专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

WO2007044508A2 SYSTEM AND METHOD FOR WHOLE BODY LANDMARK DETECTION, SEGMENTATION AND CHANGE QUANTIFICATION IN DIGITAL IMAGES 审中-公开
标题翻译：用于数字图像中整体地标检测，分割和改变量化的系统和方法
公开(公告)号：WO2007044508A2
公开(公告)日：2007-04-19
申请号：PCT/US2006/039109
申请日：2006-10-05
申请人： SIEMENS MEDICAL SOLUTIONS USA, INC. , HUANG, Xiaolei , ZHOU, Xiang , JEREBKO, Anna , KRISHNAN, Arun , GUAN, Haiying , KUBOTA, Toshiro , POTESIL, Vaclav
发明人： HUANG, Xiaolei , ZHOU, Xiang , JEREBKO, Anna , KRISHNAN, Arun , GUAN, Haiying , KUBOTA, Toshiro , POTESIL, Vaclav
IPC分类号： G06T7/00
CPC分类号： G06T7/174 , G06T7/155 , G06T7/33 , G06T7/38 , G06T2207/10072 , G06T2207/20016 , G06T2207/20081 , G06T2207/20164 , G06T2207/30004 , G06T2207/30204
摘要： A method for segmenting digitized images includes providing (11) a training set comprising a plurality of digitized whole-body images, providing labels (12) on anatomical landmarks in each image of said training set, aligning (13) each said training set image, generating (14) positive and negative training examples for each landmark by cropping the aligned training volumes into one or more cropping windows of different spatial scales, and using said positive and negative examples to train (15) a detector for each landmark at one or more spatial scales ranging from a coarse resolution to a fine resolution, wherein the spatial relationship between a cropping windows of a coarse resolution detector and a fine resolution detector is recorded.
摘要翻译：用于分割数字化图像的方法包括提供（11）包括多个数字化全身图像的训练集，在所述训练集的每个图像中的解剖标志上提供标签（12），对齐（ 13）每个所述训练集图像，通过将所述对齐的训练体裁剪成不同空间尺度的一个或多个裁剪窗口来生成（14）每个地标的正面和负面训练示例，并且使用所述正面和反面示例来训练（15）检测器，用于从粗分辨率到高分辨率的一个或多个空间尺度范围内的每个界标，其中记录粗分辨率检测器的裁剪窗口和精细分辨率检测器之间的空间关系。

2. 发明申请

WO2009045470A1 SYSTEM AND METHOD FOR ROBUST SEGMENTATION OF PULMONARY NODULES OF VARIOUS DENSITIES 审中-公开
标题翻译：不同密度脉冲分布的系统和方法
公开(公告)号：WO2009045470A1
公开(公告)日：2009-04-09
申请号：PCT/US2008/011410
申请日：2008-10-02
申请人： SIEMENS MEDICAL SOLUTIONS USA, INC. , KUBOTA, Toshiro , JEREBKO, Anna , SALGANICOFF, Marcos
发明人： KUBOTA, Toshiro , JEREBKO, Anna , SALGANICOFF, Marcos
IPC分类号： G06T7/00
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 (51) a first distance map of each point of the object of interest, determining (53) a seed point from the first distance map, starting from the seed point, growing (54) a first region by adding successive adjacent layers of points until a background point is reached, and partitioning (57, 58) 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（51）感兴趣对象的每个点的第一距离图，确定（53）来自第一距离图，从种子点开始，通过添加连续相邻的点直到达到背景点来生长（54）第一区域，并且将第一区域分割成结节区域和非结节地区。

3. 发明申请

WO2006110398A2 ESTIMATION OF SOLITARY PULMONARY NODULE DIAMETERS WITH A HYBRID SEGMENTATION APPROACH 审中-公开
标题翻译：用混合分段方法估计复合脉冲直径
公开(公告)号：WO2006110398A2
公开(公告)日：2006-10-19
申请号：PCT/US2006/012499
申请日：2006-04-05
申请人： SIEMENS MEDICAL SOLUTIONS USA, INC. , KUBOTA, Toshiro , OKADA, Kazunori
发明人： KUBOTA, Toshiro , OKADA, Kazunori
IPC分类号： G06T7/60 , A61B5/00
CPC分类号： G06K9/44 , G06K2209/053 , G06T7/0012 , G06T7/12 , G06T7/149 , G06T7/62 , G06T2207/10081 , G06T2207/20116 , G06T2207/30064 , Y10S378/901
摘要： A method for estimating a diameter of an object of interest, includes extracting a sub-volume of voxels around a marker identifying a location of the object of interest (101) , and determining a segmentation result identifying an edge of the object of interest by a reactive-diffusion method (109) . The method further includes performing a boundary check on the segmentation result to determine whether the object of interest is solitary (110) , estimating a diameter of the object of interest from the segmentation result upon determining the object of interest to be solitary (108) , and extracting the object of interest by performing ellipsoid fit on the sub-volume (111) and estimating a diameter of the object of interest upon determining the object of interest to be non-solitary (108) .
摘要翻译：一种用于估计感兴趣对象的直径的方法，包括提取标识感兴趣对象的位置的标记周围的体素的子体积（101），以及确定识别感兴趣对象的边缘的分割结果反应扩散法（109）。该方法还包括对分割结果执行边界检查以确定感兴趣对象是否是孤立的（110），在确定感兴趣的对象是单独的（108）时，从分割结果估计感兴趣对象的直径，以及通过在所述子卷（111）上执行椭圆拟合来提取所述关注对象，并且在确定所述感兴趣对象不是孤立的时候估计所述对象的直径（108）。

