公开(公告)号：US20170010224A1

公开(公告)日：2017-01-12

申请号：US15270368

申请日：2016-09-20

Applicant: General Electric Company ,  University of Notre Dame Du Lac ,  Purdue Research Foundation

Inventor： Jean-Baptiste Thibault ,  Debashish Pal ,  Jie Tang ,  Ken David Sauer ,  Charles Bouman ,  Ruoqiao Zhang

IPC: G01N23/04 ,  G06T7/00 ,  G01T1/36 ,  G06T5/10 ,  G06T11/00 ,  G01N23/087 ,  G06T3/00 ,  G06T5/00

CPC classification number: G01N23/046 ,  G01N23/087 ,  G01N2223/423 ,  G01N2223/501 ,  G01N2223/612 ,  G01T1/36 ,  G06T3/0056 ,  G06T5/002 ,  G06T5/10 ,  G06T7/0012 ,  G06T11/008 ,  G06T2207/10004 ,  G06T2207/10081 ,  G06T2211/408

Abstract: A method includes obtaining spectral computed tomography (CT) information via an acquisition unit having an X-ray source and a CT detector. The method also includes, generating, with one or more processing units, using at least one image transform, a first basis image and a second basis image using the spectral CT information. Further, the method includes performing, with the one or more processing units, guided processing on the second basis image using the first basis image as a guide to provide a modified second basis image. Also, the method includes performing at least one inverse image transform using the first basis image and the modified second basis image to generate at least one modified image.

Abstract translation: 一种方法包括经由具有X射线源和CT检测器的获取单元获得频谱计算机断层摄影（CT）信息。 该方法还包括利用一个或多个处理单元使用频谱CT信息使用至少一个图像变换，第一基础图像和第二基础图像来生成。 此外，该方法包括使用第一基础图像作为指导，使用一个或多个处理单元执行对第二基础图像的引导处理，以提供修改的第二基本图像。 此外，该方法包括使用第一基础图像和修改的第二基础图像来执行至少一个逆图像变换以生成至少一个修改图像。

公开(公告)号：US09406154B2

公开(公告)日：2016-08-02

申请号：US13918656

申请日：2013-06-14

Applicant: General Electric Company ,  The Regents of the University of Michigan

Inventor： Lin Fu ,  Madison Gray McGaffin ,  Zhou Yu ,  Jean-Baptiste Thibault ,  Sathish Ramani ,  Jeffrey Allen Fessler ,  Bruno Kristiaan Bernard De Man ,  Debashish Pal

IPC: G06T11/00

CPC classification number: G06T11/006 ,  G06T2211/424

Abstract: The use of the channelized preconditioners in iterative reconstruction is disclosed. In certain embodiments, different channels correspond to different frequency sub-bands and the output of the different channels can be combined to update an image estimate used in the iterative reconstruction process. While individual channels may be relatively simple, the combined channels can represent complex spatial variant operations. The use of channelized preconditioners allows empirical adjustment of individual channels.

Abstract translation: 公开了在迭代重建中使用信道化预处理器。 在某些实施例中，不同的信道对应于不同的频率子带，并且可以组合不同信道的输出以更新在迭代重建过程中使用的图像估计。 虽然单个通道可能相对简单，但组合通道可以表示复杂的空间变体操作。 通道化预处理器的使用允许对各个通道进行实证调整。

公开(公告)号：US20150146845A1

公开(公告)日：2015-05-28

申请号：US14092383

申请日：2013-11-27

Applicant: General Electric Company

Inventor： Jean-Baptiste Thibault ,  Ruoqiao Zhang ,  Charles Bouman ,  Ken Sauer

IPC: G06T11/00 ,  A61B6/00

CPC classification number: G06T11/006 ,  A61B6/032 ,  A61B6/5205

Abstract: Methods and systems for model-based image processing are provided. One method includes selecting at least one reference image from a plurality of reference images, partitioning the at least one reference image into a plurality of patches, generating a probability distribution for each of the patches, and generating a model of a probability distribution for the at least one reference image using the probability distributions for each of the patches.

Abstract translation: 提供了基于模型的图像处理的方法和系统。 一种方法包括从多个参考图像中选择至少一个参考图像，将至少一个参考图像划分成多个补丁，为每个补丁生成概率分布，以及生成针对所述补丁的概率分布的模型 使用每个补丁的概率分布的至少一个参考图像。

公开(公告)号：US20190108441A1

公开(公告)日：2019-04-11

申请号：US15730543

申请日：2017-10-11

Applicant: General Electric Company ,  Purdue University ,  Notre Dame University

Inventor： Jean-Baptiste Thibault ,  Somesh Srivastava ,  Jiang Hsieh ,  Charles A. Bouman, JR. ,  Dong Ye ,  Ken Sauer

IPC: G06N3/08 ,  G06T11/00 ,  G01N23/04 ,  G06N99/00

Abstract: The present approach relates to the training of a machine learning algorithm for image generation and use of such a trained algorithm for image generation. Training the machine learning algorithm may involve using multiple images produced from a single set of tomographic projection or image data (such as a simple reconstruction and a computationally intensive reconstruction), where one image is the target image that exhibits the desired characteristics for the final result. The trained machine learning algorithm may be used to generate a final image corresponding to a computationally intensive algorithm from an input image generated using a less computationally intensive algorithm.

