving crossover in genetic algorithms
    1.
    发明授权
    Segment-preserving crossover in genetic algorithms 有权
    遗传算法中的段保留交叉

    公开(公告)号：US08005772B2

    公开(公告)日：2011-08-23

    申请号：US11914991

    申请日：2006-06-15

    申请人： Larry Eshelman

    发明人： Larry Eshelman

    IPC分类号： G06F15/18 ,  G06N3/00 ,  G06N3/12

    CPC分类号： G01J3/44 ,  G01N21/274 ,  G01N21/65 ,  G01N2201/129 ,  G01N2201/1293 ,  G06K9/00523

    摘要： Cross over (S560) in a genetic algorithm (128) is adapted for deriving an optimal mask (S540), or set of segments of a line. Each mask of a chromosome is subject to cross over with the respective mask of the other parent. Any overlapping part, whether a filtering (320) or pass-through part (350), is retained in the child (334) to preserve commonality. The part is preferably, potentially extended, according to one parent or the other, as decided pseudo-randomly (430). In a preferred application, spectrums of candidate blood constituents are masked for fitting to ensemble spectrums of test blood samples (S610, S620). The developed masks are applicable to constituent spectrums to create masked spectrums (S710) which are then applicable to an actual blood sample to be analyzed (S720).

    摘要翻译： 遗传算法（128）中的交叉（S560）适于导出最佳掩码（S540）或一行的段的集合。 染色体的每个掩模与另一个亲本的相应掩模交叉。 任何重叠的部分，无论是过滤（320）还是直通部分（350）都保留在子（334）中以保持共同性。 该部分优选地，根据一个父或另一个，如伪随机地确定（430）潜在地扩展。 在优选的应用中，候选血液成分的光谱被掩蔽以适合测试血液样品的综合谱（S610，S620）。 开发的掩模适用于构成光谱的组件光谱（S710），然后将其应用于待分析的实际血液样本（S720）。

    METHOD AND APPARATUS FOR AUTOMATICALLY DEVELOPING A HIGH PERFORMANCE CLASSIFIER FOR PRODUCING MEDICALLY MEANINGFUL DESCRIPTORS IN MEDICAL DIAGNOSIS IMAGING
    4.
    发明申请
    METHOD AND APPARATUS FOR AUTOMATICALLY DEVELOPING A HIGH PERFORMANCE CLASSIFIER FOR PRODUCING MEDICALLY MEANINGFUL DESCRIPTORS IN MEDICAL DIAGNOSIS IMAGING 有权
    用于自动开发用于在医学诊断成像中生产医学意义描述符的高性能分类器的方法和装置

    公开(公告)号：US20090268952A1

    公开(公告)日：2009-10-29

    申请号：US11721999

    申请日：2005-12-13

    申请人： James David Schaffer ,  Walid Ali ,  Larry Eshelman ,  Claude Cohen-Bacrie ,  Jean-Michel Lagrange ,  Claire Levrier ,  Nicolas Francois Villain ,  Robert Randall Entrekin

    发明人： James David Schaffer ,  Walid Ali ,  Larry Eshelman ,  Claude Cohen-Bacrie ,  Jean-Michel Lagrange ,  Claire Levrier ,  Nicolas Francois Villain ,  Robert Randall Entrekin

    IPC分类号： G06K9/00

    CPC分类号： G06K9/6217

    摘要： A method for determining the presence or absence of malignant features in medical images, wherein a plurality of base comparison or training images of various types of lesions taken of actual patient is examined by one or more image reading experts to create a first database array. Low-level features of each of the lesions in the same plurality of base comparisons or training images arc determined using one or more image processing algorithms to obtain a second database array set. The first and second database array set are combined to create a training database array set which is input to a learning system that discovers/learns a classifier that maps from a subset of the low-level features to the expert's evaluation in the first database array set. The classifier is used to determine the presence of a particular mid-level feature in an image of lesion in a patient based solely on the image.

    摘要翻译： 一种用于确定医学图像中恶性特征的存在或不存在的方法，其中由一个或多个图像读取专家检查由实际患者取得的各种类型的损伤的多个基础比较或训练图像以创建第一数据库阵列。 使用一个或多个图像处理算法确定相同多个基本比较或训练图像中的每个病变的低级特征以获得第二数据库阵列集。 组合第一和第二数据库阵列组以创建训练数据库阵列集合，其被输入到发现/学习从低级特征的子集映射到第一数据库阵列集合中的专家评估的分类器的学习系统 。 分类器用于仅基于图像来确定患者的病变图像中特定中级特征的存在。

    Segment-Preserving Crossover in Genetic Algorithms
    5.
    发明申请
    Segment-Preserving Crossover in Genetic Algorithms 有权
    遗传算法中的段保留交叉

    公开(公告)号：US20080195565A1

    公开(公告)日：2008-08-14

    申请号：US11914991

    申请日：2006-06-15

    申请人： Larry Eshelman

    发明人： Larry Eshelman

    IPC分类号： G06N3/12

    CPC分类号： G01J3/44 ,  G01N21/274 ,  G01N21/65 ,  G01N2201/129 ,  G01N2201/1293 ,  G06K9/00523

    摘要： Cross over (S560) in a genetic algorithm (128) is adapted for deriving an optimal mask (S540), or set of segments of a line. Each mask of a chromosome is subject to cross over with the respective mask of the other parent. Any overlapping part, whether a filtering (320) or pass-through part (350), is retained in the child (334) to preserve commonality. The part is preferably, potentially extended, according to one parent or the other, as decided pseudo-randomly (430). In a preferred application, spectrums of candidate blood constituents are masked for fitting to ensemble spectrums of test blood samples (S610, S620). The developed masks are applicable to constituent spectrums to create masked spectrums (S710) which are then applicable to an actual blood sample to be analyzed (S720).

