公开(公告)号：US08131035B2

公开(公告)日：2012-03-06

申请号：US12025979

申请日：2008-02-05

申请人： Leo Grady ,  Fred S. Azar

发明人： Leo Grady ,  Fred S. Azar

IPC分类号： G06K9/00

CPC分类号： G06K9/0014 ,  G06T7/11 ,  G06T7/162 ,  G06T2207/10056 ,  G06T2207/20072 ,  G06T2207/20101 ,  G06T2207/30024

摘要： A computer implemented method for differentiating between elements of an image and a background includes inputting an image comprising pixels forming a view of the elements and a background, providing a model for assigning a probability of belonging to a predefined class to each of the pixels, assigning a probability to each of the pixels of belonging to the predefined class, labeling each of the pixels according to a corresponding probability and a predefined threshold, determining boundaries between groups of like-labeled pixels, and outputting a visualization of the boundaries.

摘要翻译： 用于区分图像和背景的元素的计算机实现方法包括输入包括形成元素和背景的视图的像素的图像，提供用于将属于预定类的概率分配给每个像素的模型，分配 属于预定义类别的每个像素的概率，根据相应的概率和预定义的阈值标记每个像素，确定相似标记的像素的组之间的边界，并输出边界的可视化。

公开(公告)号：US07907777B2

公开(公告)日：2011-03-15

申请号：US11273187

申请日：2005-11-14

申请人： Shmuel Aharon ,  Leo Grady ,  Thomas Schiwietz

发明人： Shmuel Aharon ,  Leo Grady ,  Thomas Schiwietz

IPC分类号： G06K9/34 ,  G06K9/48

CPC分类号： G06K9/6252 ,  G06K9/6232

摘要： A manifold learning technique is applied to the problem of discriminating an object boundary between neighboring pixels/voxels in an image. The manifold learning technique is referred to as locality preserving projections. The application is for multi-channel images, which may include registered images/volumes, a time series of images/volumes, images obtained using different pulse sequences or contrast factors, radar and color photographs.

摘要翻译： 歧管学习技术被应用于鉴别图像中相邻像素/体素之间的对象边界的问题。 歧管学习技术被称为局部保留投影。 应用于多通道图像，其可以包括记录的图像/体积，图像/体积的时间序列，使用不同脉冲序列或对比度因子获得的图像，雷达和彩色照片。

公开(公告)号：US07711168B2

公开(公告)日：2010-05-04

申请号：US11582907

申请日：2006-10-18

申请人： Leo Grady

发明人： Leo Grady

IPC分类号： G06K9/00 ,  A61B6/00

CPC分类号： G06T7/162 ,  G06T7/12 ,  G06T7/181 ,  G06T2207/10081 ,  G06T2207/20101 ,  G06T2207/30104

摘要： A method for tracking images of a blood vessel wherein user indication of the source and terminus of an image of the blood vessel is provided and the Dijkstra algorithm is used to find the shortest path along the current established from a steady-state circuit model with the current source and sink given by user-placed seeds on the image. Since the method looks at the change in current flow, multiply-connected objects that are either significantly larger or smaller than the vessel will be ignored since the current flow will change dramatically. In contrast, a simple, shortest-path, approach between the source and terminus of the vessel would be unlikely to stay within the vessel if it were to touch another object with similar intensity.

摘要翻译： 一种用于跟踪血管图像的方法，其中提供了血管图像的源和末端的用户指示，并且使用Dijkstra算法找到沿着从稳态电路模型建立的电流的最短路径，其中 由用户放置的种子在图像上给出的当前源和信宿。 由于该方法考察了当前流量的变化，所以显着大于或小于容器的多连接对象将被忽略，因为当前的流量将会发生显着变化。 相比之下，如果要接触另一个具有相似强度的物体，船只的源头和末端之间的简单，最短路径的方法将不太可能停留在船舶内。