公开(公告)号：US09460485B2

公开(公告)日：2016-10-04

申请号：US14566874

申请日：2014-12-11

Applicant: General Electric Company

Inventor： Jean-Baptiste Thibault ,  Debashish Pal ,  Jie Tang ,  Ken David Sauer ,  Charles Bouman ,  Ruoqiao Zhang

IPC: G06T3/00 ,  G01N23/04 ,  G01T1/36 ,  G01N23/087 ,  G06T5/10

CPC classification number: G01N23/046 ,  G01N23/087 ,  G01N2223/423 ,  G01N2223/501 ,  G01N2223/612 ,  G01T1/36 ,  G06T3/0056 ,  G06T5/002 ,  G06T5/10 ,  G06T7/0012 ,  G06T11/008 ,  G06T2207/10004 ,  G06T2207/10081 ,  G06T2211/408

Abstract: A method includes obtaining spectral computed tomography (CT) information via an acquisition unit having an X-ray source and a CT detector. The method also includes, generating, with one or more processing units, using at least one image transform, a first basis image and a second basis image using the spectral CT information. Further, the method includes performing, with the one or more processing units, guided processing on the second basis image using the first basis image as a guide to provide a modified second basis image. Also, the method includes performing at least one inverse image transform using the first basis image and the modified second basis image to generate at least one modified image.

Abstract translation: 一种方法包括经由具有X射线源和CT检测器的获取单元获得频谱计算机断层摄影（CT）信息。 该方法还包括利用一个或多个处理单元使用频谱CT信息使用至少一个图像变换，第一基础图像和第二基础图像来生成。 此外，该方法包括使用第一基础图像作为指导，使用一个或多个处理单元执行对第二基础图像的引导处理，以提供修改的第二基本图像。 此外，该方法包括使用第一基础图像和修改的第二基础图像来执行至少一个逆图像变换以生成至少一个修改图像。

公开(公告)号：US20160171648A1

公开(公告)日：2016-06-16

申请号：US14566874

申请日：2014-12-11

Applicant: General Electric Company

Inventor： Jean-Baptiste Thibault ,  Debashish Pal ,  Jie Tang ,  Ken David Sauer ,  Charles Bouman ,  Ruoqiao Zhang

IPC: G06T3/00 ,  G06T5/10 ,  G01N23/087 ,  G01N23/04 ,  G01T1/36

CPC classification number: G01N23/046 ,  G01N23/087 ,  G01N2223/423 ,  G01N2223/501 ,  G01N2223/612 ,  G01T1/36 ,  G06T3/0056 ,  G06T5/002 ,  G06T5/10 ,  G06T7/0012 ,  G06T11/008 ,  G06T2207/10004 ,  G06T2207/10081 ,  G06T2211/408

Abstract: A method includes obtaining spectral computed tomography (CT) information via an acquisition unit having an X-ray source and a CT detector. The method also includes, generating, with one or more processing units, using at least one image transform, a first basis image and a second basis image using the spectral CT information. Further, the method includes performing, with the one or more processing units, guided processing on the second basis image using the first basis image as a guide to provide a modified second basis image. Also, the method includes performing at least one inverse image transform using the first basis image and the modified second basis image to generate at least one modified image.

Abstract translation: 一种方法包括经由具有X射线源和CT检测器的获取单元获得频谱计算机断层摄影（CT）信息。 该方法还包括利用一个或多个处理单元使用频谱CT信息使用至少一个图像变换，第一基础图像和第二基础图像来生成。 此外，该方法包括使用第一基础图像作为指导，使用一个或多个处理单元执行对第二基础图像的引导处理，以提供修改的第二基本图像。 此外，该方法包括使用第一基础图像和修改的第二基础图像来执行至少一个逆图像变换以生成至少一个修改图像。

公开(公告)号：US20140369581A1

公开(公告)日：2014-12-18

申请号：US13918656

申请日：2013-06-14

Applicant: The Regents of the University of Michigan ,  General Electric Company

Inventor： Lin Fu ,  Madison Gray McGaffin ,  Zhou Yu ,  Jean-Baptiste Thibault ,  Sathish Ramani ,  Jeffrey Allen Fessler ,  Bruno Kristiaan Bernard De Man ,  Debashish Pal

IPC: G06T11/00

CPC classification number: G06T11/006 ,  G06T2211/424

Abstract: The use of the channelized preconditioners in iterative reconstruction is disclosed. In certain embodiments, different channels correspond to different frequency sub-bands and the output of the different channels can be combined to update an image estimate used in the iterative reconstruction process. While individual channels may be relatively simple, the combined channels can represent complex spatial variant operations. The use of channelized preconditioners allows empirical adjustment of individual channels.

