公开(公告)号：US20080075345A1

公开(公告)日：2008-03-27

申请号：US11857801

申请日：2007-09-19

申请人： Gozde Unal ,  Atilla Kiraly ,  Gregory Slabaugh ,  Carol Novak ,  Tong Fang

发明人： Gozde Unal ,  Atilla Kiraly ,  Gregory Slabaugh ,  Carol Novak ,  Tong Fang

IPC分类号： G06K9/62

CPC分类号： G06T7/149 ,  G06T7/12 ,  G06T2207/10081 ,  G06T2207/20116 ,  G06T2207/30096

摘要： A method and system for lymph node segmentation in computed tomography (CT) images is disclosed. A location of a lymph node in a CT image slice is received. Intensity constraints are determined based on a histogram analysis of the CT image slice, and a spatial analysis of the intensity constrained CT image slice is performed using edge detection. An initial contour is estimated based on the lymph node location and the spatial analysis. The lymph node is then segmented by propagating the initial contour using an evolving elliptical model to define the lymph node boundaries.

摘要翻译： 公开了一种计算机断层扫描（CT）图像中淋巴结分割的方法和系统。 接收CT图像切片中淋巴结的位置。 强度约束基于CT图像切片的直方图分析确定，并且使用边缘检测进行强度约束CT图像切片的空间分析。 基于淋巴结位置和空间分析估计初始轮廓。 然后通过使用演进的椭圆模型传播初始轮廓来分割淋巴结以限定淋巴结边界。

公开(公告)号：US20070167710A1

公开(公告)日：2007-07-19

申请号：US11555806

申请日：2006-11-02

申请人： Gozde Unal ,  Yan Yang ,  Gregory Slabaugh ,  Tong Fang

发明人： Gozde Unal ,  Yan Yang ,  Gregory Slabaugh ,  Tong Fang

IPC分类号： A61B5/05

CPC分类号： A61B5/6852 ,  A61B5/0066 ,  A61B5/0086

摘要： A method and apparatus for automatically detecting stent struts in an image is disclosed whereby the inner boundary, or lumen, of an artery wall is first detected automatically and intensity profiles along rays in the image are determined. In one embodiment, detection of the lumen boundary may be accomplished, for example, by evolving a geometric shape, such as an ellipse, using a region-based algorithm technique, a geodesic boundary-based algorithm technique or a combination of the two techniques. Once the lumen boundary has been determined, in another embodiment, the stent struts are detected using a ray shooting algorithm whereby a ray is projected outward in the OCT image starting from the position in the image of the OCT sensor. The intensities of the pixels along the ray are used to detect the presence of a stent strut in the image.

摘要翻译： 公开了一种用于自动检测图像中的支架支柱的方法和装置，其中首先自动检测动脉壁的内边界或内腔，并且确定与图像中的光线的强度分布。 在一个实施例中，可以例如通过使用基于区域的算法技术，基于测地边界的算法技术或两种技术的组合来演示诸如椭圆的几何形状来实现流明边界的检测。 一旦已经确定了管腔边界，在另一个实施例中，使用射线射击算法来检测支架支柱，由此射线从OCT传感器的图像中的位置开始向OCT中投射。 使用沿着光线的像素的强度来检测图像中支架支柱的存在。

公开(公告)号：US20070050073A1

公开(公告)日：2007-03-01

申请号：US11466149

申请日：2006-08-22

申请人： Gozde Unal ,  Gregory Slabaugh ,  Tong Fang

发明人： Gozde Unal ,  Gregory Slabaugh ,  Tong Fang

IPC分类号： G06F19/00

CPC分类号： H04R25/658 ,  G06K9/469 ,  H04R25/652 ,  H04R2225/77

摘要： An improved method of designing hearing aid molds is disclosed whereby regions of an ear impression model are identified as a function of a geodesic distance measure. According to a first embodiment, a canal point of an ear impression model is identified as that point having a maximum normalized geodesic distance as compared to all other points on the surface of the ear impression model. According to a second embodiment, a helix point of the ear impression model is identified as that point having a maximum normalized geodesic distance as compared to all points except those points in the canal region of said ear impression model. Finally, in accordance with another embodiment, a geodesic distance between a canal point and a helix point of an ear impression model is identified and a percentage threshold, illustratively 65%, is applied to that geodesic distance to identify a crus region.

