专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20130136322A1 Image-Based Detection Using Hierarchical Learning 有权
标题翻译：基于图像的检测使用分层学习
公开(公告)号：US20130136322A1
公开(公告)日：2013-05-30
申请号：US13553860
申请日：2012-07-20
申请人： Yiqiang Zhan , Maneesh Dewan , Xiang Sean Zhou
发明人： Yiqiang Zhan , Maneesh Dewan , Xiang Sean Zhou
IPC分类号： G06K9/00
CPC分类号： G06T7/73 , G06K2209/055 , G06T2207/20081 , G06T2207/20084 , G06T2207/30012
摘要： Systems and methods are provided for detecting anatomical components in images. In accordance with one implementation, at least one anchor landmark is detected in an image. The position of the anchor landmark is used to detect at least one bundle landmark in the image. In accordance with another implementation, at least two neighboring landmarks are detected in an image, and used to detect at least one anatomical primitive in the image.
摘要翻译：提供了用于检测图像中的解剖组件的系统和方法。根据一个实施方式，在图像中检测至少一个锚地标。锚地标的位置用于检测图像中的至少一个束标记。根据另一实现方式，在图像中检测至少两个相邻的界标，并且用于检测图像中的至少一个解剖图元。

2. 发明授权

US07876943B2 System and method for lesion detection using locally adjustable priors 有权
标题翻译：使用局部可调节先验的病变检测系统和方法
公开(公告)号：US07876943B2
公开(公告)日：2011-01-25
申请号：US12241183
申请日：2008-09-30
申请人： Anna Jerebko , Marcos Salganicoff , Maneesh Dewan , Harald Steck
发明人： Anna Jerebko , Marcos Salganicoff , Maneesh Dewan , Harald Steck
IPC分类号： G06K9/00 , A61B5/00
CPC分类号： G06K9/6278 , G06K2209/05 , G06K2209/053 , G06T7/0012 , G06T7/11 , G06T7/143 , G06T2207/30028 , G06T2207/30061
摘要： According to an aspect of the invention, a method for training a classifier for classifying candidate regions in computer aided diagnosis of digital medical images includes providing a training set of annotated images, each image including one or more candidate regions that have been identified as suspicious, deriving a set of descriptive feature vectors, where each candidate region is associated with a feature vector. A subset of the features are conditionally dependent, and the remaining features are conditionally independent. The conditionally independent features are used to train a naïve Bayes classifier that classifies the candidate regions as lesion or non-lesion. A joint probability distribution that models the conditionally dependent features, and a prior-odds probability ratio of a candidate region being associated with a lesion are determined from the training images. A new classifier is formed from the naïve Bayes classifier, the joint probability distribution, and the prior-odds probability ratio.
摘要翻译：根据本发明的一个方面，一种训练分类器的方法，用于对数字医学图像的计算机辅助诊断中的候选区域进行分类，包括提供注释图像的训练集，每个图像包括已被识别为可疑的一个或多个候选区域，导出一组描述性特征向量，其中每个候选区域与特征向量相关联。特征的子集有条件依赖，其余的特征是有条件的独立的。条件独立的特征用于训练将候选区域分类为病变或非损伤的朴素贝叶斯分类器。从训练图像确定与条件相关特征建模的联合概率分布以及与病变相关联的候选区域的先验概率概率。从初始贝叶斯分类器，联合概率分布和先验概率概率比构成新的分类器。

3. 发明申请

US20100232686A1 HIERARCHICAL DEFORMABLE MODEL FOR IMAGE SEGMENTATION 有权
标题翻译：用于图像分割的分层可变模型
公开(公告)号：US20100232686A1
公开(公告)日：2010-09-16
申请号：US12723909
申请日：2010-03-15
申请人： Maneesh Dewan , Yiqiang Zhan , Xiang Sean Zhou , Zhao Yi
发明人： Maneesh Dewan , Yiqiang Zhan , Xiang Sean Zhou , Zhao Yi
IPC分类号： G06K9/62 , G06K9/34
CPC分类号： G06K9/6219 , G06K9/6209 , G06K2209/051 , G06T7/12 , G06T7/149 , G06T7/174 , G06T2207/20081 , G06T2207/30004
摘要： Described herein is a technology for facilitating deformable model-based segmentation of image data. In one implementation, the technology includes receiving training image data (202) and automatically constructing a hierarchical structure (204) based on the training image data. At least one spatially adaptive boundary detector is learned based on a node of the hierarchical structure (206).
摘要翻译：这里描述的是用于促进图像数据的基于可变形模型的分割的技术。在一个实现中，该技术包括基于训练图像数据接收训练图像数据（202）并自动构建分层结构（204）。基于分层结构的节点（206），学习至少一个空间自适应边界检测器。

