专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

91. 发明申请

WO2007008289A2 GUIDANCE METHOD BASED ON 3D-2D POSE ESTIMATION AND 3D-CT REGISTRATION WITH APPLICATION TO LIVE BRONCHOSCOPY 审中-公开
标题翻译：基于三维2D位置估计和3D-CT注册的指导方法，适用于实时布隆方程
公开(公告)号：WO2007008289A2
公开(公告)日：2007-01-18
申请号：PCT/US2006/019926
申请日：2006-05-23
申请人： THE PENN STATE RESEARCH FOUNDATION , HIGGINS, William, E. , MERRITT, Scott, A. , RAI, Lav
发明人： HIGGINS, William, E. , MERRITT, Scott, A. , RAI, Lav
IPC分类号： A61B5/05
CPC分类号： A61B5/06 , A61B1/00009 , A61B5/415 , A61B5/418 , A61B6/032 , A61B6/466 , A61B6/50 , A61B34/10 , A61B34/20 , A61B90/36 , A61B90/361 , A61B2034/105 , A61B2034/2065 , A61B2090/364 , A61B2090/3762 , G06K9/00208 , G06K9/00214 , G06K9/6206
摘要： A method provides guidance to the physician during a live bronchoscopy or other endoscopic procedures. The 3D motion of the bronchoscope is estimated using a fast coarse tracking step followed by a fine registration step. The tracking is based on finding a set of corresponding feature points across a plurality of consecutive bronchoscopic video frames, then estimating for the new pose of the bronchoscope. In the preferred embodiment the pose estimation is based on linearization of the rotation matrix. By giving a set of corresponding points across the current bronchoscopic video image, and the CT-based virtual image as an input, the same method can also be used for manual registration. The fine registration step is preferably a gradient-based Gauss-Newton method that maximizes the correlation between the bronchoscopic video image and the CT-based virtual image. The continuous guidance is provided by estimating the 3D motion of the bronchoscope in a loop. Since depth-map information is available, tracking can be done by solving a 3D-2D pose estimation problem. A 3D-2D pose estimation problem is more constrained than a 2D-2D pose estimation problem and does not suffer from the limitations associated with computing an essential matrix. The use of correlation-based -cost, instead of mutual information as a registration cost^ makes it simpler to use gradient-based methods for registration.
摘要翻译：一种方法在活支气管镜检查或其他内窥镜手术过程中向医生提供指导。支气管镜的3D运动使用快速粗跟踪步骤，接着是精细配准步骤来估计。跟踪是基于在多个连续支气管镜视频帧之间找到一组对应的特征点，然后估计支气管镜的新姿势。在优选实施例中，姿态估计基于旋转矩阵的线性化。通过在目前的支气管镜视频图像上提供一组对应的点，并且基于CT的虚像作为输入，同样的方法也可以用于手动注册。精细登记步骤优选地是使支气管镜视频图像和基于CT的虚拟图像之间的相关性最大化的基于梯度的高斯 - 牛顿方法。通过在循环中估计支气管镜的3D运动来提供连续的指导。由于深度图信息可用，可以通过解决3D-2D姿态估计问题来进行跟踪。 3D-2D姿态估计问题比2D-2D姿态估计问题更受约束，并且不受与计算基本矩阵相关联的限制的影响。使用基于相关性的成本代替互信息作为注册成本，使得使用基于梯度的方法进行注册变得更为简单。