摘要翻译： 公开了一种改进的助听器模具的设计方法，其中耳朵印模模型的区域被识别为测地距离测量的函数。 根据第一实施例，与耳朵印象模型的表面上的所有其他点相比，耳朵印模模型的运河点被识别为具有最大归一化测地距离的点。 根据第二实施例，与除了所述耳朵印象模型的运河区域中的那些点之外的所有点相比，耳朵印模模型的螺旋点被识别为具有最大归一化测地距离的点。 最后，根据另一个实施例，识别耳朵印模模型的运河点和螺旋点之间的测地距离，并且示例性地将65％的百分比阈值应用于该测地距离以识别小腿区域。

公开(公告)号：US20080109192A1

公开(公告)日：2008-05-08

申请号：US11933516

申请日：2007-11-01

申请人： Gregory Slabaugh ,  Gozde Unal ,  Tong Fang

发明人： Gregory Slabaugh ,  Gozde Unal ,  Tong Fang

IPC分类号： G06F17/10

CPC分类号： G06T17/10

摘要： A method for modeling a 2-dimensional tubular structure in a digitized image includes providing a digitized image of a tubular structure containing a plurality of 2D balls of differing radii, initializing a plurality of connected spline segments that form an envelope surrounding the plurality of 2D balls, each the spline segment Si being parameterized by positions of the ith and i+1th balls and contact angles αi, αi+1 from the center of each respective ball to a point on the perimeter of each the ball contacting the spline segment Si, each the αi affecting spline segment Si and Si−1, and updating the angles by minimizing an energy that is a functional of the angles, where the updating is repeated until the energy is minimized subject to a constraint that the envelope is tangent to each ball at each point of contact, where the envelope is represented by the contact angles.

摘要翻译： 一种用于对数字化图像中的二维管状结构进行建模的方法包括提供包含不同半径的多个2D球的管状结构的数字化图像，初始化形成围绕多个2D球的包围的多个连接的花键片段 ，每个样条段S i i i被第i个和第i + 1个第球的位置参数化，并且接触角α1 从每个相应球的中心到接触花键片段S i的每个球的周边上的点的每个α，α，α， 影响样条线段S i和S i-1，并且通过使作为角度的函数的能量最小化来更新角度，其中 重复更新直到能量被最小化，受限于在每个接触点处包络与每个球相切，其中包络由接触角表示。

公开(公告)号：US20080075375A1

公开(公告)日：2008-03-27

申请号：US11779413

申请日：2007-07-18

申请人： Gozde Unal ,  Susann Bucher ,  Gregory Slabaugh ,  Tong Fang

发明人： Gozde Unal ,  Susann Bucher ,  Gregory Slabaugh ,  Tong Fang

IPC分类号： G06K9/36

CPC分类号： G06K9/621 ,  G06K2209/05 ,  G06T7/12 ,  G06T7/149 ,  G06T7/174 ,  G06T2207/10081 ,  G06T2207/10132 ,  G06T2207/30101 ,  Y10S128/922

摘要： A method for segmenting intravascular images includes acquiring a series of digitized images acquired from inside a vessel, each said image comprising a plurality of intensities corresponding to a 2-dimensional grid of pixels, providing a precomputed set of shapes for modeling contours of vessel wall boundaries, wherein a contour can be expressed as a sum of a mean shape and a inner product of shape modes and shape weights, initializing a boundary contour for one of said set of images, initializing said shape weights by projecting a contour into said shape modes, updating said shape weights from differential equations of said shape weights, and computing a contour by summing said mean shape and said inner product of shape modes and updated shape weights.

