利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

46 条记录 (耗时 0.022 秒)

    System and Method for Detecting Spherical and Ellipsoidal Objects Using Cutting Planes
    21.
    发明申请
    System and Method for Detecting Spherical and Ellipsoidal Objects Using Cutting Planes 审中-公开
    使用切割平面检测球形和椭圆体物体的系统和方法

    公开(公告)号：US20090016583A1

    公开(公告)日：2009-01-15

    申请号：US12169773

    申请日：2008-07-09

    申请人： Matthias Wolf ,  Marcos Salganicoff ,  Sarang Lakare

    发明人： Matthias Wolf ,  Marcos Salganicoff ,  Sarang Lakare

    IPC分类号： G06K9/46

    CPC分类号： G06K9/4609 ,  G06K9/50 ,  G06K2209/053

    摘要： A method for detecting spherical and ellipsoidal objects is digitized medical images includes providing a 2-dimensional (2D) slice I(x, y) extracted from a medical image volume of a colon, said image volume comprising a plurality of intensities associated with a 3 grid of points, generating a plurality of templates of different sizes whose shape matches a target structure being sought in said slice, calculating a normalized gradient from said slice, calculating a diverging field gradient response (DFGR) for each of the plurality of masks with the normalized gradient, and selecting a strongest response as being indicative of the position and size of the target structure.

    摘要翻译： 用于检测球形和椭圆体的方法是数字化医学图像，包括提供从结肠的医学图像体积提取的二维（2D）切片I（x，y），所述图像体积包括与3 生成多个不同尺寸的模板，其形状与在所述切片中寻找的目标结构相匹配，从所述切片计算归一化梯度，计算多个掩模中的每一个的发散场梯度响应（DFGR） 并且选择最强的响应来表示目标结构的位置和大小。

    Synchronized navigation of medical images
    24.
    发明授权
    Synchronized navigation of medical images 有权
    医学图像同步导航

    公开(公告)号：US09460510B2

    公开(公告)日：2016-10-04

    申请号：US13853174

    申请日：2013-03-29

    申请人： Gerardo Hermosillo Valadez ,  Marcos Salganicoff ,  Matthias Wolf ,  Xiang Sean Zhou ,  Yiqiang Zhan

    发明人： Gerardo Hermosillo Valadez ,  Marcos Salganicoff ,  Matthias Wolf ,  Xiang Sean Zhou ,  Yiqiang Zhan

    IPC分类号： G06K9/00 ,  G06T7/00

    CPC分类号： G06T7/0028 ,  G06T7/33 ,  G06T2207/30004

    摘要： Disclosed herein is a framework for facilitating synchronized image navigation. In accordance with one aspect, at least first and second medical images are received. A non-linear mapping between the first and second medical images is generated. A selection of a given location in the first medical image is received in response to a user's navigational operation. Without deforming the second medical image, a target location in the second medical image is determined by using the non-linear mapping. The target location corresponds to the given location in the first medical image. An optimized deformation-free view of the second medical image is generated based at least in part on the target location. While the user performs navigational operations on the first medical image, the framework repeatedly receives the selection of the given location, determines the target location using the non-linear mapping, and generates the optimized deformation-free view of the second medical image based at least in part on the target location.

    摘要翻译： 这里公开了一种促进同步图像导航的框架。 根据一个方面，至少接收第一和第二医学图像。 产生第一和第二医学图像之间的非线性映射。 响应于用户的导航操作接收对第一医疗图像中的给定位置的选择。 在不使第二医用图像变形的情况下，通过使用非线性映射来确定第二医用图像中的目标位置。 目标位置对应于第一医疗图像中的给定位置。 至少部分地基于目标位置产生第二医疗图像的优化的无变形视图。 当用户在第一医学图像上执行导航操作时，框架重复地接收对给定位置的选择，使用非线性映射确定目标位置，并且至少基于第二医学图像生成优化的无变形视图 部分在目标位置。

    System and Method for Robust Segmentation of Pulmonary Nodules of Various Densities
    28.
    发明申请
    System and Method for Robust Segmentation of Pulmonary Nodules of Various Densities 有权
    用于各种密度的肺结节的鲁棒分割的系统和方法

    公开(公告)号：US20090092302A1

    公开(公告)日：2009-04-09

    申请号：US12243387

    申请日：2008-10-01

    申请人： Toshiro Kubota ,  Anna Jerebko ,  Marcos Salganicoff

    发明人： Toshiro Kubota ,  Anna Jerebko ,  Marcos Salganicoff

    IPC分类号： G06K9/00

    CPC分类号： G06T7/0012 ,  G06T7/11 ,  G06T7/187 ,  G06T2207/30064

    摘要： A method for differentiating pulmonary nodules in digitized medical images includes identifying an object of interest from a digital image of the lungs, computing a first distance map of each point of the object of interest, determining a seed point from the first distance map, starting from the seed point, growing a first region by adding successive adjacent layers of points until a background point is reached, and partitioning the first region into a nodule region and a non-nodule region.

