公开(公告)号：US09846935B2

公开(公告)日：2017-12-19

申请号：US14403292

申请日：2012-05-31

申请人： Sergey Simanovsky ,  Julia Pavlovich ,  Ram Naidu

发明人： Sergey Simanovsky ,  Julia Pavlovich ,  Ram Naidu

IPC分类号： G06K9/00 ,  G06T7/00 ,  G06T7/10 ,  G01V5/00 ,  G06K9/46 ,  G06K9/52 ,  G06T7/11

CPC分类号： G06T7/0012 ,  G01V5/0008 ,  G06K9/4609 ,  G06K9/52 ,  G06K2009/4666 ,  G06T7/10 ,  G06T7/11 ,  G06T2207/10081 ,  G06T2207/30112

摘要： Among other things, one or more systems and/or techniques for segmenting a representation of a sheet object from an image are provided herein. To identify elements of an image (e.g., pixels and/or voxels) representative of sheet objects, a constant false alarm rate (CFAR) score and a topological score are computed for respective elements being analyzed. The CFAR score indicates a relationship between an element and a neighborhood of elements when viewed as a collective unit. The topological score indicates a relationship between the element and a neighborhood of elements when viewed neighbor-by-neighbor. When the CFAR score is within a specified range of CFAR scores and the topological score is within a specified range of topological scores, the element is labeled as being associated with a sheet object. A connected component labeling (CCL) approach may be used to group elements labeled as being associated with a sheet object.

公开(公告)号：US20150104089A1

公开(公告)日：2015-04-16

申请号：US14397751

申请日：2012-05-01

申请人： Andrew Litvin ,  Ram Naidu ,  David Lieblich ,  Sergey Simanovsky

发明人： Andrew Litvin ,  Ram Naidu ,  David Lieblich ,  Sergey Simanovsky

IPC分类号： G06T11/00 ,  G01N23/04

CPC分类号： G06T11/006 ,  G01N23/046 ,  G06T2211/408 ,  G06T2211/424 ,  G06T2211/436

摘要： Z-effective (e.g., atomic number) values are generated for one or more sets of voxels in a CT density image using sparse (measured) multi-energy projection data. Voxels in the CT density image are assigned a starting z-effective value, causing a CT z-effective image to be generated from the CT density image. The accuracy of the assigned z-effective values is tested by forward projecting the CT z-effective image to generate synthetic multi-energy projection data and comparing the synthetic multi-energy projection data to the sparse multi-energy projection data. When the measure of similarity between the synthetic data and the sparse data is low, the z-effective value assigned to one or more voxels is modified until the measure of similarity is above a specified threshold (e.g., with an associated confidence score), at which point the z-effective values substantially reflect the z-effective values that would be obtained using a (more expensive) dual-energy CT imaging modality.

摘要翻译： 使用稀疏（测量）多能量投影数据，在CT密度图像中的一组或多组体素生成Z-有效（例如，原子序数）值。 CT密度图像中的体素被分配起始z有效值，从CT密度图像产生CT z有效图像。 通过向前投影CT z有效图像来产生合成多能量投影数据并将合成的多能量投影数据与稀疏多能量投影数据进行比较，来测试所分配的z-有效值的精度。 当合成数据和稀疏数据之间的相似性度量低时，分配给一个或多个体素的z-有效值被修改，直到相似性的度量高于指定的阈值（例如，具有相关的可信度得分），在 这指出z-有效值基本上反映了使用（更昂贵）双能CT成像模式将获得的z-有效值。

公开(公告)号：US08787669B2

公开(公告)日：2014-07-22

申请号：US13121892

申请日：2008-09-30

申请人： Andrew Litvin ,  Sergey Simanovsky ,  Ram Naidu

发明人： Andrew Litvin ,  Sergey Simanovsky ,  Ram Naidu

IPC分类号： G06K9/34

CPC分类号： G06T7/155

摘要： Representations of an object can comprise two or more separate sub-objects, producing a compound object. Compound objects can affect the quality of object visualization and threat identification. As provided herein, a compound object can be separated into sub-objects based on object morphological properties (e.g., an object's shape, surface area). Further, a potential compound object can be split into sub-objects, for example, eroding one or more outer layers of volume space (e.g., voxels) from the potential compound object. Additionally, a volume of a representation of the sub-objects in an image can be reconstructed, for example, by generating sub-objects that have a combined volume approximate to that of the compound object. Furthermore, sub-objects, which can be parts of a same physical object, but may have been erroneously split, can be identified and merged using connectivity and compactness based techniques.