Abstract translation: 公开了在迭代重建中使用信道化预处理器。 在某些实施例中，不同的信道对应于不同的频率子带，并且可以组合不同信道的输出以更新在迭代重建过程中使用的图像估计。 虽然单个通道可能相对简单，但组合通道可以表示复杂的空间变体操作。 通道化预处理器的使用允许对各个通道进行实证调整。

公开(公告)号：US20140369580A1

公开(公告)日：2014-12-18

申请号：US13918517

申请日：2013-06-14

Applicant: General Electric Company ,  Purdue University ,  The Regents of the University of Michigan

Inventor： Zhou Yu ,  Bruno Kristiaan Bernard De Man ,  Jean-Baptiste Thibault ,  Debashish Pal ,  Lin Fu ,  Charles A. Bouman ,  Jeffrey Allen Fessler ,  Hung Nien

IPC: G06T11/00

CPC classification number: G06T11/006 ,  G06T2211/424 ,  G06T2211/428

Abstract: A framework for an iterative reconstruction algorithm is described which combines two or more of an ordered subset method, a preconditioner method, and a nested loop method. In one type of implementation a nested loop (NL) structure is employed where the inner loop sub-problems are solved using ordered subset (OS) methods. The inner loop may be solved using OS and a preconditioner method. In other implementations, the inner loop problems are created by augmented Lagrangian methods and then solved using OS method.

Abstract translation: 描述了一种迭代重建算法的框架，其结合有序子集方法，预处理器方法和嵌套循环方法中的两个或更多个。 在一种类型的实现中，使用嵌套循环（NL）结构，其中使用有序子集（OS）方法来解决内循环子问题。 可以使用OS和预处理器方法来解决内循环。 在其他实现中，内循环问题是通过增强拉格朗日方法产生的，然后使用OS方法求解。

公开(公告)号：US20140369463A1

公开(公告)日：2014-12-18

申请号：US13918215

申请日：2013-06-14

Applicant: General Electric Company ,  Purdue Research Foundation ,  University of Notre Dame du Lac

Inventor： Jean-Baptiste Thibault ,  Xue Rui ,  Somesh Srivastava ,  Ken David Sauer ,  Lin Fu ,  Charles Addison Bouman, JR.

IPC: G06T11/00 ,  G01N23/04

CPC classification number: G01N23/046 ,  A61B6/032 ,  A61B6/5205 ,  G01N2223/1016 ,  G01N2223/419 ,  G06T11/006 ,  G06T2211/424

Abstract: A system and method include acquisition of projection data from a scanned object, the set of projection data comprising a plurality of projection measurements. The system and method also include calculation of a set of modified statistical weights from the projection data, wherein a respective modified statistical weight of the set of modified statistical weights comprises a deviation from an inverse variance of a corresponding projection measurement of the projection data. The system and method further include reconstruction of an image of the scanned object using the set of modified statistical weights as coefficients in an iterative reconstruction algorithm.

Abstract translation: 一种系统和方法包括从扫描对象获取投影数据，该组投影数据包括多个投影测量。 该系统和方法还包括从投影数据计算一组经修改的统计权重，其中修改的统计权重集合的相应修改的统计权重包括与投影数据的相应投影测量的逆方差的偏差。 该系统和方法还包括使用经修改的统计权重的集合来重建扫描对象的图像作为迭代重建算法中的系数。

公开(公告)号：US20190180481A1

公开(公告)日：2019-06-13

申请号：US15840953

申请日：2017-12-13

Applicant: General Electric Company ,  Purdue University ,  Notre Dame University

Inventor： Lin Fu ,  Jean-Baptiste Thibault ,  Somesh Srivastava ,  Charles A. Bouman, Jr. ,  Donghye Ye ,  Amirkoushyar Ziabari ,  Ken Sauer

IPC: G06T11/00 ,  A61B6/03

Abstract: An iterative reconstruction approach is provided that allows the use of differing weights in pixels or larger sub-regions in the reconstructed image. By way of example, the relative significance of each projection measurement may be determined based on both the measurement position and the location of the reconstructed pixel. Computationally, the significance of each projection based on these two factors is represented by a weight factor employed in the algorithmic computation.