4. 发明申请

US20100034440A1 Anatomical Primitive Detection 有权
标题翻译：解剖原始检测
公开(公告)号：US20100034440A1
公开(公告)日：2010-02-11
申请号：US12507991
申请日：2009-07-23
申请人： Yiqiang Zhan , Maneesh Dewan , Zhigang Peng , Xiang Sean Zhou
发明人： Yiqiang Zhan , Maneesh Dewan , Zhigang Peng , Xiang Sean Zhou
IPC分类号： G06K9/00
CPC分类号： G06T7/33 , G06T2207/10088 , G06T2207/20076 , G06T2207/30004
摘要： A method of detecting an anatomical primitive in an image volume includes detecting a plurality of transformationally invariant points (TIPS) in the volume, aligning the volume using the TIPs, detecting a plurality landmark points in the aligned volume that are indicative of a given anatomical object, and fitting a target geometric primitive as the anatomical primitive based using the detected landmark points.
摘要翻译：检测图像体积中的解剖学原语的方法包括检测体积中的多个变形不变点（TIPS），使用TIP对齐体积，检测对准的体积中指示给定解剖对象的多个界标点并且使用检测到的地标点将目标几何基元拟合为解剖基元。

5. 发明申请

US20090092300A1 System and Method for Lesion Detection Using Locally Adjustable Priors 有权
标题翻译：使用局部可调节的病变检测系统和方法
公开(公告)号：US20090092300A1
公开(公告)日：2009-04-09
申请号：US12241183
申请日：2008-09-30
申请人： Anna Jerebko , Marcos Salganicoff , Maneesh Dewan , Harald Steck
发明人： Anna Jerebko , Marcos Salganicoff , Maneesh Dewan , Harald Steck
IPC分类号： G06K9/00
CPC分类号： G06K9/6278 , G06K2209/05 , G06K2209/053 , G06T7/0012 , G06T7/11 , G06T7/143 , G06T2207/30028 , G06T2207/30061
摘要： According to an aspect of the invention, a method for training a classifier for classifying candidate regions in computer aided diagnosis of digital medical images includes providing a training set of annotated images, each image including one or more candidate regions that have been identified as suspicious, deriving a set of descriptive feature vectors, where each candidate region is associated with a feature vector. A subset of the features are conditionally dependent, and the remaining features are conditionally independent. The conditionally independent features are used to train a naïve Bayes classifier that classifies the candidate regions as lesion or non-lesion. A joint probability distribution that models the conditionally dependent features, and a prior-odds probability ratio of a candidate region being associated with a lesion are determined from the training images. A new classifier is formed from the naïve Bayes classifier, the joint probability distribution, and the prior-odds probability ratio.
摘要翻译：根据本发明的一个方面，一种训练分类器的方法，用于对数字医学图像的计算机辅助诊断中的候选区域进行分类，包括提供注释图像的训练集，每个图像包括已被识别为可疑的一个或多个候选区域，导出一组描述性特征向量，其中每个候选区域与特征向量相关联。特征的子集有条件依赖，其余的特征是有条件的独立的。条件独立的特征用于训练将候选区域分类为病变或非损伤的朴素贝叶斯分类器。从训练图像确定与条件相关特征建模的联合概率分布以及与病变相关联的候选区域的先验概率概率。从初始贝叶斯分类器，联合概率分布和先验概率概率比构成新的分类器。

