公开(公告)号：US20070244395A1

公开(公告)日：2007-10-18

申请号：US11619495

申请日：2007-01-03

申请人： Ge Wang ,  Alexander Cong ,  Weimin Han ,  Ming Jiang ,  Haiou Shen ,  Wenxiang Cong

发明人： Ge Wang ,  Alexander Cong ,  Weimin Han ,  Ming Jiang ,  Haiou Shen ,  Wenxiang Cong

IPC分类号： A61B5/00

CPC分类号： A61B5/0059 ,  A61B5/0077 ,  A61B6/03 ,  A61B6/4488 ,  A61B6/482 ,  A61B6/508 ,  A61B6/5247 ,  A61B2503/40

摘要： Bioluminescent imaging has proven to be a valuable tool for monitoring physiological and pathological activities at cellular and molecular levels in living small animals. Using biological techniques, target cells can be tagged with reporters which generate characteristic photons in a wide spectrum covering the infra-red range. Part of the diffused light can reach the body surface of a subject/specimen (e.g., a small animal), be separated into several spectral bands using optical means, and collected by a sensitive camera. Systems and methods are disclosed herein for multi-spectral bioluminescence tomography (MBLT), in which an image of an underlying 3D bioluminescent source distribution is synergistically reconstructed from spectrally resolved datasets externally measured. This MBLT process involves two or multiple imaging modalities that produce structural information of the object and optical properties of the object as well to enable and improve the quality of MBLT.

摘要翻译： 已经证明生物发光成像是监测活的小动物细胞和分子水平的生理和病理活动的有价值的工具。 使用生物学技术，靶细胞可以用记录器进行标记，记者在覆盖红外范围的广谱中产生特征光子。 扩散光的一部分可以到达对象/标本（例如，小动物）的身体表面，使用光学装置分离成若干光谱带，并由敏感摄像机收集。 本文公开了用于多光谱生物发光断层摄影（MBLT）的系统和方法，其中底层3D生物发光源分布的图像从外部测量的光谱解析数据集协同地重建。 该MBLT过程涉及产生物体的结构信息和对象的光学性质的两个或多个成像模态，以及实现和提高MBLT的质量。

公开(公告)号：US20070238966A1

公开(公告)日：2007-10-11

申请号：US11731624

申请日：2007-03-30

申请人： Lizhi Sun ,  Yi Liu ,  Zhiguo Wang ,  Ge Wang

发明人： Lizhi Sun ,  Yi Liu ,  Zhiguo Wang ,  Ge Wang

IPC分类号： A61B5/05

CPC分类号： A61B5/4312 ,  A61B5/0053 ,  A61B5/442

摘要： A method for obtaining a distribution of a stiffness property in tissue includes applying a plurality of loadings to the tissue, obtaining a plurality of two-dimensional (2-D) imaging projections of the tissue from different directions, measuring a force resulting from one of the plurality of loadings, measuring from at least one of the plurality of 2-D imaging projections a displacement of the tissue in response to the force, obtaining an initial set of input parameters for an estimated stiffness property of the tissue, and solving iteratively for the stiffness property using a computer.

摘要翻译： 用于获得组织中刚度性质分布的方法包括将多个负载施加到组织，从不同方向获得组织的多个二维（2-D）成像突起，测量由下列之一产生的力： 所述多个负载从所述多个2-D成像投影中的至少一个成像投影中测量所述组织响应于所述力的位移，获得用于所述组织的估计刚度特性的初始输入参数集合，并迭代地求解 使用计算机的刚度属性。

公开(公告)号：US20060247513A1

公开(公告)日：2006-11-02

申请号：US11281798

申请日：2005-11-17

申请人： Ge Wang ,  Shiying Zhao

发明人： Ge Wang ,  Shiying Zhao

IPC分类号： A61B5/05

CPC分类号： G01T1/2985 ,  A61B6/032 ,  A61B6/5235 ,  G01N23/046 ,  G01N2223/419 ,  G01N2223/612 ,  G06T11/005 ,  G06T2211/436 ,  Y10S378/901

摘要： The present invention relates to a method and system (CMCT system) for improving spatial resolution imaging of CT systems. The systems and method can achieve improved spatial resolution while using CT X-ray dosage levels comparable to those currently used in practice. The system and method can be used for micro-tomography and/or micortomosynthesis of a local region and/or volume of interest in a patient head or another body part.

