利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

17 条记录 (耗时 0.019 秒)

    Feature Processing For Lung Nodules In Computer Assisted Diagnosis
    1.
    发明申请
    Feature Processing For Lung Nodules In Computer Assisted Diagnosis 有权
    计算机辅助诊断中肺结节特征处理

    公开(公告)号：US20090041328A1

    公开(公告)日：2009-02-12

    申请号：US12170639

    申请日：2008-07-10

    申请人： Lin Hong ,  Christopher V. Alvino ,  Hong Shen

    发明人： Lin Hong ,  Christopher V. Alvino ,  Hong Shen

    IPC分类号： G06K9/62

    CPC分类号： G06T7/0012 ,  G06T2207/30061 ,  G06T2207/30064

    摘要： Feature processing is provided for lung nodules in computer-assisted diagnosis. A feature that may better distinguish nodules from background is extracted using a Hough transform. Rather than relying on a specific boundary shape, the Hough transform accumulates evidence associated with a region, such as a ring region. The accumulated evidence provides a feature score without requiring a nodule to fit a specific shape. In another approach, a background level is determined from extracted features. Rather than attempting to normalize an image prior to extraction, the features are normalized. The feature normalization and generalized Hough transform extraction may be used together or alone.

    摘要翻译： 在计算机辅助诊断中为肺结节提供特征处理。 使用霍夫变换提取可以更好地区分结节与背景的特征。 霍夫变换不是依赖于特定的边界形状，而是累积与区域相关联的证据，例如环形区域。 积累的证据提供了一个特征分数，而不需要结节来适应特定的形状。 在另一种方法中，从提取的特征确定背景级别。 在尝试在提取之前对图像进行归一化，而不是将特征归一化。 特征归一化和广义霍夫变换提取可以一起使用或单独使用。

    Feature processing for lung nodules in computer assisted diagnosis
    2.
    发明授权
    Feature processing for lung nodules in computer assisted diagnosis 有权
    计算机辅助诊断肺结节特征处理

    公开(公告)号：US08107699B2

    公开(公告)日：2012-01-31

    申请号：US12170639

    申请日：2008-07-10

    申请人： Lin Hong ,  Christopher V. Alvino ,  Hong Shen

    发明人： Lin Hong ,  Christopher V. Alvino ,  Hong Shen

    IPC分类号： G06K9/00

    CPC分类号： G06T7/0012 ,  G06T2207/30061 ,  G06T2207/30064

    摘要： Feature processing is provided for lung nodules in computer-assisted diagnosis. A feature that may better distinguish nodules from background is extracted using a Hough transform. Rather than relying on a specific boundary shape, the Hough transform accumulates evidence associated with a region, such as a ring region. The accumulated evidence provides a feature score without requiring a nodule to fit a specific shape. In another approach, a background level is determined from extracted features. Rather than attempting to normalize an image prior to extraction, the features are normalized. The feature normalization and generalized Hough transform extraction may be used together or alone.

    摘要翻译： 在计算机辅助诊断中为肺结节提供特征处理。 使用霍夫变换提取可以更好地区分结节与背景的特征。 霍夫变换不是依赖于特定的边界形状，而是累积与区域相关联的证据，例如环形区域。 积累的证据提供了一个特征分数，而不需要结节来适应特定的形状。 在另一种方法中，从提取的特征确定背景级别。 在尝试在提取之前对图像进行归一化，而不是将特征归一化。 特征归一化和广义霍夫变换提取可以一起使用或单独使用。

    Machine Learning For Tissue Labeling Segmentation
    3.
    发明申请
    Machine Learning For Tissue Labeling Segmentation 有权
    机器学习用于组织标签分割

    公开(公告)号：US20090116737A1

    公开(公告)日：2009-05-07

    申请号：US12261383

    申请日：2008-10-30

    申请人： Atilla Peter Kiraly ,  Christopher V. Alvino ,  Hong Shen

    发明人： Atilla Peter Kiraly ,  Christopher V. Alvino ,  Hong Shen

    IPC分类号： G06K9/62

    CPC分类号： G06K9/6269 ,  G06K9/0014 ,  G06T7/11 ,  G06T7/143 ,  G06T2207/30024 ,  G06T2207/30096

    摘要： A method for directed machine learning includes receiving features including intensity data and location data of an image, condensing the intensity data and the location data into a feature vector, processing the feature vector by a plurality of classifiers, each classifier trained for a respective trained class among a plurality of classes, outputting, from each classifier, a probability of the feature vector belong to the respective trained class, and assigning the feature vector a label according to the probabilities of the classifiers, wherein the assignment produces a segmentation of the image.