92. 发明申请

WO2007001884A2 DIRECT METHOD FOR MODELING NON-RIGID MOTION WITH THIN FILM PLATE SPLINE TRANSFORMATION 审中-公开
标题翻译：用薄膜平面线变换建立非刚性运动的直接方法
公开(公告)号：WO2007001884A2
公开(公告)日：2007-01-04
申请号：PCT/US2006/023350
申请日：2006-06-15
申请人： HONDA MOTOR CO., LTD. , LIM, Jongwoo , YANG, Ming-Hsuan
发明人： LIM, Jongwoo , YANG, Ming-Hsuan
IPC分类号： G06K9/36 , G06K9/00
CPC分类号： G06T7/20 , G06K9/6206
摘要： A system and a method model the motion of a non-rigid object using a thin plate spline (TPS) transform. A first image of a video sequence is received, and a region of interest, referred to as a template, is chosen manually or automatically. A set of arbitrarily-chosen fixed reference points is positioned on the template. A target image of the video sequence is chosen for motion estimation relative to the template. A set of pixels in the target image corresponding to the pixels of the template is determined, and this set of pixels is back- warped to match the template using a thin-plate-spline-based technique. The error between the template and the back-warped image is determined and iteratively minimized using a gradient descent technique. The TPS parameters can then be used to estimate the relative motion between the template and the corresponding region of the target image. According to one embodiment, a stiff-to-flexible approach mitigates instability that can arise when reference points lie in textureless regions, or when the initial TPS parameters are not close to the desired ones. The value of a regularization parameter is varied from a larger to a smaller value, varying the nature of the warp from stiff to flexible, so as to progressively emphasize local non-rigid deformations.
摘要翻译：使用薄板样条（TPS）变换来建模非刚性物体的运动的系统和方法。接收视频序列的第一图像，并且手动地或自动地选择被称为模板的感兴趣区域。一组任意选择的固定参考点位于模板上。选择视频序列的目标图像用于相对于模板的运动估计。确定与模板的像素对应的目标图像中的一组像素，并且使用基于薄板样条的技术将该组像素反向弯曲以匹配模板。使用梯度下降技术确定模板和反翘曲图像之间的误差并迭代地最小化。然后可以使用TPS参数来估计模板和目标图像的对应区域之间的相对运动。根据一个实施例，柔性到柔性的方法减轻了当参考点位于无纹理区域时或者当初始TPS参数不接近期望的区域时可能出现的不稳定性。正则化参数的值从较大值变化到较小值，将翘曲的性质从刚性变化到柔性，从而逐渐强调局部非刚性变形。

93. 发明申请

WO2006044242A2 METHOD FOR DETECTING POLYPS IN A THREE DIMENSIONAL IMAGE VOLUME 审中-公开
标题翻译：在三维图像体积中检测多边形的方法
公开(公告)号：WO2006044242A2
公开(公告)日：2006-04-27
申请号：PCT/US2005036123
申请日：2005-10-07
申请人： SIEMENS CORP RES INC , SIEMENS MEDICAL SOLUTIONS , TU ZHUOWEN , ZHOU XIANG SEAN , BARBU ADRIAN , BOGONI LUCA , COMANICIU DORIN
发明人： TU ZHUOWEN , ZHOU XIANG SEAN , BARBU ADRIAN , BOGONI LUCA , COMANICIU DORIN
IPC分类号： G06K9/62
CPC分类号： G06K9/4614 , G06K9/6206 , G06K9/6214 , G06K9/6257 , G06K2209/053 , G06T7/0012 , G06T2207/10072 , G06T2207/30032
摘要： A method for detecting target objects in a three dimensional (3D) image volume of an anatomical structure is disclosed. A set of candidate locations in the image volume are obtained. For each candidate location, sub-volumes of at least two different scales are cropped out. Each sub-volume comprises a plurality of voxels. For each of the sub-volumes, each sub-volume is rotated in at least two different orientations. A shape classifier is applied to each sub-volume. If the voxels in the sub-volume pass the shape classifier, a gradient direction is computed for the voxels. If the gradient direction for the voxels is one of a predefined orientation, a probability classifier is applied to the voxels. A probability measure computed by the probability classifier as a confidence measure is used for the sub-volume. If the confidence measure is above a predetermined threshold value, the sub-volume is determined to contain the target object
摘要翻译：公开了一种用于检测解剖结构的三维（3D）图像体积中的目标对象的方法。获得图像体积中的一组候选位置。对于每个候选位置，至少有两个不同比例的子卷被裁剪掉。每个子体积包括多个体素。对于每个子体积，每个子体积至少在两个不同的方向旋转。形状分类器应用于每个子卷。如果子体积中的体素通过形状分类器，则为体素计算梯度方向。如果体素的梯度方向是预定义方向之一，则将概率分类器应用于体素。由概率分类器计算的概率度量作为置信度量度用于子量。如果置信度量高于预定阈值，则确定子量包含目标对象