摘要翻译： 本发明涉及用于改善CT系统的空间分辨率成像的方法和系统（CMCT系统）。 系统和方法可以在使用与实际使用的CT X射线剂量水平相当的CT X射线剂量水平时实现改善的空间分辨率。 该系统和方法可以用于患者头部或另一个身体部位的局部区域和/或感兴趣体积的微层析和/或微合成。

公开(公告)号：US20060050842A1

公开(公告)日：2006-03-09

申请号：US11182504

申请日：2005-07-15

申请人： Ge Wang ,  Yangbo Ye

发明人： Ge Wang ,  Yangbo Ye

IPC分类号： H05G1/60 ,  A61B6/00 ,  G01N23/00 ,  G21K1/12

CPC分类号： G06T11/006 ,  A61B6/027 ,  A61B6/508 ,  G01N23/046 ,  G01N2223/419 ,  G01N2223/612 ,  G06T2211/416 ,  G06T2211/421 ,  Y10S378/901

摘要： Provided herein are methods of reconstructing an image from projection data provided by a tomography scanner that is based on geometric optics comprising scanning an object in a cone-beam imaging geometry following a non-standard spiral path or a general piecewise smooth scanning path wherein projection data is generated and reconstructing an image according to a closed-form formula that is either in the filtered backprojection (FBP) or backprojection filtration (or backprojected filtration, BPF) formats. Also provided herein are associated systems and apparatuses for tomographic imaging.

摘要翻译： 本文提供的方法是从由基于几何光学的断层摄影扫描仪提供的投影数据重建图像的方法包括以非标准螺旋路径或通用分段平滑扫描路径扫描锥形束成像几何中的物体，其中投影数据 被生成并根据封闭形式的公式重新构建图像，该公式处于滤波反投影（FBP）或反投影过滤（或反向投影过滤，BPF）格式中。 本文还提供了用于断层成像的相关系统和装置。

公开(公告)号：US06983034B2

公开(公告)日：2006-01-03

申请号：US10780916

申请日：2004-02-17

申请人： Ge Wang ,  Seung Wook Lee

发明人： Ge Wang ,  Seung Wook Lee

IPC分类号： A61B6/00

CPC分类号： G06T11/006 ,  A61B6/027 ,  A61B6/583 ,  G01N23/046 ,  G01N2223/419 ,  G06T2211/436 ,  Y10S378/901

摘要： An image of an object is reconstructed in a three-dimensional coordinate system in an x-ray computed tomography system. A partial scan of the object is performed by rotating an x-ray beam having a cone beam geometry around a portion of the object or rotating the object in the cone-beam. The x-ray beam forms on a scanning trajectory through a plurality of projection lines from a plurality of successive focal point locations. The scanning trajectory may be substantially circular, helical, spiral, or spiral-like. The x-ray beam, attenuated by the object during the spiral scan, is detected to produce detector values. The detector values are integrated along straight lines on the detector plane to obtain intermediate data. Three-dimensional Radon values representing approximate plane integrals of the object are calculated from the intermediate data using a Grangeat relationship or a modified or extended version or the Grangeat relationship. The calculated and estimated Radon values are then reconstructed into an image volume according to the Radon inversion formula.

摘要翻译： 在X射线计算机断层摄影系统中的三维坐标系中重建对象的图像。 通过旋转具有围绕物体的一部分的锥形光束几何形状的X射线束或者在锥形束中旋转物体来执行物体的部分扫描。 X射线束通过来自多个连续焦点位置的多条投影线在扫描轨迹上形成。 扫描轨迹可以是大致圆形，螺旋状，螺旋状或螺旋状。 在螺旋扫描期间由物体衰减的X射线束被检测以产生检测器值。 检测器值沿检测器平面上的直线积分，以获得中间数据。 使用Grangeat关系或修改或扩展版本或Grangeat关系从中间数据计算表示对象的近似平面积分的三维Radon值。 然后根据Radon倒置公式将计算和估计的Radon值重建为图像体积。

公开(公告)号：US11682110B2

公开(公告)日：2023-06-20

申请号：US17034016

申请日：2020-09-28

申请人： Ge Wang ,  Hongming Shan

发明人： Ge Wang ,  Hongming Shan

IPC分类号： G06T5/50 ,  G06T5/00 ,  G06N3/04 ,  G06N3/08

CPC分类号： G06T5/50 ,  G06N3/04 ,  G06N3/08 ,  G06T5/002 ,  G06T2207/10081 ,  G06T2207/20081 ,  G06T2207/20084

摘要： A system for enhancing a low-dose (LD) computed tomography (CT) image is described. The system includes a modularized adaptive processing neural network (MAP-NN) apparatus and a MAP module. The MAP-NN apparatus is configured to receive a LDCT image as input. The MAP-NN apparatus includes a number, T, trained neural network (NN) modules coupled in series. Each trained NN module is configured to generate a respective test intermediate output image based, at least in part, on a respective received test input image. Each test intermediate output image corresponds to an incrementally denoised respective received test input image. The MAP module is configured to identify an optimum mapping depth, D, based, at least in part, on a selected test intermediate output image, the selected test intermediate output image selected by a domain expert. The mapping depth, D, is less than or equal to the number, T.