摘要翻译： 用于分割血管内图像的方法包括获取从血管内获取的一系列数字化图像，每个所述图像包括对应于像素的二维网格的多个强度，提供用于建模血管壁边界的轮廓的预先计算的一组形状 其中轮廓可以表示为平均形状和形状模式和形状权重的内积的和，初始化所述图像集合中的一个图像的边界轮廓，通过将轮廓投影到所述形状模式中来初始化所述形状权重， 从所述形状权重的微分方程更新所述形状权重，以及通过将所述平均形状和形状模式的内积与更新的形状权重相加来计算轮廓。

公开(公告)号：US20070160277A1

公开(公告)日：2007-07-12

申请号：US11620078

申请日：2007-01-05

申请人： Gregory Slabaugh ,  Gozde Unal ,  Tong Fang ,  Huy-Nam Doan

发明人： Gregory Slabaugh ,  Gozde Unal ,  Tong Fang ,  Huy-Nam Doan

IPC分类号： G06K9/00

CPC分类号： G06K9/342 ,  G06K9/6224 ,  G06K2209/05

摘要： A system and method for segmentation of anatomical structures in MRI volumes using graph cuts is disclosed. In this method, a template is registered to an MRI brain volume. The template identifies seed points of anatomical brain structures, such as the cerebrum, the cerebellum, and the brain stem, in the MRI brain volume. Any or all of the anatomical brain structures can be segmented using graph cuts segmentation initialized based on the seed points identified by the template. It is possible to segment each of the anatomical brain structures by performing a hierarchical three-phase segmentation process including brain/non-brain segmentation, cerebrum/cerebellum and brain stem segmentation, and cerebellum/brain stem segmentation.

摘要翻译： 公开了一种用于使用图形切割来分割MRI体积中的解剖结构的系统和方法。 在该方法中，将模板登记到MRI脑体积。 该模板在MRI脑容量中识别解剖脑结构的种子点，如大脑，小脑和脑干。 可以使用基于由模板识别的种子点初始化的图切割分段来分割任何或所有解剖脑结构。 通过执行包括脑/非脑分割，大脑/小脑和脑干分割以及小脑/脑干分割的分层三阶段分割过程，可以分割每个解剖脑结构。

公开(公告)号：US20070153000A1

公开(公告)日：2007-07-05

申请号：US11466211

申请日：2006-08-22

申请人： Hui Xie ,  Jin Zhou ,  Gregory Slabaugh ,  Gozde Unal ,  Tong Fang

发明人： Hui Xie ,  Jin Zhou ,  Gregory Slabaugh ,  Gozde Unal ,  Tong Fang

IPC分类号： G06T17/20 ,  G06T15/30

CPC分类号： G06T17/20

摘要： A method and apparatus for rounding a sharp edge of a model of an object is disclosed whereby a ball is propagated in a desired direction along the edge to be smoothed. The position of the ball at each point in its propagation is noted and, as a result, a virtual tunnel through which the ball passed may be constructed. Points on the sides of the surface of the object in proximity to the sharp edge are then projected onto the virtual tunnel by connecting with a line each point in proximity to the sharp edge to the center of the tunnel. New projected points are created at each position on the surface of the tunnel where the lines intersect that surface. The original points along the sharp edge are then hidden or deleted and the points along the virtual tunnel are connected via well-known surface reconstruction methods. In this way, a sharp edge of a triangle mesh model are advantageously smoothed.

摘要翻译： 公开了一种用于使物体的模型的锋利边缘倒圆的方法和装置，其中球沿着待平滑的边缘在期望的方向上传播。 注意到球在其传播中的每个点处的位置，结果可以构造球通过的虚拟隧道。 接近尖锐边缘的物体表面侧面的点然后通过与尖锐边缘附近的每条线连接到隧道中心而投射到虚拟隧道上。 在隧道表面的每个位置上创建新的投影点，其中线与该表面相交。 然后沿尖锐边缘的原始点被隐藏或删除，沿着虚拟隧道的点通过公知的表面重建方法连接。 以这种方式，有利地平滑了三角形网格模型的尖锐边缘。

公开(公告)号：US20070058829A1

公开(公告)日：2007-03-15

申请号：US11462834

申请日：2006-08-07

申请人： Gozde Unal ,  Gregory Slabaugh ,  Tong Fang ,  Jason Tyan

发明人： Gozde Unal ,  Gregory Slabaugh ,  Tong Fang ,  Jason Tyan

IPC分类号： H04R25/00

CPC分类号： G06K9/00214 ,  G06T7/30 ,  G06T19/00 ,  G06T2207/30004 ,  H04R25/652 ,  H04R25/658 ,  H04R2225/77

摘要： A method for registering two three-dimensional shapes is disclosed whereby the two shapes are represented as zero level set of signed distance functions and the energy between these two functions is minimized. In a first embodiment two undetailed ear impression models are rigidly registered with each other. In another embodiment, a detailed ear impression is initially aligned with an undetailed ear impression model and, then, the detailed ear impression model is rigidly registered with the undetailed ear impression model as a function of said signed distance functions. In accordance with another embodiment, an undetailed ear impression model is non-rigidly registered with a template ear impression model as a function of said signed distance functions.