摘要翻译： 对象的表示可以包括两个或多个单独的子对象，产生复合对象。 复合对象可以影响对象可视化和威胁识别的质量。 如本文所提供的，可以基于对象形态特性（例如，对象的形状，表面积）将复合对象分成子对象。 此外，潜在的复合对象可以被分割成子对象，例如，从潜在的复合对象侵蚀体积空间的一个或多个外层（例如，体素）。 此外，可以例如通过生成具有近似于复合对象的组合体积的子对象来重建图像中子对象的表示量。 此外，可以使用基于连接性和紧凑性的技术来识别和合并可以是相同物理对象的部分但可能被错误地分割的子对象。

公开(公告)号：US07190757B2

公开(公告)日：2007-03-13

申请号：US10850910

申请日：2004-05-21

申请人： Zhengrong Ying ,  Ram Naidu ,  Sergey Simanovsky ,  Carl R. Crawford

发明人： Zhengrong Ying ,  Ram Naidu ,  Sergey Simanovsky ,  Carl R. Crawford

IPC分类号： A61B6/00

CPC分类号： G01N23/046 ,  G01N2223/419

摘要： A method of and a system for computing Z (effective atomic number) images from projection data are provided, wherein the projections are acquired using at least two x-ray spectra for a set of scanned objects, including a set of low energy projections and a set of high energy projections; the method comprises decomposing the low energy projections and high energy projections into photoelectric projections, reconstructing the photoelectric projections into photoelectric images, reconstructing one of the two sets of projections into CT images, and computing Z images from the CT images and the photoelectric images with parameters obtained from a calibration procedure.

摘要翻译： 提供了一种用于从投影数据计算Z（有效原子序号）图像的方法和系统，其中使用用于一组扫描对象的至少两个X射线光谱来获取投影，包括一组低能量投影和 一套高能量投影; 该方法包括将低能量投影和高能量投影分解为光电投影，将光电投影重建为光电图像，将两组投影中的一个重建为CT图像，并从CT图像和光电图像中计算Z图像 从校准程序获得。

公开(公告)号：US09390523B2

公开(公告)日：2016-07-12

申请号：US14397751

申请日：2012-05-01

申请人： Andrew Litvin ,  Ram Naidu ,  David Lieblich ,  Sergey Simanovsky

发明人： Andrew Litvin ,  Ram Naidu ,  David Lieblich ,  Sergey Simanovsky

IPC分类号： G06T11/00 ,  G01N23/04

CPC分类号： G06T11/006 ,  G01N23/046 ,  G06T2211/408 ,  G06T2211/424 ,  G06T2211/436

摘要： Z-effective (e.g., atomic number) values are generated for one or more sets of voxels in a CT density image using sparse (measured) multi-energy projection data. Voxels in the CT density image are assigned a starting z-effective value, causing a CT z-effective image to be generated from the CT density image. The accuracy of the assigned z-effective values is tested by forward projecting the CT z-effective image to generate synthetic multi-energy projection data and comparing the synthetic multi-energy projection data to the sparse multi-energy projection data. When the measure of similarity between the synthetic data and the sparse data is low, the z-effective value assigned to one or more voxels is modified until the measure of similarity is above a specified threshold (e.g., with an associated confidence score), at which point the z-effective values substantially reflect the z-effective values that would be obtained using a (more expensive) dual-energy CT imaging modality.

摘要翻译： 使用稀疏（测量）多能量投影数据，在CT密度图像中的一组或多组体素生成Z-有效（例如，原子序数）值。 CT密度图像中的体素被分配起始z有效值，从CT密度图像产生CT z有效图像。 通过向前投影CT z有效图像来产生合成多能量投影数据并将合成的多能量投影数据与稀疏多能量投影数据进行比较，来测试所分配的z-有效值的精度。 当合成数据和稀疏数据之间的相似性度量低时，分配给一个或多个体素的z-有效值被修改，直到相似性的度量高于指定的阈值（例如，具有相关的可信度得分），在 这指出z-有效值基本上反映了使用（更昂贵）双能CT成像模式将获得的z-有效值。