94. 发明申请

WO2005106793A2 A METHOD, A COMPUTER PROGRAM, AN APPARATUS, AN IMAGE ANALYSIS SYSTEM AND AN IMAGING SYSTEM FOR AN OBJECT MAPPING IN A MULTI-DIMENSIONAL DATASET 审中-公开
标题翻译：方法，计算机程序，设备，图像分析系统和用于多维数据库中的对象映射的成像系统
公开(公告)号：WO2005106793A2
公开(公告)日：2005-11-10
申请号：PCT/IB2005/051298
申请日：2005-04-21
申请人： KONINKLIJKE PHILIPS ELECTRONICS N.V. , HABETS, Raymond, J., E. , SUDITU, Nicolae , LOBREGT, Steven , GERRITSEN, Frans, A.
发明人： HABETS, Raymond, J., E. , SUDITU, Nicolae , LOBREGT, Steven , GERRITSEN, Frans, A.
IPC分类号： G06T7/00
CPC分类号： G06K9/6206 , G06T7/0012 , G06T7/12 , G06T7/149 , G06T7/60 , G06T2207/10081 , G06T2207/20128 , G06T2207/30008
摘要： The apparatus (40) arranged for enabling an object mapping in a multidimensional dataset has an input (42) for receiving the multi-dimensional dataset in any suitable form. The core of the apparatus is formed by a processor (44), such as a conventional microprocessor or signal processor, a background storage (48) (typically based on a hard disk) and working memory (46) (typically based on RAM). The background storage (48) can be used for storing the dataset (or parts of it) when not being processed, and for storing operations of the graphic relational application macro and models (when not being executed by the processor). The main memory (46) typically holds the (parts of) the dataset being processed and the instructions of the graphic relational application macro and the models used for processing those parts of the dataset. The apparatus (40) according to the invention comprises computation means (45) arranged to define a set of geometric relations between a set of geometric templates using a geometrical relational application framework macro and means (47) for associating the multi-dimensional graphic objects with the geometric templates. Preferably, means (45) and (47) are operable by a computer program (43), preferably stored in memory (48). An output (49) is used for outputting the result of the mapping. Preferably, the output comprises a result of the associating of the multi-dimensional graphic objects with the geometric templates inter-related by the graphic relational application macro. The invention further relates to a method, a computer program, an image analysis system and an imaging system for an object mapping in a multi-dimensional dataset.
摘要翻译：布置成使多维数据集中的对象映射能够实现的设备（40）具有用于以任何合适的形式接收多维数据集的输入（42）。该装置的核心由诸如常规微处理器或信号处理器的处理器（44），后台存储器（通常基于硬盘）和工作存储器（46）（通常基于RAM）形成。后台存储（48）可以用于在不处理时存储数据集（或其部分），并且用于存储图形关系应用程序宏和模型的操作（当处理器未被执行时）。主存储器（46）通常保存正在处理的数据集的（部分）和图形关系应用宏的指令以及用于处理数据集的这些部分的模型。根据本发明的装置（40）包括计算装置（45），其被布置为使用几何关系应用框架宏来定义一组几何模板之间的几何关系的集合;以及用于将多维图形对象与几何模板。优选地，装置（45）和（47）可由计算机程序（43）操作，优选地存储在存储器（48）中。输出（49）用于输出映射结果。优选地，输出包括将多维图形对象与由图形关系应用宏相互关联的几何模板相关联的结果。本发明还涉及一种用于多维数据集中的对象映射的方法，计算机程序，图像分析系统和成像系统。