公开(公告)号：US20230026961A1

公开(公告)日：2023-01-26

申请号：US17859186

申请日：2022-07-07

申请人： Ge Wang ,  Chuang Niu ,  Wenxiang Cong

发明人： Ge Wang ,  Chuang Niu ,  Wenxiang Cong

IPC分类号： G06T11/00 ,  G06T5/00 ,  G06N3/04

摘要： In one embodiment, there is provided an apparatus for low-dimensional manifold constrained disentanglement for metal artifact reduction (MAR) in computed tomography (CT) images. The apparatus includes a patch set construction module, a manifold dimensionality module, and a training module. The patch set construction module is configured to construct a patch set based, at least in part on training data. The manifold dimensionality module is configured to determine a dimensionality of a manifold. The training module is configured to optimize a combination loss function comprising a network loss function and the manifold dimensionality. The optimizing the combination loss function includes optimizing at least one network parameter.

公开(公告)号：US20220375142A1

公开(公告)日：2022-11-24

申请号：US17642725

申请日：2020-09-14

申请人： Huidong Xie ,  Ge Wang ,  Hongming Shan ,  Wenxiang Cong

发明人： Huidong Xie ,  Ge Wang ,  Hongming Shan ,  Wenxiang Cong

IPC分类号： G06T11/00

摘要： A system for few-view computed tomography (CT) image reconstruction is described. The system includes a preprocessing module, a first generator network, and a discriminator network. The preprocessing module is configured to apply a ramp filter to an input sinogram to yield a filtered sinogram. The first generator network is configured to receive the filtered sinogram, to learn a filtered back-projection operation and to provide a first reconstructed image as output. The first reconstructed image corresponds to the input sinogram. The discriminator network is configured to determine whether a received image corresponds to the first reconstructed image or a corresponding ground truth image. The generator network and the discriminator network correspond to a Wasserstein generative adversarial network (WGAN). The WGAN is optimized using an objective function based, at least in part, on a Wasserstein distance and based, at least in part, on a gradient penalty.

公开(公告)号：US20210097662A1

公开(公告)日：2021-04-01

申请号：US17034016

申请日：2020-09-28

申请人： Ge Wang ,  Hongming Shan

发明人： Ge Wang ,  Hongming Shan

IPC分类号： G06T5/50 ,  G06T5/00 ,  G06N3/04 ,  G06N3/08

摘要： A system for enhancing a low-dose (LD) computed tomography (CT) image is described. The system includes a modularized adaptive processing neural network (MAP-NN) apparatus and a MAP module. The MAP-NN apparatus is configured to receive a LDCT image as input. The MAP-NN apparatus includes a number, T, trained neural network (NN) modules coupled in series. Each trained NN module is configured to generate a respective test intermediate output image based, at least in part, on a respective received test input image. Each test intermediate output image corresponds to an incrementally denoised respective received test input image. The MAP module is configured to identify an optimum mapping depth, D, based, at least in part, on a selected test intermediate output image, the selected test intermediate output image selected by a domain expert. The mapping depth, D, is less than or equal to the number, T.

公开(公告)号：US20160113602A1

公开(公告)日：2016-04-28

申请号：US14924495

申请日：2015-10-27

申请人： Ge Wang ,  Fenglin Liu ,  Wenxiang Cong ,  Qingsong Yang

发明人： Ge Wang ,  Fenglin Liu ,  Wenxiang Cong ,  Qingsong Yang

IPC分类号： A61B6/00 ,  A61B6/03

CPC分类号： A61B6/4035 ,  A61B6/032 ,  A61B6/482 ,  A61B6/544 ,  A61B6/583

摘要： Dynamic bowties, imaging systems including a bowtie, and methods of imaging including such bowties or systems are provided. A bowtie can be a three-dimensional (3-D) dynamic bowtie and can include a highly-attenuating bowtie (HB) and a weakly-attenuating bowtie (WB). The HB can be filled with a liquid, and the WB can be immersed in the liquid of the HB.

摘要翻译： 提供动态弯曲，包括弓形的成像系统，以及包括这种弯曲或系统的成像方法。 Bowtie可以是一个三维（3-D）动态的蝴蝶结，可以包括高度衰减的蝴蝶结（HB）和弱衰减的蝴蝶结（WB）。 HB可以充满液体，WB可以浸入HB的液体中。