公开(公告)号：US08817019B2

公开(公告)日：2014-08-26

申请号：US13387851

申请日：2009-07-31

申请人： Ram Naidu ,  Sergey Simanovsky ,  Andrew Litvin

发明人： Ram Naidu ,  Sergey Simanovsky ,  Andrew Litvin

IPC分类号： G06T15/00 ,  G09G5/02

CPC分类号： G06T11/001

摘要： A projection image of an object is colored using three-dimensional image data. This may be particularly useful in radiographic imaging applications, for example. In one embodiment, a colored synthetic image is rendered from a colored three-dimensional image of an object, and color components of pixels of the synthetic image are used to determine color components, or color values, for corresponding pixels of a projection image depicting a similar view of the object as the synthetic image. In this way, the two-dimensional projection image is colored similarly to the colored three-dimensional image. For example, the projection image may be colored based upon density (if the three-dimensional image is colored based upon density) so aspects of the object that attenuate a similar amount of radiation but have different densities may be colored differently.

摘要翻译： 使用三维图像数据对物体的投影图像进行着色。 例如，这可能在放射照相成像应用中特别有用。 在一个实施例中，彩色合成图像从对象的彩色三维图像呈现，并且使用合成图像的像素的颜色分量来确定用于描绘图像的投影图像的相应像素的颜色分量或颜色值 作为合成图像的对象的类似视图。 以这种方式，二维投影图像与彩色三维图像类似地着色。 例如，投影图像可以基于密度着色（如果三维图像基于密度着色），则可以对不同密度的相似量的辐射削弱相同量的物体的方面进行着色。

公开(公告)号：US08774496B2

公开(公告)日：2014-07-08

申请号：US13387502

申请日：2009-07-29

申请人： Julia Pavlovich ,  Sergey Simanovsky ,  Zhengrong Ying ,  Ram Naidu

发明人： Julia Pavlovich ,  Sergey Simanovsky ,  Zhengrong Ying ,  Ram Naidu

IPC分类号： G06K9/00

CPC分类号： G06K9/00771 ,  G06K2209/09 ,  G06T7/11 ,  G06T7/143 ,  G06T2207/10081 ,  G06T2207/30112 ,  G06T2207/30232

摘要： Representations of an object in an image generated by an imaging apparatus can comprise two or more separate sub-objects, producing a compound object. Compound objects can negatively affect the quality of object visualization and threat identification performance. As provided herein, a compound object can be separated into sub-objects. Topology score map data, representing topological differences in the potential compound object, may be computed and used in a statistical distribution to identify modes that may be indicative of the sub-objects. The identified modes may be assigned a label and a voxel of the image data indicative of the potential compound object may be relabeled based on the label assigned to a mode that represents data corresponding to properties of a portion of the object that the voxel represents to create image data indicative of one or more sub-objects.

摘要翻译： 由成像装置生成的图像中的对象的表示可以包括两个或更多个单独的子对象，产生复合对象。 复合对象可以对对象可视化和威胁识别性能的质量产生负面影响。 如本文所提供的，复合对象可以被分成子对象。 可以计算表示潜在复合对象中的拓扑差异的拓扑得分图数据，并用于统计分布中以识别可指示子对象的模式。 可以为所识别的模式分配标签，并且可以基于分配给表示对应于体素代表创建的对象的一部分的属性的模式的标签来重新标记指示潜在复合对象的图像数据的体素 指示一个或多个子对象的图像数据。

公开(公告)号：US08483360B2

公开(公告)日：2013-07-09

申请号：US13376715

申请日：2009-06-12

申请人： Andrew Litvin ,  Julia Pavlovich ,  Aleksander Roshi ,  Sergey Simanovsky ,  Ram Naidu

发明人： Andrew Litvin ,  Julia Pavlovich ,  Aleksander Roshi ,  Sergey Simanovsky ,  Ram Naidu

IPC分类号： H05G1/64 ,  G06K9/00

CPC分类号： A61B6/405 ,  A61B6/032 ,  A61B6/4007 ,  A61B6/4035 ,  A61B6/482 ,  A61B6/583 ,  G06T11/005 ,  G06T2211/408

摘要： The techniques described herein provide for correcting projection data that comprises contamination due to source switching in a multi energy scanner. The correction is a multi-neighbor correction. That is, it uses data from at least two other views of an object (e.g., generally a previous view and a subsequent view) to correct a current view of the object. The multi-neighbor correction may use one or more correction factors to determine how much data from the other two views to use to correct the current view. The correction factor(s) are determined based upon a calibration that utilizes image space data and/or projection space data of a phantom. In this way, the correction factor(s) account for source leakage that occurs in multi energy scanners.