    摘要翻译： 用于定向机器学习的方法包括接收包括强度数据和图像的位置数据的特征，将强度数据和位置数据聚合成特征向量，通过多个分类器处理特征向量，每个分类器针对相应的训练类进行训练 在多个类中，从每个分类器输出特征向量属于相应训练类的概率，并根据分类器的概率向特征向量分配标签，其中分配产生图像的分割。

    Machine learning for tissue labeling segmentation
    6.
    发明授权
    Machine learning for tissue labeling segmentation 有权
    机器学习组织标签分割

    公开(公告)号：US08170330B2

    公开(公告)日：2012-05-01

    申请号：US12261383

    申请日：2008-10-30

    申请人： Atilla Peter Kiraly ,  Christopher V. Alvino ,  Hong Shen

    发明人： Atilla Peter Kiraly ,  Christopher V. Alvino ,  Hong Shen

    IPC分类号： G06K9/62

    CPC分类号： G06K9/6269 ,  G06K9/0014 ,  G06T7/11 ,  G06T7/143 ,  G06T2207/30024 ,  G06T2207/30096

    摘要： A method for directed machine learning includes receiving features including intensity data and location data of an image, condensing the intensity data and the location data into a feature vector, processing the feature vector by a plurality of classifiers, each classifier trained for a respective trained class among a plurality of classes, outputting, from each classifier, a probability of the feature vector belong to the respective trained class, and assigning the feature vector a label according to the probabilities of the classifiers, wherein the assignment produces a segmentation of the image.

    摘要翻译： 用于定向机器学习的方法包括接收包括强度数据和图像的位置数据的特征，将强度数据和位置数据聚合成特征向量，通过多个分类器处理特征向量，每个分类器针对相应的训练类进行训练 在多个类中，从每个分类器输出特征向量属于相应训练类的概率，并根据分类器的概率向特征向量分配标签，其中分配产生图像的分割。

    Fluid Dynamics Approach To Image Segmentation
    9.
    发明申请
    Fluid Dynamics Approach To Image Segmentation 有权
    流体动力学方法对图像分割

    公开(公告)号：US20100002925A1

    公开(公告)日：2010-01-07

    申请号：US12496959

    申请日：2009-07-02

    申请人： Atilla Peter Kiraly ,  Leo Grady ,  Christopher V. Alvino

    发明人： Atilla Peter Kiraly ,  Leo Grady ,  Christopher V. Alvino

    IPC分类号： G06K9/34 ,  G06K9/00

    CPC分类号： G06K9/342 ,  G06K2009/366 ,  G06T7/11 ,  G06T7/149 ,  G06T2207/10072 ,  G06T2207/10132 ,  G06T2207/20101 ,  G06T2207/30004

    摘要： A method for segmenting image data within a data processing system includes acquiring an image. One or more seed points are established within the image. An advection vector field is computed based on image influences and user input. A dye concentration is determined at each of a plurality of portions of the image that results from a diffusion of dye within the computed advection field. The image is segmented into one or more regions based on the determined dye concentration for the corresponding dye.

    摘要翻译： 一种用于在数据处理系统内分割图像数据的方法包括获取图像。 在图像内建立一个或多个种子点。 基于图像影响和用户输入计算平流矢量场。 在由计算的对流场内的染料扩散产生的图像的多个部分中的每一个处确定染料浓度。 基于所确定的相应染料的染料浓度，将图像分割成一个或多个区域。

    Piecewise Smooth Mumford-Shah on an Arbitrary Graph
    10.
    发明申请
    Piecewise Smooth Mumford-Shah on an Arbitrary Graph 有权
    在任意图上分段平滑的Mumford-Shah

    公开(公告)号：US20090190833A1

    公开(公告)日：2009-07-30

    申请号：US12362892

    申请日：2009-01-30

    申请人： Christopher V. Alvino ,  Leo Grady

    发明人： Christopher V. Alvino ,  Leo Grady

    IPC分类号： G06K9/40

    CPC分类号： G06K9/40 ,  G06K9/6207

    摘要： A method for recovering a contour using combinatorial optimization includes receiving an input image, initializing functions for gradient f, smooth background g, and contour r, determining an optimum of the gradient f of a region R in the input image, extending the optimum of the gradient f of region R to a complement of R, determining an optimum of the smooth background function g for a region Q corresponding to the complement of R, extending the optimum of the smooth background function g of region Q to a complement of Q, and determining an optimum contour r according to the optimum of the gradient f and the optimum of the smooth background function g.

    摘要翻译： 使用组合优化来恢复轮廓的方法包括：接收输入图像，初始化梯度f，平滑背景g和轮廓r的函数，确定输入图像中的区域R的渐变f的最佳值， 区域R到R的补数的梯度f，确定对应于R的补码的区域Q的平滑背景函数g的最优，将区域Q的平滑背景函数g的最优值延伸到Q的补数，以及 根据梯度f的最优值和平滑背景函数g的最优值确定最佳轮廓r。