-
1.发明授权Global error minimization in image mosaicking using graph laplacians and its applications in microscopy 有权使用图形拉普拉斯算子的图像拼接中的全局误差最小化及其在显微镜中的应用公开(公告)号：US08983230B2
公开(公告)日：2015-03-17
申请号：US13810940
申请日：2011-07-25
申请人： Parmeshwar Khurd , Rafiou Oketokoun , Ali Kamen , Leo Grady , Hari Sundar , John V. Frangioni , Tejas Gajera
发明人： Parmeshwar Khurd , Rafiou Oketokoun , Ali Kamen , Leo Grady , Hari Sundar , John V. Frangioni , Tejas Gajera
CPC分类号： G06T11/60 , G06T3/0068 , G06T3/4038 , G06T7/32 , G06T2200/32 , G06T2207/10056 , G06T2207/30024
摘要： An image mosaicking method includes performing pairwise registration of a plurality of tiles (101), determining absolute homographies for each of the plurality of tiles according to the pairwise registration (102B), and performing a blending of the plurality of tiles to obtain a stitched image according to the absolute homographies (103).
摘要翻译： 图像拼接方法包括执行多个瓦片（101）的配对注册，根据成对配准（102B）确定多个瓦片中的每一个的绝对同位素，并且执行多个瓦片的混合以获得缝合图像 根据绝对同位素（103）。
-
2.发明申请Global Error Minimization In Image Mosaicking Using Graph Laplacians And Its Applications In Microscopy 有权使用图形拉普拉斯算子的图像拼接中的全局误差最小化及其在显微镜中的应用公开(公告)号：US20130243352A1
公开(公告)日：2013-09-19
申请号：US13810940
申请日：2011-07-25
申请人： Parmeshwar Khurd , Rafiou Oketokoun , Ali Kamen , Leo Grady , Hari Sundar , John V. Frangioni
发明人： Parmeshwar Khurd , Rafiou Oketokoun , Ali Kamen , Leo Grady , Hari Sundar , John V. Frangioni
IPC分类号： G06T11/60
CPC分类号： G06T11/60 , G06T3/0068 , G06T3/4038 , G06T7/32 , G06T2200/32 , G06T2207/10056 , G06T2207/30024
摘要： An image mosaicking method includes performing pairwise registration of a plurality of tiles (101), determining absolute homographies for each of the plurality of tiles according to the pairwise registration (102B), and performing a blending of the plurality of tiles to obtain a stitched image according to the absolute homographies (103)
摘要翻译： 图像拼接方法包括执行多个瓦片（101）的配对注册，根据成对配准（102B）确定多个瓦片中的每一个的绝对同位素，并且执行多个瓦片的混合以获得缝合图像 根据绝对同位素（103）
-
公开(公告)号：US09047660B2
公开(公告)日：2015-06-02
申请号：US13780370
申请日：2013-02-28
CPC分类号： G06T7/0012 , A61B6/5229 , G06K9/0014 , G06K9/469 , G06T7/344 , G06T17/20 , G06T2207/10056 , G06T2207/20072 , G06T2207/30024
摘要： Methods for analyzing biomedical data include: (a) obtaining macroscopic imaging data; (b) obtaining histopathological imaging data; (c) executing a parallel algorithm stored on a non-transient computer-readable medium to compute one or a plurality of network cycle features of a relative neighborhood graph derived from the histopathological imaging data; (d) registering the macroscopic imaging data and the histopathological imaging data; and (e) correlating the macroscopic imaging data and the network cycle features. Systems for analyzing biomedical data and computer readable storage media are described.
摘要翻译： 分析生物医学数据的方法包括：（a）获取宏观成像数据; （b）获得组织病理学成像数据; （c）执行存储在非瞬时计算机可读介质上的并行算法，以计算从组织病理学成像数据导出的相对邻域图的一个或多个网络周期特征; （d）记录宏观成像数据和组织病理学成像数据; 和（e）将宏观成像数据和网络周期特征相关联。 描述用于分析生物医学数据和计算机可读存储介质的系统。
-
公开(公告)号：US20130243292A1
公开(公告)日：2013-09-19
申请号：US13780370
申请日：2013-02-28
IPC分类号： G06T7/00
CPC分类号： G06T7/0012 , A61B6/5229 , G06K9/0014 , G06K9/469 , G06T7/344 , G06T17/20 , G06T2207/10056 , G06T2207/20072 , G06T2207/30024
摘要： Methods for analyzing biomedical data include: (a) obtaining macroscopic imaging data; (b) obtaining histopathological imaging data; (c) executing a parallel algorithm stored on a non-transient computer-readable medium to compute one or a plurality of network cycle features of a relative neighborhood graph derived from the histopathological imaging data; (d) registering the macroscopic imaging data and the histopathological imaging data; and (e) correlating the macroscopic imaging data and the network cycle features. Systems for analyzing biomedical data and computer readable storage media are described.
