公开(公告)号：US07536044B2

公开(公告)日：2009-05-19

申请号：US10991933

申请日：2004-11-18

申请人： Xiang Sean Zhou ,  Bogdan Georgescu ,  Dorin Comaniciu ,  R. Bharat Rao ,  Alok Gupta

发明人： Xiang Sean Zhou ,  Bogdan Georgescu ,  Dorin Comaniciu ,  R. Bharat Rao ,  Alok Gupta

IPC分类号： G06K9/00 ,  G06K9/62

CPC分类号： G06K9/6206 ,  G06K9/6256 ,  G06T7/12 ,  G06T7/149 ,  G06T7/251 ,  G06T2207/10132 ,  G06T2207/30048

摘要： A detection framework that matches anatomical structures using appearance and shape is disclosed. A training set of images are used in which object shapes or structures are annotated in the images. A second training set of images represents negative examples for such shapes and structures, i.e., images containing no such objects or structures. A classification algorithm trained on the training sets is used to detect a structure at its location. The structure is matched to a counterpart in the training set that can provide details about the structure's shape and appearance.

摘要翻译： 公开了一种使用外观和形状匹配解剖结构的检测框架。 使用图像的训练集，其中在图像中注释对象形状或结构。 图像的第二训练集表示这种形状和结构的负面例子，即不包含这样的对象或结构的图像。 训练集训练的分类算法用于检测其位置的结构。 该结构与训练集中的对应物匹配，可以提供关于结构形状和外观的细节。

公开(公告)号：US20070237370A1

公开(公告)日：2007-10-11

申请号：US11539989

申请日：2006-10-10

申请人： Shaohua Zhou ,  Jie Shao ,  Jonathan Dowdall ,  Adrian Barbu ,  Bogdan Georgescu ,  Dorin Comaniciu

发明人： Shaohua Zhou ,  Jie Shao ,  Jonathan Dowdall ,  Adrian Barbu ,  Bogdan Georgescu ,  Dorin Comaniciu

IPC分类号： G06K9/00

CPC分类号： G06K9/6257 ,  G06K2209/05 ,  G06T7/33 ,  G06T2207/10124 ,  G06T2207/10132 ,  G06T2207/30048

摘要： The present invention is directed to a method for populating a database with a set of images of an anatomical structure. The database is used to perform appearance matching in image pairs of the anatomical structure. A set of image pairs of anatomical structures is received, where each image pair is annotated with a plurality of location-sensitive regions that identify a particular aspect of the anatomical structure. Weak learners are iteratively selected and an image patch is identified. A boosting process is used to identify a strong classifier based on responses to the weak learners applied to the identified image patch for each image pair. The responses comprise a feature response and a location response associated with the image patch. Positive and negative image pairs are generated. The positive and negative image pairs are used to learn a similarity function. The learned similarity function and iteratively selected weak learners are stored in the database.

摘要翻译： 本发明涉及一种用解剖结构的一组图像填充数据库的方法。 该数据库用于在解剖结构的图像对中执行外观匹配。 接收一组解剖结构的图像对，其中每个图像对用多个识别解剖结构的特定方面的位置敏感区域注释。 迭代选择弱学习者，并识别图像补丁。 基于对应用于每个图像对的所识别的图像补丁的弱学习者的响应，使用增强过程来识别强分类器。 响应包括与图像块相关联的特征响应和位置响应。 产生正负图像对。 正负图像对用于学习相似度函数。 学习的相似度函数和迭代选择的弱学习者存储在数据库中。

公开(公告)号：US20070071313A1

公开(公告)日：2007-03-29

申请号：US11372782

申请日：2006-03-10

申请人： Shaohua Zhou ,  Bogdan Georgescu ,  Xiang Zhou ,  Dorin Comaniciu

发明人： Shaohua Zhou ,  Bogdan Georgescu ,  Xiang Zhou ,  Dorin Comaniciu

IPC分类号： G06K9/62

CPC分类号： G06K9/6256 ,  G06K2009/00322 ,  G06K2209/05

摘要： A method for performing image based regression using boosting to infer an entity that is associated with an image of an object is disclosed. A regression function for a plurality of images is learned in which for each image the associated entity is known. The learned regression function is used to predict an entity associated with an image in which the entity is not known.