4. 发明申请

WO2008085996A1 AUTOMATIC NODULE SEGMENTATION AND MEASUREMENTS 审中-公开
标题翻译：自动分配和测量
公开(公告)号：WO2008085996A1
公开(公告)日：2008-07-17
申请号：PCT/US2008/000300
申请日：2008-01-09
申请人： SIEMENS MEDICAL SOLUTIONS USA, INC. , KUBOTA, Toshiro
发明人： KUBOTA, Toshiro
IPC分类号： G06T5/00 , G06T7/60
CPC分类号： G06T7/0012 , G06K9/342 , G06K2209/05 , G06T7/11 , G06T7/194 , G06T7/62 , G06T2207/10081 , G06T2207/20101 , G06T2207/30064
摘要： A system for automatically estimating a measure of a nodule includes a memory device storing a dataset including image volume data including marked positions of the nodule (100) and instructions for estimating the measure and a processor receiving the dataset and executing the instructions to perform a method including, extracting a sub-volume from the dataset (101), determining a solid foreground of the sub-volume and a non-solid foreground of the sub-volume (102), determining a seed point corresponding to the nodule from the solid and non-solid foregrounds (103), selecting one of the seed point of the solid foreground or the seed point of the non-solid foreground (104), determining whether the selected seed point is solitary or non-solitary (105) and performing region growing for non-solitary selected seed point (106), determining a segmentation of the selected seed point, estimating the measure corresponding to the segmentation (107), and outputting the segmentation and an estimate of the measure of the nodule (108).
摘要翻译：一种用于自动估计结节的度量的系统包括：存储装置，其存储数据集，所述数据集包括包括所述结节（100）的标记位置的图像体积数据和用于估计所述测量的指令，以及接收所述数据集并执行所述指令以执行方法包括从所述数据集（101）提取子体积，确定所述子体积（102）的子体积的固体前景和所述子体积（102）的非固体前景，从所述实体确定对应于所述结节的种子点，以及非固体前景（103），选择固体前景的种子点或非固体前景的种子点之一（104），确定所选择的种子点是单独的还是非孤立的（105）并且执行区域针对非孤立选择的种子点（106）生长，确定所选种子点的分割，估计对应于分割（107）的度量，以及输出分割和估计的结节（108）的度量。

5. 发明申请

WO2007056495A1 SYSTEM AND METHOD FOR COMPUTER AIDED DETECTION VIA ASYMMETRIC CASCADE OF SPARSE LINEAR CLASSIFIERS 审中-公开
标题翻译：用于计算机辅助检测的系统和方法通过非线性分类器的不对称分类
公开(公告)号：WO2007056495A1
公开(公告)日：2007-05-18
申请号：PCT/US2006/043585
申请日：2006-11-08
申请人： SIEMENS MEDICAL SOLUTIONS USA, INC. , BI, Jinbo , PERIASWAMY, Senthil , OKADA, Kazunori , KUBOTA, Toshiro , FUNG, Glenn , SALGANICOFF, Marcos , RAO, R. Bharat
发明人： BI, Jinbo , PERIASWAMY, Senthil , OKADA, Kazunori , KUBOTA, Toshiro , FUNG, Glenn , SALGANICOFF, Marcos , RAO, R. Bharat
IPC分类号： G06K9/68 , G06K9/62
CPC分类号： G06K9/6256 , G06K9/6282
摘要： A method for computer aided detection of anatomical abnormalities in medical images includes providing a plurality of abnormality candidates (10) and features (11, 13, 15) of said abnormality candidates, and classifying said abnormality candidates as true positives or false positives using a hierarchical cascade of linear classifiers (12, 14, 16) of the form sign (w T x+ b ), wherein x is a feature vector, w is a weighting vector and b is a model parameter, wherein different weights are used to penalize false negatives and false positives, and wherein more complex features are used for each successive stage of said cascade of classifiers.
摘要翻译：一种用于计算机辅助检测医学图像中的解剖异常的方法，包括提供所述异常候选的多个异常候选（10）和特征（11,13,15），并且使用分层次分析将所述异常候选分类为真阳性或假阳性（x，x，x + b）的线性分类器（12,14,16）的级联，其中x是特征向量，w是加权向量，b是模型参数，其中使用不同的权重来惩罚假阴性和假阳性，并且其中对于分级器级联的每个连续阶段使用更复杂的特征。