    摘要翻译： 遗传算法（128）中的交叉（S 560）适于导出最佳掩码（S 540）或一行的段的集合。 染色体的每个掩模与另一个亲本的相应掩模交叉。 任何重叠的部分，无论是过滤（320）还是直通部分（350）都保留在子（334）中以保持共同性。 该部分优选地，根据一个父或另一个，如伪随机地确定（430）潜在地扩展。 在优选的应用中，候选血液成分的光谱被掩蔽以适合测试血液样品的综合谱（S 610，S 620）。 显影的掩模适用于构成光谱以产生掩蔽光谱（S 710），其然后可应用于待分析的实际血液样品（S 720）。

    Method and apparatus for selecting the operating parameters for a medical imaging system
    6.
    发明申请
    Method and apparatus for selecting the operating parameters for a medical imaging system 审中-公开
    用于选择医学成像系统的操作参数的方法和装置

    公开(公告)号：US20060100738A1

    公开(公告)日：2006-05-11

    申请号：US10537872

    申请日：2003-12-12

    申请人： Yasser Alsafadi ,  Larry Eshelman ,  Xinxin Zhu ,  Amr Yassin

    发明人： Yasser Alsafadi ,  Larry Eshelman ,  Xinxin Zhu ,  Amr Yassin

    IPC分类号： G06F7/00

    CPC分类号： G06F19/325 ,  A61B5/055 ,  A61B6/03 ,  A61B6/56 ,  A61B8/00 ,  A61B2560/0271 ,  G06F19/321 ,  G16H50/70

    摘要： A system is provided for guiding the selection of a value for each of a plurality of parameters needed to perform a procedure with a medical system (100). The system includes a first knowledge base (210) comprising procedures and treatment regimes, a second knowledge base (212) comprising patient information and therapy history, and a third knowledge base (214) comprising clinical guidelines. A domain ontology (220) provides the semantic mapping between information in the first, second, and third knowledge bases. A system configuration database (226) contains physical characteristics pertaining to the medical system and a system characteristics database (228) contains mathematical formulas and algorithms for calibrating the medical system based on the data in the system configuration database. An interference engine (224) is also provided for generating a set of parameters based on the information in the first, second, and third knowledge bases, the system configuration database, and the system characteristics database.

    摘要翻译： 提供了一种系统，用于引导用于与医疗系统（100）执行过程所需的多个参数中的每一个的值的选择。 该系统包括包括程序和治疗方案的第一知识库（210），包括患者信息和治疗历史的第二知识库（212）和包括临床指南的第三知识库（214）。 域本体（220）提供第一，第二和第三知识库中的信息之间的语义映射。 系统配置数据库（226）包含与医疗系统相关的物理特性，系统特征数据库（228）包含用于基于系统配置数据库中的数据来校准医疗系统的数学公式和算法。 还提供干扰引擎（224），用于基于第一，第二和第三知识库中的信息，系统配置数据库和系统特征数据库来生成一组参数。

    Method for determining normal measurements for a patient
    7.
    发明申请
    Method for determining normal measurements for a patient 审中-公开
    用于确定患者正常测量的方法

    公开(公告)号：US20060135855A1

    公开(公告)日：2006-06-22

    申请号：US10537874

    申请日：2003-12-03

    申请人： Yasser Alsafadi ,  Larry Eshelman ,  Xinxin Zhu ,  Amr Yassin ,  Doug Sluis

    发明人： Yasser Alsafadi ,  Larry Eshelman ,  Xinxin Zhu ,  Amr Yassin ,  Doug Sluis

    IPC分类号： A61B5/00

    CPC分类号： A61B5/107 ,  A61B5/4504 ,  G06F19/325 ,  G16H10/60 ,  G16H50/20

    摘要： Method and system for determining a norm to apply to a patient being examined in which at least one physical characteristic of the patient is determined from the examination and guidelines relating thereto are obtained. Information about the patient other than from the examination and established norms for each characteristic are also obtained. An established norm to be applied to the patient is selected based on the determination of the characteristic(s), the guidelines relating to the determination thereof, and the information about the patient other than from the examination. The selection of the norm is performed by an inference engine. The norm is applied to the characteristic, e.g., a measured anatomical feature, to obtain a normal value therefor. The measured anatomical feature is compared to the normal value to determine whether it is indicative of a normal or abnormal condition.

    摘要翻译： 用于确定适用于正在检查的患者的规范的方法和系统，其中从检查确定患者的至少一个身体特征并且获得与之相关的准则。 还可以获得关于除了检查以外的患者的信息以及针对每个特征的确定的规范。 基于特征的确定，与其确定有关的准则以及除了检查之外的关于患者的信息，选择适用于患者的既定规范。 规范的选择由推理机执行。 将范数应用于特征，例如测量的解剖特征，以获得其正常值。 将测量的解剖特征与正常值进行比较，以确定其是否表示正常或异常状况。