摘要翻译： 公开了一种使用增强来执行基于图像的回归的方法来推断与对象的图像相关联的实体。 学习用于多个图像的回归函数，其中对于每个图像，相关联的实体是已知的。 学习的回归函数用于预测与实体不知道的图像相关联的实体。

公开(公告)号：US20050185826A1

公开(公告)日：2005-08-25

申请号：US11058784

申请日：2005-02-16

申请人： Bogdan Georgescu ,  Xiang Zhou ,  Dorin Comaniciu ,  R. Rao

发明人： Bogdan Georgescu ,  Xiang Zhou ,  Dorin Comaniciu ,  R. Rao

IPC分类号： G06K9/64 ,  G06T7/20 ,  G06K9/00

CPC分类号： G06K9/3216 ,  G06K9/6206 ,  G06T7/215 ,  G06T7/269

摘要： A system and method for tracking an object is disclosed. A video sequence including a plurality of image frames are received. A sample based representation of object appearance distribution is maintained. An object is divided into one or more components. For each component, its location and uncertainty with respect to the sample based representation are estimated. Variable-Bandwidth Density Based Fusion (VBDF) is applied to each component to determine a most dominant motion. The motion estimate is used to determine the track of the object.

摘要翻译： 公开了一种跟踪对象的系统和方法。 接收包括多个图像帧的视频序列。 维护对象外观分布的基于样本的表示。 一个对象被分成一个或多个组件。 对于每个组件，估计其相对于基于样本的表示的位置和不确定性。 基于可变带宽密度的融合（VBDF）应用于每个组件以确定最主要的运动。 运动估计用于确定对象的轨迹。

公开(公告)号：US20190197199A9

公开(公告)日：2019-06-27

申请号：US13754174

申请日：2013-01-30

申请人： Tommaso Mansi ,  Bogdan Georgescu ,  Xudong Zheng ,  Ali Kamen ,  Dorin Comaniciu

发明人： Tommaso Mansi ,  Bogdan Georgescu ,  Xudong Zheng ,  Ali Kamen ,  Dorin Comaniciu

IPC分类号： G06F17/50

CPC分类号： G06F17/5009 ,  A61B5/0044 ,  A61B5/055 ,  A61B8/0883 ,  A61B2576/023 ,  A61N1/3627 ,  A61N1/36514 ,  A61N1/36585 ,  G06T17/00 ,  G06T2210/41 ,  G09B23/30 ,  G16H50/50

摘要： A method and system for patient-specific planning of cardiac therapy, such as cardiac resynchronization therapy (CRT), based on preoperative clinical data and medical images, such as ECG data, magnetic resonance imaging (MRI) data, and ultrasound data, is disclosed. A patient-specific anatomical model of the left and right ventricles is generated from medical image data of a patient. A patient-specific computational heart model, which comprises cardiac electrophysiology, biomechanics and hemodynamics, is generated based on the patient-specific anatomical model of the left and right ventricles and clinical data. Simulations of cardiac therapies, such as CRT at one or more anatomical locations are performed using the patient-specific computational heart model. Changes in clinical cardiac parameters are then computed from the patient-specific model, constituting predictors of therapy outcome useful for therapy planning and optimization.