    摘要翻译： 用于区分数字化医学图像中的肺结节的方法包括从肺的数字图像识别感兴趣对象，计算感兴趣对象的每个点的第一距离图，从第一距离图确定种子点，从 种子点，通过添加连续的相邻层点直到达到背景点来生长第一区域，并将第一区域划分成结节区域和非结节区域。

    System and Method for Lesion Detection Using Locally Adjustable Priors
    29.
    发明申请
    System and Method for Lesion Detection Using Locally Adjustable Priors 有权
    使用局部可调节的病变检测系统和方法

    公开(公告)号：US20090092300A1

    公开(公告)日：2009-04-09

    申请号：US12241183

    申请日：2008-09-30

    申请人： Anna Jerebko ,  Marcos Salganicoff ,  Maneesh Dewan ,  Harald Steck

    发明人： Anna Jerebko ,  Marcos Salganicoff ,  Maneesh Dewan ,  Harald Steck

    IPC分类号： G06K9/00

    CPC分类号： G06K9/6278 ,  G06K2209/05 ,  G06K2209/053 ,  G06T7/0012 ,  G06T7/11 ,  G06T7/143 ,  G06T2207/30028 ,  G06T2207/30061

    摘要： According to an aspect of the invention, a method for training a classifier for classifying candidate regions in computer aided diagnosis of digital medical images includes providing a training set of annotated images, each image including one or more candidate regions that have been identified as suspicious, deriving a set of descriptive feature vectors, where each candidate region is associated with a feature vector. A subset of the features are conditionally dependent, and the remaining features are conditionally independent. The conditionally independent features are used to train a naïve Bayes classifier that classifies the candidate regions as lesion or non-lesion. A joint probability distribution that models the conditionally dependent features, and a prior-odds probability ratio of a candidate region being associated with a lesion are determined from the training images. A new classifier is formed from the naïve Bayes classifier, the joint probability distribution, and the prior-odds probability ratio.

    摘要翻译： 根据本发明的一个方面，一种训练分类器的方法，用于对数字医学图像的计算机辅助诊断中的候选区域进行分类，包括提供注释图像的训练集，每个图像包括已被识别为可疑的一个或多个候选区域， 导出一组描述性特征向量，其中每个候选区域与特征向量相关联。 特征的子集有条件依赖，其余的特征是有条件的独立的。 条件独立的特征用于训练将候选区域分类为病变或非损伤的朴素贝叶斯分类器。 从训练图像确定与条件相关特征建模的联合概率分布以及与病变相关联的候选区域的先验概率概率。 从初始贝叶斯分类器，联合概率分布和先验概率概率比构成新的分类器。

    Method and system for polyp segmentation for 3D computed tomography colonography
    30.
    发明申请
    Method and system for polyp segmentation for 3D computed tomography colonography 有权
    用于3D计算机断层扫描结构的息肉分割方法和系统

    公开(公告)号：US20090074272A1

    公开(公告)日：2009-03-19

    申请号：US12231772

    申请日：2008-09-05

    申请人： Le Lu ,  Adrian Barbu ,  Matthias Wolf ,  Sarang Lakare ,  Luca Bogoni ,  Marcos Salganicoff ,  Dorin Comaniciu

    发明人： Le Lu ,  Adrian Barbu ,  Matthias Wolf ,  Sarang Lakare ,  Luca Bogoni ,  Marcos Salganicoff ,  Dorin Comaniciu

    IPC分类号： G06K9/00

    CPC分类号： G06T7/0012 ,  G06T7/11 ,  G06T7/143 ,  G06T2207/10081 ,  G06T2207/20076 ,  G06T2207/30032

    摘要： A method and system for polyp segmentation in computed tomography colonogrphy (CTC) volumes is disclosed. The polyp segmentation method utilizes a three-staged probabilistic binary classification approach for automatically segmenting polyp voxels from surrounding tissue in CTC volumes. Based on an input initial polyp position, a polyp tip is detected in a CTC volume using a trained 3D point detector. A local polar coordinate system is then fit to the colon surface in the CTC volume with the origin at the detected polyp tip. Polyp interior voxels and polyp exterior voxels are detected along each axis of the local polar coordinate system using a trained 3D box. A boundary voxel is detected on each axis of the local polar coordinate system based on the detected polyp interior voxels and polyp exterior voxels by boosted 1D curve parsing using a trained classifier. This results in a segmented polyp boundary.

    摘要翻译： 公开了一种计算机断层扫描（CTC）体积中息肉分割的方法和系统。 息肉分割方法采用三阶段概率二分类方法，自动分割CTC体积周围组织的息肉体素。 基于输入的初始息肉位置，使用训练有素的3D点检测器在CTC体积中检测息肉末端。 然后将局部极坐标系拟合到CTC体积中的结肠表面，其中原点在检测到的息肉末端。 使用训练有素的3D框，在局部极坐标系的每个轴上检测Polyp内部体素和息肉外部体素。 基于检测到的息肉内部体素和息肉外部体素，通过使用训练有素的分类器进行升压1D曲线解析，在局部极坐标系的每个轴上检测边界体素。 这导致分段息肉边界。