95. 发明申请

WO2005052860A3 SYSTEM AND METHOD FOR DETECTING AND MATCHING ANATOMICAL STRUCTURES USING APPEARANCE AND SHAPE 审中-公开
标题翻译：使用外观和形状检测和匹配解剖结构的系统和方法
公开(公告)号：WO2005052860A3
公开(公告)日：2005-09-22
申请号：PCT/US2004038837
申请日：2004-11-19
申请人： SIEMENS CORP RES INC , SIEMENS MEDICAL SOLUTIONS , ZHOU XIANG SEAN , GEORGESCU BOGDAN , COMANICIU DORIN , RAO R BHARAT , GUPTA ALOK
发明人： ZHOU XIANG SEAN , GEORGESCU BOGDAN , COMANICIU DORIN , RAO R BHARAT , GUPTA ALOK
IPC分类号： G06K9/62 , G06K9/64 , G06T7/00 , G06F19/00
CPC分类号： G06K9/6206 , G06K9/6256 , G06T7/12 , G06T7/149 , G06T7/251 , G06T2207/10132 , G06T2207/30048
摘要： A detection framework that matches anatomical structures using appearance and shape is disclosed. A training set of images are used in which object shapes or structures are annotated in the images. A second training set of images represents negative examples for such shapes and structures, i.e., images containing no such objects or structures. A classification algorithm trained on the training sets is used to detect a structure at its location. The structure is matched to a counterpart in the training set that can provide details about the structure's shape and appearance
摘要翻译：公开了一种使用外观和形状匹配解剖结构的检测框架。使用图像的训练集合，其中对图像中的对象形状或结构进行注释。图像的第二训练集表示这种形状和结构的负面例子，即不包含这样的对象或结构的图像。在训练集上训练的分类算法用于检测其位置处的结构。该结构与训练集中的对应部分相匹配，可以提供关于结构形状和外观的详细信息

96. 发明申请

WO2005017818A1 PROCEDE DE MESURE DE PROXIMITE DE DEUX CONTOURS ET SYSTEME D'IDENTIFICATION AUTOMATIQUE DE CIBLES 审中-公开
标题翻译：用于测量两个轮廓近似的方法和用于自动识别目标的系统
公开(公告)号：WO2005017818A1
公开(公告)日：2005-02-24
申请号：PCT/EP2004/051476
申请日：2004-07-13
申请人： THALES , RUCH, Olivier
发明人： RUCH, Olivier
IPC分类号： G06K9/64
CPC分类号： G06K9/3241 , G06K9/6204 , G06K9/6206
摘要： Un procédé de mesure de proximité d'un deuxième contour (CM) à un premier contour (CI), comprend pour chaque point du premier contour, une étape d'association avec un point du deuxième contour déterminé comme le plus proche, et une étape d'appariement de chaque point (M 15 ) du deuxième contour avec un ou zéro point du premier contour, par détermination du point du premier contour le plus proche (I 24 ) parmi l'ensemble des points (I 24 , I 28 , I 29 ) du premier contour associés au dit point du deuxième contour. Un procédé d'identification automatique de cibles applique ce processus de mesure de proximité pour déterminer la mesure de proximité d'un contour modèle, appliqué comme deuxième contour, à un contour image, appliqué comme premier contour.
摘要翻译：本发明涉及一种用于测量第二轮廓（CM）与第一轮廓（CI）的接近度的方法，包括将第一轮廓的每个点与被确定为最接近的轮廓的第二轮廓的点相关联的步骤，以及通过确定在该组点（I24，I28，I29）中最接近的（I24）的第一轮廓的点，将第二轮廓的每个点（M15）与一个或多个第一轮廓的点配对）与第二轮廓的所述点相关联的第一轮廓。用于自动识别目标的方法应用所述接近度测量方法以确定应用为作为第一轮廓的图像轮廓的作为第二轮廓的模型轮廓的接近程度。

97. 发明申请

WO2004084124A1 SYSTEM AND METHOD OF POINT MATCHING MEASURED POSITIONS TO TEMPLATE POSITIONS 审中-公开
标题翻译：点匹配测量位置的模糊位置的系统和方法
公开(公告)号：WO2004084124A1
公开(公告)日：2004-09-30
申请号：PCT/US2004/007812
申请日：2004-03-12
申请人： APPLIED PRECISION, LLC , KRAFT, Raymond, H.
发明人： KRAFT, Raymond, H.
IPC分类号： G06K9/64
CPC分类号： G06K9/6206 , G06K9/6211
摘要： A system and method of point matching measured positions to template, or reference, positions for various applications may generally comprise creating force field vectors and moments operative to perturb measured point locations into alignment with template point locations. Progressive reduction of the force radius may produce results that match very well for points that are highly correlated with the template pattern.
摘要翻译：将测量位置与模板或参考位置的点匹配的点匹配的系统和方法通常可以包括创建力场矢量和力矩，以将扰动测量的点位置与模板点位置对准。力半径的逐渐减小可能产生与模板图案高度相关的点非常好匹配的结果。