公开(公告)号：US10321892B2

公开(公告)日：2019-06-18

申请号：US13234697

申请日：2011-09-16

申请人： Yang Wang ,  Bogdan Georgescu ,  Helene C. Houle ,  Dorin Comaniciu

发明人： Yang Wang ,  Bogdan Georgescu ,  Helene C. Houle ,  Dorin Comaniciu

IPC分类号： A61B8/00 ,  A61B8/08 ,  G06T7/246

摘要： Computerized characterization of cardiac wall motion is provided. Quantities for cardiac wall motion are determined from a four-dimensional (i.e., 3D+time) sequence of ultrasound data. A processor automatically processes the volume data to locate the cardiac wall through the sequence and calculate the quantity from the cardiac wall position or motion. Various machine learning is used for locating and tracking the cardiac wall, such as using a motion prior learned from training data for initially locating the cardiac wall and the motion prior, speckle tracking, boundary detection, and mass conservation cues for tracking with another machine learned classifier. Where the sequence extends over multiple cycles, the cycles are automatically divided for independent tracking of the cardiac wall. The cardiac wall from one cycle may be used to propagate to another cycle for initializing the tracking. Independent tracking in each cycle may reduce or avoid inaccuracies due to drift.

公开(公告)号：US10296809B2

公开(公告)日：2019-05-21

申请号：US13780230

申请日：2013-02-28

申请人： Saikiran Rapaka ,  Tommaso Mansi ,  Bogdan Georgescu ,  Ali Kamen ,  Dorin Comaniciu

发明人： Saikiran Rapaka ,  Tommaso Mansi ,  Bogdan Georgescu ,  Ali Kamen ,  Dorin Comaniciu

IPC分类号： G16H50/50 ,  G06F17/50 ,  G06K9/62 ,  G06T7/143 ,  G06T7/149 ,  G06K9/00

摘要： A method and system for patient-specific cardiac electrophysiology is disclosed. Particularly, a patient-specific anatomical model of a heart is generated from medical image data of a patient, a level-set representation of the patient-specific anatomical model is generated of the heart on a Cartesian grid; and a transmembrane action potential at each node of the level-set representation of the of the patient-specific anatomical model of the heart is computed on a Cartesian grid.

公开(公告)号：US09405996B2

公开(公告)日：2016-08-02

申请号：US12562454

申请日：2009-09-18

申请人： Razvan Ionasec ,  Bogdan Georgescu ,  Yefeng Zheng ,  Dorin Comaniciu

发明人： Razvan Ionasec ,  Bogdan Georgescu ,  Yefeng Zheng ,  Dorin Comaniciu

IPC分类号： G06G7/48 ,  G06K9/62 ,  G06F19/00 ,  G06T7/00 ,  G06T13/20 ,  G06T17/00

CPC分类号： G06K9/6256 ,  G06F19/00 ,  G06F19/321 ,  G06K2209/051 ,  G06T7/12 ,  G06T7/149 ,  G06T13/20 ,  G06T17/00 ,  G06T2207/30048 ,  G06T2210/41 ,  G16H50/50

摘要： A method and system for generating a patient specific anatomical heart model is disclosed. Volumetric image data, such as computed tomography (CT) or echocardiography image data, of a patient's cardiac region is received. Individual models for multiple heart components, such as the left ventricle (LV) endocardium, LV epicardium, right ventricle (RV), left atrium (LA), right atrium (RA), mitral valve, aortic valve, aorta, and pulmonary trunk, are estimated in said volumetric cardiac image data. A patient specific anatomical heart model is generated by integrating the individual models for each of the heart components.

摘要翻译： 公开了一种用于产生患者特异性解剖心脏模型的方法和系统。 接收患者心脏区域的体积图像数据，例如计算机断层扫描（CT）或超声心动图像数据。 用于多个心脏组件的单独模型，例如左心室（LV）心内膜，LV心外膜，右心室（RV），左心房（LA），右心房（RA），二尖瓣，主动脉瓣，主动脉和肺动脉干， 在所述体积心脏图像数据中估计。 患者特异性解剖心脏模型是通过对每个心脏部件的各个模型进行整合来产生的。