摘要翻译： 公开了一种用于记录两个三维形状的方法，其中两个形状被表示为有限距离函数的零级集合，并且这两个函数之间的能量被最小化。 在第一实施例中，两个未详细的耳朵印象模型彼此刚性地对齐。 在另一个实施例中，详细的耳朵印象最初与未详细的耳朵印象模型对准，然后，作为所述有符号距离函数的函数，详细的耳朵印象模型与未详细的耳朵印模模型刚性地注册。 根据另一个实施例，作为所述有符号距离函数的函数，未确定的耳朵印象模型与模板耳朵印模模型非刚性地对齐。

公开(公告)号：US20070057941A1

公开(公告)日：2007-03-15

申请号：US11462804

申请日：2006-08-07

申请人： Tong Fang ,  Gozde Unal ,  Fred McBagonluri ,  Alexander Zouhar ,  Hui Xie ,  Gregory Slabaugh ,  Jason Tyan

发明人： Tong Fang ,  Gozde Unal ,  Fred McBagonluri ,  Alexander Zouhar ,  Hui Xie ,  Gregory Slabaugh ,  Jason Tyan

IPC分类号： G06F19/00

CPC分类号： H04R25/652 ,  H04R25/658 ,  H04R25/70 ,  H04R2225/77

摘要： A method of designing hearing aid molds is disclosed whereby two shapes corresponding to graphical images of ear impressions are registered with each other to facilitate joint processing of the hearing aid design. In a first embodiment, a first graphical representation of a first ear impression is received and a feature, such as the aperture of the ear impression, is identified on that graphical model. A first vector is generated that represents the orientation and shape of that first feature. The three-dimensional translation and rotation of that first vector are determined that are necessary to align the first vector with a second vector representing the orientation and a shape of a feature, once again such as the aperture, of a second ear impression. In another embodiment, this alignment is then refined by minimizing the sum of the distances between points on the first and second graphical representations.

摘要翻译： 公开了一种设计助听器模具的方法，其中对应于耳朵印象的图形图像的两个形状彼此对准以便于助听器设计的联合处理。 在第一实施例中，接收第一耳朵印象的第一图形表示，并且在该图形模型上识别诸如耳朵印象的孔的特征。 生成表示该第一特征的取向和形状的第一向量。 确定该第一矢量的三维平移和旋转是必要的，以使第一矢量与代表第二耳朵印象的特征的取向和形状的第二矢量（例如孔）对齐。 在另一个实施例中，然后通过最小化第一和第二图形表示上的点之间的距离之和来改进该对准。

公开(公告)号：US20070014473A1

公开(公告)日：2007-01-18

申请号：US11456947

申请日：2006-07-12

申请人： Gregory Slabaugh ,  Gozde Unal

发明人： Gregory Slabaugh ,  Gozde Unal

IPC分类号： G06K9/34 ,  G06K9/46

CPC分类号： G06K9/6206 ,  G06K9/342

摘要： A system and method for graph cut image segmentation using a shape prior is provided. In this method, an initial shape is applied to a portion of an image to be segmented. A narrowband is formed around a border of the shape, and a minimized graph cut is calculated for a portion of the image within the narrowband. The shape is then adjusted using the shape prior to fit the minimized graph cut. This method can be iteratively performed so that the shape evolves to segment an object from an image. The shape prior can be a parametric shape, such as an ellipse, or a statistical shape eigenspace calculated based on one or more training shapes.

摘要翻译： 提供了一种使用形状先前的图形切割图像分割的系统和方法。 在该方法中，将初始形状应用于待分割图像的一部分。 在形状的边界周围形成窄带，并且对于窄带内的图像的一部分计算最小化的图形切割。 然后在适合最小化图形切割之前使用形状来调整形状。 可以迭代地执行该方法，使得形状演变成从图像分割对象。 前面的形状可以是参数形状，例如椭圆，或者基于一个或多个训练形状计算的统计形状本征空间。