摘要翻译： 分析生物医学数据的方法包括：（a）获取宏观成像数据; （b）获得组织病理学成像数据; （c）执行存储在非瞬时计算机可读介质上的并行算法，以计算从组织病理学成像数据导出的相对邻域图的一个或多个网络周期特征; （d）记录宏观成像数据和组织病理学成像数据; 和（e）将宏观成像数据和网络周期特征相关联。 描述了用于分析生物医学数据和计算机可读存储介质的系统。
-
5.发明授权Systems and method for automatic prostate localization in MR images using random walker segmentation initialized via boosted classifiers 有权使用通过增强分类器初始化的随机步行器分割的MR图像中的自动前列腺定位的系统和方法公开(公告)号：US08811701B2
公开(公告)日：2014-08-19
申请号：US13291615
申请日：2011-11-08
申请人： Parmeshwar Khurd , Leo Grady , Ali Kamen , Mamadou Diallo , Kalpitkumar Gajera , Peter Gall , Martin Requardt , Berthold Kiefer , Clifford R. Weiss
发明人： Parmeshwar Khurd , Leo Grady , Ali Kamen , Mamadou Diallo , Kalpitkumar Gajera , Peter Gall , Martin Requardt , Berthold Kiefer , Clifford R. Weiss
CPC分类号： G06K9/6226 , G06T7/11 , G06T7/143 , G06T7/194 , G06T2207/10088 , G06T2207/20081 , G06T2207/20156 , G06T2207/30081
摘要： Automatic prostate localization in T2-weighted MR images facilitate labor-intensive cancer imaging techniques. Methods and systems to accurately segment the prostate gland in MR images are provided and address large variations in prostate anatomy and disease, intensity inhomogeneities, and artifacts induced by endorectal coils. A center of the prostate is automatically detected with a boosted classifier trained on intensity based multi-level Gaussian Mixture Model Expectation Maximization (GMM-EM) segmentations of the raw MR images. A shape model is used in conjunction with Multi-Label Random Walker (MLRW) to constrain the seeding process within MLRW.
摘要翻译： T2加权MR图像中的自动前列腺定位有利于劳动密集型癌症成像技术。 提供了准确分割MR图像前列腺的方法和系统，并解决了前列腺解剖和疾病，强度不均匀性以及直肠内线圈引起的假象的巨大变化。 用基于强度的多级高斯混合模型预期最大化（GMM-EM）原始MR图像分段训练的增强分类器自动检测前列腺的中心。 形状模型与多标签随机Walker（MLRW）结合使用，以限制MLRW内的播种过程。
-
6.发明授权Method and system for integrated radiological and pathological information for diagnosis, therapy selection, and monitoring 有权用于诊断，治疗选择和监测的综合放射学和病理学信息的方法和系统公开(公告)号：US09478022B2
公开(公告)日：2016-10-25
申请号：US14240534
申请日：2012-08-22
申请人： Ali Kamen , Leo Grady , Gianluca Paladini , Parmeshwar Khurd , Oliver Kutter , Dorin Comaniciu
发明人： Ali Kamen , Leo Grady , Gianluca Paladini , Parmeshwar Khurd , Oliver Kutter , Dorin Comaniciu
CPC分类号： G06T7/0012 , A61B6/12 , A61B6/463 , A61B6/467 , A61B8/0841 , A61B8/463 , A61B8/465 , A61B8/467 , A61B10/02 , G06F19/00 , G06F19/3481 , G06T2207/30004 , G16H50/20
摘要： A method and system for integrating radiological and pathological information for cancer diagnosis, therapy selection, and monitoring is disclosed. A radiological image of a patient, such as a magnetic resonance (MR), computed tomography (CT), positron emission tomography (PET), or ultrasound image, is received. A location corresponding to each of one or more biopsy samples is determined in the at least one radiological image. An integrated display is used to display a histological image corresponding to the each biopsy samples, the radiological image, and the location corresponding to each biopsy samples in the radiological image. Pathological information and radiological information are integrated by combining features extracted from the histological images and the features extracted from the corresponding locations in the radiological image for cancer grading, prognosis prediction, and therapy selection.