公开(公告)号：US08934693B2

公开(公告)日：2015-01-13

申请号：US13682820

申请日：2012-11-21

申请人： Sasa Grbic ,  Razvan Ioan Ionasec ,  Fernando Vega-Higuera ,  Dominik Bernhardt ,  Bogdan Georgescu ,  Dorin Comaniciu

发明人： Sasa Grbic ,  Razvan Ioan Ionasec ,  Fernando Vega-Higuera ,  Dominik Bernhardt ,  Bogdan Georgescu ,  Dorin Comaniciu

IPC分类号： G06K9/00 ,  G06T7/00

CPC分类号： G06T7/0012 ,  G06T7/75 ,  G06T2207/10081 ,  G06T2207/20081 ,  G06T2207/30048 ,  G06T2207/30101

摘要： A method and system for automated intervention planning for transcatheter aortic valve implantations using computed tomography (CT) data is disclosed. A patient-specific aortic valve model is detected in a CT volume of a patient. The patient-specific aortic valve model is detected by detecting a global location of the patient-specific aortic valve model in the CT volume, detecting aortic valve landmarks based on the detected global location, and fitting an aortic root surface model. Angulation parameters of a C-arm imaging device for acquiring intra-operative fluoroscopic images and anatomical measurements of the aortic valve are automatically determined based on the patient-specific aortic valve model.

摘要翻译： 公开了一种使用计算机断层扫描（CT）数据进行经导管主动脉瓣植入术的自动干预计划的方法和系统。 在患者的CT体积中检测患者特异性主动脉瓣模型。 通过检测CT体积中患者特异性主动脉瓣模型的全局位置检测患者特异性主动脉瓣模型，根据检测到的全局位置检测主动脉瓣标志，并配合主动脉根部表面模型。 基于患者特异性主动脉瓣模型自动确定用于获取手术中透视图像和主动脉瓣的解剖学测量的C形臂成像装置的角度参数。

公开(公告)号：US08771189B2

公开(公告)日：2014-07-08

申请号：US12702036

申请日：2010-02-08

申请人： Razvan Ioan Ionasec ,  Ingmar Voigt ,  Yang Wang ,  Bogdan Georgescu ,  Helene C. Houle ,  Dorin Comaniciu ,  Fernando Vega-Higuera

发明人： Razvan Ioan Ionasec ,  Ingmar Voigt ,  Yang Wang ,  Bogdan Georgescu ,  Helene C. Houle ,  Dorin Comaniciu ,  Fernando Vega-Higuera

IPC分类号： A61B8/00

CPC分类号： G06T7/0016 ,  G06T7/251 ,  G06T7/262 ,  G06T7/277 ,  G06T2207/10016 ,  G06T2207/10076 ,  G06T2207/10136 ,  G06T2207/20016 ,  G06T2207/30048 ,  G06T2207/30241

摘要： Heart valve operation is assessed with patient-specific medical diagnostic imaging data. To deal with the complex motion of the passive valve tissue, a hierarchal model is used. Rigid global motion of the overall valve, non-rigid local motion of landmarks of the valve, and surface motion of the valve are modeled sequentially. For the non-rigid local motion, a spectral trajectory approach is used in the model to determine location and motion of the landmarks more efficiently than detection and tracking. Given efficiencies in processing, more than one valve may be modeled at a same time. A graphic overlay representing the valve in four dimensions and/or quantities may be provided during an imaging session. One or more of these features may be used in combination or independently.

摘要翻译： 心脏瓣膜手术用患者特定的医学诊断成像数据进行评估。 为了处理被动瓣膜组织的复杂运动，使用了层次模型。 总体阀门的刚性全局运动，阀门的标志的非刚性局部运动以及阀门的表面运动被依次建模。 对于非刚性局部运动，在模型中使用频谱轨迹方法，以比检测和跟踪更有效地确定地标的位置和运动。 在处理效率方面，可以同时对多个阀进行建模。 可以在成像会话期间提供表示四维和/或数量的阀的图形覆盖。 这些特征中的一个或多个可以组合使用或独立使用。