公开(公告)号：US07542604B2

公开(公告)日：2009-06-02

申请号：US11205729

申请日：2005-08-17

申请人： Leo Grady ,  Tolga Tasdizen ,  Ross Whitaker

发明人： Leo Grady ,  Tolga Tasdizen ,  Ross Whitaker

IPC分类号： G06K9/34

CPC分类号： G06T7/143 ,  G06T7/12 ,  G06T2207/20016 ,  G06T2207/20101 ,  G06T2207/30004

摘要： A method of segmenting a digitized image includes marking a subset of pixels in an image, defining edge conductances between each pair of adjacent pixels in the image based on the intensity difference of each said pixel pair, associating a probability potential with each unmarked pixel, and using a multigrid method to solve for the probability potentials for each unmarked pixel, wherein a restriction operator from the image grid to a coarse grid is calculated from a conductance-weighted average of the conductances on the image grid, the coarse grid conductances are calculated from the image grid conductances using a Δ-Y conversion, and the multigrid prolongation operator is calculated using a conductance-weighted interpolation of the coarse grid conductances.

摘要翻译： 分割数字化图像的方法包括标记图像中的像素子集，基于每个所述像素对的强度差定义图像中每对相邻像素之间的边缘电导，将概率电位与每个未标记像素相关联，以及 使用多网格方法来求解每个未标记像素的概率电位，其中根据图像网格上的电导的电导加权平均来计算从图像网格到粗网格的限制算子，粗网格电导从 使用Delta-Y转换的图像格栅电导，并且使用粗网格电导的电导加权插值来计算多网格延长算子。

公开(公告)号：US07519220B2

公开(公告)日：2009-04-14

申请号：US11273511

申请日：2005-11-14

申请人： Shmuel Aharon ,  Leo Grady ,  Thomas Schiwietz

发明人： Shmuel Aharon ,  Leo Grady ,  Thomas Schiwietz

IPC分类号： G06K9/34

CPC分类号： G06K9/6224 ,  G06K9/342 ,  G06T7/12 ,  G06T7/194 ,  G06T7/62 ,  G06T2207/20101

摘要： A system and method for segmenting an object in an image using an isoperimetric ratio in a graphics processing unit is disclosed. The object is identified by one or more selected pixels located within the object. The system includes a graphics processing unit and software loadable on the graphics processing unit. The software is operable to find weights for edges, to build a Laplacian matrix and a d vector, to eliminate the row and column corresponding to the one or more selected pixels to determine L0 and d0, to solve x0 in the equation L0x0=d0; and to threshold the potentials x at the value that selects the object having the lowest isoperimetric ratio.

摘要翻译： 公开了一种用于在图形处理单元中使用等效比分割图像中的对象的系统和方法。 对象由位于对象内的一个或多个所选像素识别。 该系统包括图形处理单元和可加载在图形处理单元上的软件。 软件可操作以找到边缘的权重，以构建拉普拉斯矩阵和d向量，以消除与一个或多个所选像素相对应的行和列，以确定L0和d0，以求解方程式L0x0 = d0中的x0; 并且以选择具有最低等效比的对象的值来阈值电位x。

公开(公告)号：US20080226169A1

公开(公告)日：2008-09-18

申请号：US11876847

申请日：2007-10-23

申请人： Leo Grady

发明人： Leo Grady

IPC分类号： G06K9/34

CPC分类号： G06K9/342

摘要： A method for image volume segmentation includes receiving an input image, obtaining an oriented closed contour on one or more slices of the input image, determining a minimum-weight surface from the oriented closed contour using a minimum-cost circulation network flow, and outputting the minimum-weight surface as a segmentation of the input image.

摘要翻译： 一种用于图像体积分割的方法包括接收输入图像，在所述输入图像的一个或多个切片上获得定向闭合轮廓，使用最小成本循环网络流从所述定向闭合轮廓确定最小权重曲面，并输出 最小重量表面作为输入图像的分割。

公开(公告)号：US20080187198A1

公开(公告)日：2008-08-07

申请号：US12025979

申请日：2008-02-05

申请人： Leo Grady ,  Fred S. Azar

发明人： Leo Grady ,  Fred S. Azar

IPC分类号： G06K9/00

CPC分类号： G06K9/0014 ,  G06T7/11 ,  G06T7/162 ,  G06T2207/10056 ,  G06T2207/20072 ,  G06T2207/20101 ,  G06T2207/30024

摘要： A computer implemented method for differentiating between elements of an image and a background includes inputting an image comprising pixels forming a view of the elements and a background, providing a model for assigning a probability of belonging to a predefined class to each of the pixels, assigning a probability to each of the pixels of belonging to the predefined class, labeling each of the pixels according to a corresponding probability and a predefined threshold, determining boundaries between groups of like-labeled pixels, and outputting a visualization of the boundaries.