摘要翻译： 公开了用于整合放射学和病理学信息用于癌症诊断，治疗选择和监测的方法和系统。 接收患者的放射学图像，例如磁共振（MR），计算机断层摄影（CT），正电子发射断层摄影（PET）或超声图像。 在至少一个放射图像中确定与一个或多个活检样本中的每一个对应的位置。 使用集成显示器来显示对应于每个活检样本，放射图像和对应于放射图像中的每个活检样本的位置的组织学图像。 通过组合图像提取的特征和从放射图像中相应位置提取的特征，进行癌症分级，预后预测和治疗选择，整合病理信息和放射学信息。
-
7.发明申请Systems and Method for Automatic Prostate Localization in MR Images Using Random Walker Segmentation Initialized Via Boosted Classifiers 有权使用随机步行器分割的MR图像中自动前列腺定位的系统和方法通过增强分类器初始化公开(公告)号：US20130064439A1
公开(公告)日：2013-03-14
申请号：US13291615
申请日：2011-11-08
申请人： Parmeshwar Khurd , Leo Grady , Ali Kamen , Mamadou Diallo , Kalpitkumar Gajera , Peter Gall , Martin Requardt , Berthold Kiefer , Clifford R. Weiss
发明人： Parmeshwar Khurd , Leo Grady , Ali Kamen , Mamadou Diallo , Kalpitkumar Gajera , Peter Gall , Martin Requardt , Berthold Kiefer , Clifford R. Weiss
CPC分类号： G06K9/6226 , G06T7/11 , G06T7/143 , G06T7/194 , G06T2207/10088 , G06T2207/20081 , G06T2207/20156 , G06T2207/30081
摘要： Automatic prostate localization in T2-weighted MR images facilitate labor-intensive cancer imaging techniques. Methods and systems to accurately segment the prostate gland in MR images are provided and address large variations in prostate anatomy and disease, intensity inhomogeneities, and artifacts induced by endorectal coils. A center of the prostate is automatically detected with a boosted classifier trained on intensity based multi-level Gaussian Mixture Model Expectation Maximization (GMM-EM) segmentations of the raw MR images. A shape model is used in conjunction with Multi-Label Random Walker (MLRW) to constrain the seeding process within MLRW.
摘要翻译： T2加权MR图像中的自动前列腺定位有利于劳动密集型癌症成像技术。 提供了准确分割MR图像前列腺的方法和系统，并解决了前列腺解剖和疾病，强度不均匀性以及直肠内线圈引起的假象的巨大变化。 用基于强度的多级高斯混合模型预期最大化（GMM-EM）原始MR图像分段训练的增强分类器自动检测前列腺的中心。 形状模型与多标签随机Walker（MLRW）结合使用，以限制MLRW内的播种过程。
-
公开(公告)号：US20100286517A1
公开(公告)日：2010-11-11
申请号：US12774798
申请日：2010-05-06
申请人： Ali Kamen , Wolfgang Wein , Parmeshwar Khurd , Mamadou Diallo , Ralf Nanke , Jens Fehre , Berthold Kiefer , Martin Requardt , Clifford Weiss
发明人： Ali Kamen , Wolfgang Wein , Parmeshwar Khurd , Mamadou Diallo , Ralf Nanke , Jens Fehre , Berthold Kiefer , Martin Requardt , Clifford Weiss
CPC分类号： A61B10/0241 , A61B8/4254 , A61B34/20 , A61B2017/00274 , A61B2017/00694 , A61B2017/3413 , A61B2018/00547 , A61B2034/105 , A61B2034/107 , A61B2034/2051 , A61B2090/367 , A61B2090/374 , A61B2090/378
摘要： In a method for image guided prostate cancer needle biopsy, a first registration is performed to match a first image of a prostate to a second image of the prostate. Third images of the prostate are acquired and compounded into a three-dimensional (3D) image. The prostate in the compounded 3D image is segmented to show its border. A second registration and then a third registration different from the second registration is performed on distance maps generated from the prostate borders of the first image and the compounded 3D image, wherein the first and second registrations are based on a biomechanical property of the prostate. A region of interest in the first image is mapped to the compounded 3D image or a fourth image of the prostate acquired with the second modality.