98. 发明申请

WO2004032337A2 METHOD OF DETECTING, INTERPRETING, RECOGNIZING, IDENTIFYING AND COMPARING N-DIMENSIONAL SHAPES, PARTIAL SHAPES, EMBEDDED SHAPES AND SHAPE COLLAGES USING MULTIDIMENSIONAL ATTRACTOR TOKENS 审中-公开
标题翻译：检测，解释，识别，识别和比较N维形状，部分形状，嵌入形状和使用多维吸引器功能的形状组合的方法
公开(公告)号：WO2004032337A2
公开(公告)日：2004-04-15
申请号：PCT/US2003/030454
申请日：2003-09-26
申请人： OMNIGON TECHNOLOGIES LTD. , HAPPEL, Kenneth, M.
发明人： HAPPEL, Kenneth, M.
IPC分类号： H04B
CPC分类号： G06K9/6204 , G06K9/481 , G06K9/62 , G06K9/6206 , G06K9/6885
摘要： A method of detecting, interpreting, recognizing, identifying and comparing N-dimensional shapes, partial shapes, embedded shapes and shape collages is disclosed. One embodiment of the invention allows for the characterization of shapes as sequences of unit vector descriptions, attributes of unit vector descriptions, shape segments, and shape segment collages whereby the detection, interpretation, recognition, identification, comparison and analysis of one- to n-dimensional shapes in one- to n-dimensional spaces can be accomplished using multidimensional attractor tokens. These attractor processes map the sequence from its original sequence representation space (OSRS) into a hierarchical multidimensional attractor space (HMAS). The HMAS can be configured to represent equivalent symbol distributions within two symbol sequences or perform exact symbol sequence matching. The mapping process results in each sequence being drawn to an attractor in the HMAS. Each attractor within the HMAS forms a unique token for a group of sequences with no overlap between the sequence groups represented by different attractors. The size of the sequence groups represented by a given attractor can be reduced from approximately half of all possible sequences to a much smaller subset of possible sequences. The mapping process is repeated for a given sequence so that tokens are created for the whole sequence and a series of subsequences created by repeatedly removing a symbol from the one end of sequence and then repeating the process from the other end. The resulting string of tokens represents the exact identity of the whole sequence and all its subsequences ordered from each end.
摘要翻译：公开了一种检测，解释，识别，识别和比较N维形状，部分形状，嵌入形状和形状拼贴的方法。本发明的一个实施例允许将形状表征为单位矢量描述的序列，单位矢量描述的属性，形状段和形状段拼贴，由此一对一的检测，解释，识别，识别，比较和分析，可以使用多维吸引子令牌来实现一维至二维空间中的三维形状。这些吸引器过程将序列从其原始序列表示空间（OSRS）映射到分层多维吸引子空间（HMAS）。可以将HMAS配置为表示两个符号序列内的等效符号分布或执行精确的符号序列匹配。映射过程导致每个序列被绘制到HMAS中的吸引子。 HMAS中的每个吸引子形成用于由不同吸引子表示的序列组之间没有重叠的一组序列的唯一标记。由给定吸引子表示的序列组的大小可以从所有可能序列的大约一半减少到可能序列的小得多的子集。对于给定的序列重复映射过程，以便为整个序列创建令牌，并通过从序列的一端重复地移除符号，然后从另一端重复该过程而创建一系列子序列。所得到的令牌字符串表示整个序列的确切身份以及从每一端排序的所有子序列。