摘要翻译： 用于区分图像和背景的元素的计算机实现方法包括输入包括形成元素和背景的视图的像素的图像，提供用于将属于预定类的概率分配给每个像素的模型，分配 属于预定义类别的每个像素的概率，根据相应的概率和预定义的阈值标记每个像素，确定相似标记的像素的组之间的边界，并输出边界的可视化。

公开(公告)号：US20080033302A1

公开(公告)日：2008-02-07

申请号：US11735529

申请日：2007-04-16

申请人： Leo Grady ,  Osman Bodur ,  Randolph Setser ,  Arthur Stillman ,  Thomas O'Donnell ,  Gareth Funka-Lea

发明人： Leo Grady ,  Osman Bodur ,  Randolph Setser ,  Arthur Stillman ,  Thomas O'Donnell ,  Gareth Funka-Lea

IPC分类号： A61B5/02

CPC分类号： G06T7/0012 ,  G06K9/34 ,  G06K2009/00932 ,  G06K2209/05 ,  G06T7/66 ,  G06T2207/30101

摘要： A method for automatically analyzing an aortic aneurysm includes providing a digitized 3-dimensional image volume of an aorta, determining which voxels in said image are likely to be lumen voxels, determining a distance of said lumen voxels from an aortic boundary, finding a centerline of the aorta in said image volume based on said lumen voxel distances, constructing a series of 2-dimensional multiplanar reformatted (MFR) image planes orthogonal to this centerline, segmenting aortic cross sections in each said MPR image plane wherein an aortic wall is located in each MPR image, and constructing from said aortic wall locations a 3D model of the aorta.

摘要翻译： 用于自动分析主动脉瘤的方法包括提供主动脉的数字化的3维图像体积，确定所述图像中的哪些体素可能是腔体素，确定所述腔体素与主动脉边界的距离，找到 基于所述管腔体素距离在所述图像体积中的主动脉，构建与该中心线正交的一系列二维多平面重整格式（MFR）图像平面，在每个所述MPR图像平面中分割主动脉横截面，其中主动脉壁位于每个 MPR图像，以及从所述主动脉壁构建主动脉的3D模型。

公开(公告)号：US20060147115A1

公开(公告)日：2006-07-06

申请号：US11234977

申请日：2005-09-26

申请人： Leo Grady

发明人： Leo Grady

IPC分类号： G06K9/34

CPC分类号： G06T7/162 ,  G06T7/11 ,  G06T7/143 ,  G06T2207/10072 ,  G06T2207/20016 ,  G06T2207/30004

摘要： A method of segmenting a digitized image includes providing a digitized image on a domain of points on an N%N grid, defining a weight between each pair of adjacent points in the image based on the intensity difference of each said point pair, marking a subset of points in the image, associating a probability potential with each unmarked point, and using a multigrid method to solve for the probability potentials for each unmarked point, wherein a restriction operator for the image is applied to an (N−1)%(N−1) image wherein each image weight is treated as a function of an adjoining point for application of the restriction operator, wherein said restriction operator determines weights of a coarse level grid.

公开(公告)号：US20060050959A1

公开(公告)日：2006-03-09

申请号：US11205729

申请日：2005-08-17

申请人： Leo Grady ,  Tolga Tasdizen ,  Ross Whitaker

发明人： Leo Grady ,  Tolga Tasdizen ,  Ross Whitaker

IPC分类号： G06K9/34

CPC分类号： G06T7/143 ,  G06T7/12 ,  G06T2207/20016 ,  G06T2207/20101 ,  G06T2207/30004

摘要： A method of segmenting a digitized image includes marking a subset of pixels in an image, defining edge conductances between each pair of adjacent pixels in the image based on the intensity difference of each said pixel pair, associating a probability potential with each unmarked pixel, and using a multigrid method to solve for the probability potentials for each unmarked pixel, wherein a restriction operator from the image grid to a coarse grid is calculated from a conductance-weighted average of the conductances on the image grid, the coarse grid conductances are calculated from the image grid conductances using a Δ-Y conversion, and the multigrid prolongation operator is calculated using a conductance-weighted interpolation of the coarse grid conductances.