摘要翻译： 在用于图像引导的前列腺癌针活检的方法中，首先进行配准以将前列腺的第一图像与前列腺的第二图像相匹配。 获取前列腺的第三图像并将其复合成三维（3D）图像。 复合3D图像中的前列腺被分割以显示其边界。 在从第一图像和复合3D图像的前列腺边界产生的距离图上执行与第二登记不同的第二登记，然后第三登记，其中第一和第二登记基于前列腺的生物力学性质。 将第一图像中的感兴趣区域映射到复合3D图像或用第二模态获取的前列腺的第四图像。
-
公开(公告)号：US09521994B2
公开(公告)日：2016-12-20
申请号：US12774798
申请日：2010-05-06
申请人： Ali Kamen , Wolfgang Wein , Parmeshwar Khurd , Mamadou Diallo , Ralf Nanke , Jens Fehre , Berthold Kiefer , Martin Requardt , Clifford Weiss
发明人： Ali Kamen , Wolfgang Wein , Parmeshwar Khurd , Mamadou Diallo , Ralf Nanke , Jens Fehre , Berthold Kiefer , Martin Requardt , Clifford Weiss
CPC分类号： A61B10/0241 , A61B8/4254 , A61B34/20 , A61B2017/00274 , A61B2017/00694 , A61B2017/3413 , A61B2018/00547 , A61B2034/105 , A61B2034/107 , A61B2034/2051 , A61B2090/367 , A61B2090/374 , A61B2090/378
摘要： In a method for image guided prostate cancer needle biopsy, a first registration is performed to match a first image of a prostate to a second image of the prostate. Third images of the prostate are acquired and compounded into a three-dimensional (3D) image. The prostate in the compounded 3D image is segmented to show its border. A second registration and then a third registration different from the second registration is performed on distance maps generated from the prostate borders of the first image and the compounded 3D image, wherein the first and second registrations are based on a biomechanical property of the prostate. A region of interest in the first image is mapped to the compounded 3D image or a fourth image of the prostate acquired with the second modality.
摘要翻译： 在用于图像引导的前列腺癌针活检的方法中，首先进行配准以将前列腺的第一图像与前列腺的第二图像相匹配。 获取前列腺的第三图像并将其复合成三维（3D）图像。 复合3D图像中的前列腺被分割以显示其边界。 在从第一图像和复合3D图像的前列腺边界产生的距离图上执行与第二登记不同的第二登记，然后第三登记，其中第一和第二登记基于前列腺的生物力学性质。 将第一图像中的感兴趣区域映射到复合3D图像或用第二模态获取的前列腺的第四图像。
-
公开(公告)号：US09305352B2
公开(公告)日：2016-04-05
申请号：US14068276
申请日：2013-10-31
申请人： Sofiene Jenzri , Parmeshwar Khurd
发明人： Sofiene Jenzri , Parmeshwar Khurd
CPC分类号： G06T7/0016 , G06T7/33 , G06T2207/10072 , G06T2207/30048 , G06T2207/30061 , G06T2207/30101
摘要： Deformable, anatomical trees represented by scan data from different times are matched. Coherent point drift (CPD) solved using expectation maximization is enhanced with tangent or other curve information. By including point-curve information, another characteristic than GMM-based probabilities are included in the cost function for matching. The angle information provided by the tangent, normal, or other point-curve measure may more likely match points in one set representing a tree to points in another set representing the tree.
摘要翻译： 由不同时间的扫描数据表示的变形，解剖树匹配。 使用预期最大化解决的相干点漂移（CPD）通过切线或其他曲线信息增强。 通过包含点曲线信息，在用于匹配的成本函数中包括除基于GMM的概率之外的另一个特征。 由切线，正常或其他点曲线测量提供的角度信息可能更有可能将表示树的一组中的点与表示树的另一组中的点匹配。
-
-
-
-
-
-
-
-
-
搜索结果
13 条记录 (耗时 0.023 秒)