摘要翻译： 本文描述的技术提供用于校正投影数据，其包括由于多能量扫描器中的源切换引起的污染。 校正是多邻居校正。 也就是说，它使用来自对象的至少两个其他视图的数据（例如，通常为先前视图和后续视图）来校正对象的当前视图。 多邻居校正可以使用一个或多个校正因子来确定来自用于校正当前视图的另外两个视图的数据量。 基于利用幻影的图像空间数据和/或投影空间数据的校准来确定校正因子。 以这种方式，校正因子考虑到在多能量扫描仪中发生的源泄漏。

公开(公告)号：US08391600B2

公开(公告)日：2013-03-05

申请号：US12357035

申请日：2009-01-21

申请人： Andrew Litvin ,  Sergey Simanovsky ,  Ram Naidu

发明人： Andrew Litvin ,  Sergey Simanovsky ,  Ram Naidu

IPC分类号： G06K9/00 ,  G06K9/34

CPC分类号： G06T7/0004 ,  G06T7/11 ,  G06T7/194 ,  G06T2207/10081 ,  G06T2207/30112

摘要： Certain imaging systems, such as automatic explosives detection systems, employ techniques that utilize image processing, feature extraction and decision making steps to detect threats in images. Such techniques use segmentation as a first algorithmic step, which extracts data representing objects from image data. Some of the extracted objects are actually composed of multiple distinct physical objects. For these compound objects discrimination becomes difficult because computed object properties are less specific than properties computed for a single physical object. A technique is described which includes splitting such compound objects by separating the data of each component from the rest of the data and using properties of density histograms based on voxel distributions in both density and spatial domains.

摘要翻译： 某些成像系统，例如自动爆炸物检测系统，采用利用图像处理，特征提取和决策步骤来检测图像中的威胁的技术。 这样的技术使用分割作为第一算法步骤，其从图像数据中提取表示对象的数据。 一些提取的对象实际上由多个不同的物理对象组成。 对于这些复合对象，鉴别变得困难，因为计算的对象属性比为单个物理对象计算的属性的特性要小。 描述了一种技术，其包括通过将每个组件的数据与其余数据分离并使用基于密度和空间域中的体素分布的密度直方图的属性来拆分这样的复合对象。

公开(公告)号：US07801348B2

公开(公告)日：2010-09-21

申请号：US11183471

申请日：2005-07-18

申请人： Zhengrong Ying ,  Ram Naidu ,  Sergey Simanovsky ,  Matthew Hirsch ,  Carl R. Crawford

发明人： Zhengrong Ying ,  Ram Naidu ,  Sergey Simanovsky ,  Matthew Hirsch ,  Carl R. Crawford

IPC分类号： G06K9/00

CPC分类号： G06K9/00771 ,  G01V5/0041 ,  G01V5/005

摘要： A method of and a system for identifying objects using local distribution features from multi-energy CT images are provided. The multi-energy CT images include a CT image, which approximates density measurements of scanned objects, and a Z image, which approximates effective atomic number measurements of scanned objects. The local distribution features are first and second order statistics of the local distributions of the density and atomic number measurements of different portions of a segmented object. The local distributions are the magnitude images of the first order derivative of the CT image and the Z image. Each segmented object is also divided into different portions to provide geometrical information for discrimination. The method comprises preprocessing the CT and Z images, segmenting images into objects, computing local distributions of the CT and Z images, computing local distribution histograms, computing local distribution features from the said local distribution histograms, classifying objects based on the local distribution features.

摘要翻译： 提供了一种使用多能CT图像的局部分布特征识别物体的方法和系统。 多能CT图像包括近似于扫描对象的密度测量的CT图像和近似有效的扫描对象原子数测量的Z图像。 局部分布特征是分段对象的不同部分的密度和原子序数测量的局部分布的一阶和二阶统计。 局部分布是CT图像和Z图像的一阶导数的幅度图像。 每个分段对象也被分成不同的部分以提供用于辨别的几何信息。 该方法包括预处理CT和Z图像，将图像分割成对象，计算CT和Z图像的局部分布，计算局部分布直方图，从所述局部分布直方图计算局部分布特征，根据局部分布特征对对象进行分类。