6. 发明申请

WO2006110399A2 ESTIMATION OF SOLITARY PULMONARY NODULE DIAMETERS WITH REACTION-DIFFUSION SEGMENTATION 审中-公开
标题翻译：具有反应扩散分段的固体脉冲直径的估计
公开(公告)号：WO2006110399A2
公开(公告)日：2006-10-19
申请号：PCT/US2006/012501
申请日：2006-04-05
申请人： SIEMENS MEDICAL SOLUTIONS USA, INC. , KUBOTA, Toshiro
发明人： KUBOTA, Toshiro
IPC分类号： G06T7/60 , A61B5/00
CPC分类号： G06K9/34 , G06K9/38 , G06T7/12 , G06T7/149 , G06T7/62 , G06T2207/10081 , G06T2207/20116 , G06T2207/30064
摘要： A reactive-diffusion method for estimating a diameter of an object of interest includes providing a volume of interest including a plurality of voxels (101), initializing at least two volumes of the volume of interest (102), wherein each of the voxels has at least two values corresponding to the at least two volumes of the volume of interest, respectively, performing a diffusion operation and a reaction operation on the voxels to adjust the at least two values (109), comparing, for each voxel, the at least two values to a threshold to assign each voxel to one of the at least two volumes (106), wherein the assignment of the voxels is a segmentation result (107), and estimating a diameter of the object of interest from the segmentation result (108), wherein the object of interest is represented by at least one of the at least two volumes but less than all the volumes.
摘要翻译：用于估计感兴趣对象的直径的反应性扩散方法包括提供包括多个体素（101）的兴趣体积，初始化至少两个体积的感兴趣体积（102），其中每个体素具有分别对应于感兴趣体积的至少两个体积的至少两个值，对体素进行扩散操作和反应操作以调整至少两个值（109），对于每个体素，比较至少两个值到阈值，以将每个体素分配给所述至少两个体积（106）中的一个，其中所述体素的分配是分割结果（107），并且从分割结果（108）估计感兴趣对象的直径，，其中所述感兴趣对象由所述至少两个体积中的至少一个而不是所有体积表示。

7. 发明申请

WO2006110399A3 ESTIMATION OF SOLITARY PULMONARY NODULE DIAMETERS WITH REACTION-DIFFUSION SEGMENTATION 审中-公开
标题翻译：具有反应扩散分段的固体脉冲直径的估计
公开(公告)号：WO2006110399A3
公开(公告)日：2007-03-22
申请号：PCT/US2006012501
申请日：2006-04-05
申请人： SIEMENS MEDICAL SOLUTIONS , KUBOTA TOSHIRO
发明人： KUBOTA TOSHIRO
IPC分类号： G06T7/60 , G06T5/00
CPC分类号： G06K9/34 , G06K9/38 , G06T7/12 , G06T7/149 , G06T7/62 , G06T2207/10081 , G06T2207/20116 , G06T2207/30064
摘要： A reactive-diffusion method for estimating a diameter of an object of interest includes providing a volume of interest including a plurality of voxels (101), initializing at least two volumes of the volume of interest (102), wherein each of the voxels has at least two values corresponding to the at least two volumes of the volume of interest, respectively, performing a diffusion operation and a reaction operation on the voxels to adjust the at least two values (109), comparing, for each voxel, the at least two values to a threshold to assign each voxel to one of the at least two volumes (106), wherein the assignment of the voxels is a segmentation result (107), and estimating a diameter of the object of interest from the segmentation result (108), wherein the object of interest is represented by at least one of the at least two volumes but less than all the volumes.
摘要翻译：用于估计感兴趣对象的直径的反应性扩散方法包括提供包括多个体素（101）的兴趣体积，初始化至少两个体积的感兴趣体积（102），其中每个体素具有分别对应于感兴趣体积的至少两个体积的至少两个值，对体素进行扩散操作和反应操作以调整至少两个值（109），对于每个体素，比较至少两个值到阈值，以将每个体素分配给所述至少两个体积（106）中的一个，其中所述体素的分配是分割结果（107），并且从分割结果（108）估计感兴趣对象的直径，，其中所述感兴趣对象由所述至少两个体积中的至少一个而不是所有体积表示。