99. 发明申请

WO00010119A1 METHOD FOR RECOGNIZING OBJECTS IN DIGITIZED IMAGES 审中-公开
标题翻译：用于数字化照片的认识 - 物体
公开(公告)号：WO00010119A1
公开(公告)日：2000-02-24
申请号：PCT/EP1999/005946
申请日：1999-08-13
IPC分类号： G06K9/00 , G06K9/64 , G06K9/80
CPC分类号： G06K9/6206 , G06K9/00288 , G06K9/00355 , G06K9/469 , G06K9/80
摘要： The inventive method comprises the following steps: (a) providing at least one reference graph comprised of reference images, whereby the or each reference graph provides a net-like structure which is defined each time in that reference image nodes, said nodes being connected to one another by links in a predetermined manner, are appointed to certain reference image data, and of jets, whereby one jet is assigned to each node and each jet comprises at least one partial jet. Said partial jet is determined by convolutions of at least one class of filter functions with different quantities and/or orientations by means of the reference image data, or is determined by convolutions of at least one class of filter functions with different quantities and/or orientations by means of color-segmented reference image data, or is determined by color information with regard to the reference image data, or is determined by means of texture descriptions of the corresponding reference image, or is determined by means of movement vectors at the appointed node; (b) determining an optimal image graph from the digitized image data for each reference graph, whereby the optimal image graph for an appointed reference graph represents the optimal adaptation to the same, and; (c) assigning the or each structure to the reference image corresponding to the reference graph for which the graph comparison function is optimal with regard to the optimal image graph that is determined for said reference graph.
摘要翻译：该方法包括：（a）提供的参考图像的至少一个参考图形，其中，所述或每个参考图中，网状结构，其在由以预定方式链路互连该特定的参考图像数据的节点分别定义，要分配的步骤，和喷气机其中每个节点被分配一个Jet和每个喷嘴包括Teiljet至少，通过折叠至少一个类别的具有不同尺寸和/或取向与参考图像数据滤波器的功能，或通过折叠至少一类的过滤器功能的具有不同尺寸和/或取向颜色分段的参考图像数据，或通过在特定节点上的参考图像数据或纹理描述对应的参照图像的，或由运动矢量的颜色信息来确定，（b）确定从数字化的胆红素最优的图像图形 -dates对于每个参考图，它用于说明最优适应这一点，和（c）特定的参考图中的最佳的图像图形分配所述或每个结构以对应于所述图形比较功能的参考图形相对于该既定用于其最佳图像图形中的参考图像是最佳的。

100. 发明申请

WO9905639A9 WAVELET SNAKE TECHNIQUE FOR DISCRIMINATION OF NODULES AND FALSE POSITIVES IN DIGITAL RADIOGRAPHS 审中-公开
标题翻译：用于歧视数字无线电广播中的节目和虚拟角色的小波收音机技术
公开(公告)号：WO9905639A9
公开(公告)日：1999-04-22
申请号：PCT/US9815278
申请日：1998-07-24
申请人： ARCH DEV CORP
发明人： YOSHIDA HIROYUKI , KATUSURAGAWA SHIGEHIKO , AMIT YALI , DOI KUNIO
IPC分类号： G06K9/64 , G06T7/00 , G06K9/00
CPC分类号： G06K9/6206 , G06T7/0012
摘要： A method and apparatus for discrimination of nodules and false positive in digital chest radiographs, using a wavelet snake technique (1802; 1804; 1806; 1808). The wavelet snake is a deformable contour designed to identify the boundary of a relatively round object (1900). The shape of the snake is determined by a set of wavelet coefficient in a certain range of scales. Portions of the boundary of a nodule are first extracted using a multiscale edge representation. The multiscale edge are then fitted (2000; 1814) by a gradient descent procedure which deforms the shape of a wavelet snake by changing its wavelet coefficients. The degree of overlap between the fitted snake and the multiscale edges is calculated and used as a fit quality indicator for discrimination of nodules and false detection (1816; 1818; 1820).
摘要翻译：使用小波蛇技术（1802; 1804; 1806; 1808）在数字胸片中鉴别结节和假阳性的方法和装置。小波蛇是一种可变形轮廓，用于识别相对圆形物体的边界（1900）。蛇的形状由一定范围的小波系数确定。首先使用多尺度边缘表示提取结节边界的部分。然后通过梯度下降程序将多尺度边缘拟合（2000; 1814），其通过改变其小波系数来变形小波蛇的形状。计算拟合蛇和多尺度边缘之间的重叠程度，并将其用作辨别结节和错误检测的适合质量指标（1816; 1818; 1820）。

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