8. 发明申请

WO2007044508A3 SYSTEM AND METHOD FOR WHOLE BODY LANDMARK DETECTION, SEGMENTATION AND CHANGE QUANTIFICATION IN DIGITAL IMAGES 审中-公开
标题翻译：系统和方法，用于数字图像全身体检测，分段和更改量化
公开(公告)号：WO2007044508A3
公开(公告)日：2007-08-02
申请号：PCT/US2006039109
申请日：2006-10-05
申请人： SIEMENS MEDICAL SOLUTIONS , HUANG XIAOLEI , ZHOU XIANG , JEREBKO ANNA , KRISHNAN ARUN , GUAN HAIYING , KUBOTA TOSHIRO , POTESIL VACLAV
发明人： HUANG XIAOLEI , ZHOU XIANG , JEREBKO ANNA , KRISHNAN ARUN , GUAN HAIYING , KUBOTA TOSHIRO , POTESIL VACLAV
IPC分类号： G06T7/00
CPC分类号： G06T7/174 , G06T7/155 , G06T7/33 , G06T7/38 , G06T2207/10072 , G06T2207/20016 , G06T2207/20081 , G06T2207/20164 , G06T2207/30004 , G06T2207/30204
摘要： A method for segmenting digitized images includes providing (11) a training set comprising a plurality of digitized whole-body images, providing labels (12) on anatomical landmarks in each image of said training set, aligning (13) each said training set image, generating (14) positive and negative training examples for each landmark by cropping the aligned training volumes into one or more cropping windows of different spatial scales, and using said positive and negative examples to train (15) a detector for each landmark at one or more spatial scales ranging from a coarse resolution to a fine resolution, wherein the spatial relationship between a cropping windows of a coarse resolution detector and a fine resolution detector is recorded.
摘要翻译：用于分割数字化图像的方法包括提供（11）包括多个数字化全身图像的训练集合，在所述训练集合的每个图像中的解剖学标志上提供标签（12），对准（13）每个所述训练集合图像，通过将对准的训练量裁剪成不同空间尺度的一个或多个裁剪窗口来生成（14）每个地标的正和负训练示例，并且使用所述正和负的示例来训练（15）每个地标的检测器在一个或多个记录从粗分辨率到精细分辨率的空间刻度，其中记录粗分辨率检测器的裁剪窗与精细分辨率检测器之间的空间关系。

9. 发明申请

WO2006110398A3 ESTIMATION OF SOLITARY PULMONARY NODULE DIAMETERS WITH A HYBRID SEGMENTATION APPROACH 审中-公开
标题翻译：用混合分段方法估计固体脉冲直径
公开(公告)号：WO2006110398A3
公开(公告)日：2007-03-22
申请号：PCT/US2006012499
申请日：2006-04-05
申请人： SIEMENS MEDICAL SOLUTIONS , KUBOTA TOSHIRO , OKADA KAZUNORI
发明人： KUBOTA TOSHIRO , OKADA KAZUNORI
IPC分类号： G06T7/60 , A61B5/00 , G06T5/00
CPC分类号： G06K9/44 , G06K2209/053 , G06T7/0012 , G06T7/12 , G06T7/149 , G06T7/62 , G06T2207/10081 , G06T2207/20116 , G06T2207/30064 , Y10S378/901
摘要： A method for estimating a diameter of an object of interest, includes extracting a sub-volume of voxels around a marker identifying a location of the object of interest (101) , and determining a segmentation result identifying an edge of the object of interest by a reactive-diffusion method (109) . The method further includes performing a boundary check on the segmentation result to determine whether the object of interest is solitary (110) , estimating a diameter of the object of interest from the segmentation result upon determining the object of interest to be solitary (108) , and extracting the object of interest by performing ellipsoid fit on the sub-volume (111) and estimating a diameter of the object of interest upon determining the object of interest to be non-solitary (108) .
摘要翻译：一种用于估计感兴趣对象的直径的方法，包括提取标识感兴趣对象的位置的标记周围的体素的子体积（101），以及确定识别感兴趣对象的边缘的分割结果反应扩散法（109）。该方法还包括对分割结果执行边界检查以确定感兴趣对象是否是孤立的（110），在确定感兴趣对象是单独的（108）时，从分割结果估计感兴趣对象的直径，以及通过在所述子卷（111）上执行椭圆拟合来提取所述关注对象，并且在确定所述感兴趣对象不是孤立的时候估计所述对象的直径（108）。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式