6. 发明授权

US08577130B2 Hierarchical deformable model for image segmentation 有权
标题翻译：图像分割的层次可变形模型
公开(公告)号：US08577130B2
公开(公告)日：2013-11-05
申请号：US12723909
申请日：2010-03-15
申请人： Maneesh Dewan , Yiqiang Zhan , Xiang Sean Zhou , Zhao Yi
发明人： Maneesh Dewan , Yiqiang Zhan , Xiang Sean Zhou , Zhao Yi
IPC分类号： G06K9/62
CPC分类号： G06K9/6219 , G06K9/6209 , G06K2209/051 , G06T7/12 , G06T7/149 , G06T7/174 , G06T2207/20081 , G06T2207/30004
摘要： Described herein is a technology for facilitating deformable model-based segmentation of image data. In one implementation, the technology includes receiving training image data (202) and automatically constructing a hierarchical structure (204) based on the training image data. At least one spatially adaptive boundary detector is learned based on a node of the hierarchical structure (206).
摘要翻译：这里描述的是用于促进图像数据的基于可变形模型的分割的技术。在一个实现中，该技术包括基于训练图像数据接收训练图像数据（202）并自动构建分层结构（204）。基于分层结构的节点（206），学习至少一个空间自适应边界检测器。

7. 发明授权

US08406494B2 Anatomical primitive detection 有权
标题翻译：解剖原始检测
公开(公告)号：US08406494B2
公开(公告)日：2013-03-26
申请号：US12507991
申请日：2009-07-23
申请人： Yiqiang Zhan , Maneesh Dewan , Zhigang Peng , Xiang Sean Zhou
发明人： Yiqiang Zhan , Maneesh Dewan , Zhigang Peng , Xiang Sean Zhou
IPC分类号： G06K9/00 , G06K9/32
CPC分类号： G06T7/33 , G06T2207/10088 , G06T2207/20076 , G06T2207/30004
摘要： A method of detecting an anatomical primitive in an image volume includes detecting a plurality of transformationally invariant points (TIPS) in the volume, aligning the volume using the TIPs, detecting a plurality landmark points in the aligned volume that are indicative of a given anatomical object, and fitting a target geometric primitive as the anatomical primitive based using the detected landmark points.
摘要翻译：检测图像体积中的解剖学原语的方法包括检测体积中的多个变形不变点（TIPS），使用TIP对齐体积，检测对准的体积中指示给定解剖对象的多个界标点并且使用检测到的地标点将目标几何基元拟合为解剖基元。

8. 发明申请

US20110044534A1 HIERARCHICAL CLASSIFIER FOR DATA CLASSIFICATION 有权
标题翻译：用于数据分类的分层分类器
公开(公告)号：US20110044534A1
公开(公告)日：2011-02-24
申请号：US12887640
申请日：2010-09-22
申请人： Maneesh Dewan , Gerardo Hermosillo Valadez , Zhao Yi , Yiqiang Zhan
发明人： Maneesh Dewan , Gerardo Hermosillo Valadez , Zhao Yi , Yiqiang Zhan
IPC分类号： G06K9/62
CPC分类号： G06K9/6219 , G06K9/6209 , G06K2209/051
摘要： Described herein is a framework for constructing a hierarchical classifier for facilitating classification of digitized data. In one implementation, a divergence measure of a node of the hierarchical classifier is determined. Data at the node is divided into at least two child nodes based on a splitting criterion to form at least a portion of the hierarchical classifier. The splitting criterion is selected based on the divergence measure. If the divergence measure is less than a predetermined threshold value, the splitting criterion comprises a divergence-based splitting criterion which maximizes subsequent divergence after a split. Otherwise, the splitting criterion comprises an information-based splitting criterion which seeks to minimize subsequent misclassification error after the split.
摘要翻译：这里描述了用于构建用于促进数字化数据的分类的分级分类器的框架。在一个实现中，确定分级分类器的节点的发散度量度。基于分割标准将节点处的数据划分为至少两个子节点，以形成分级分类器的至少一部分。基于分歧度量选择分割标准。如果发散度小于预定阈值，则分割标准包括基于发散的分裂标准，其使分裂后的随后发散最大化。否则，分割标准包括基于信息的分割标准，其寻求在分裂之后使随后的错误分类错误最小化。

9. 发明申请

US20060183999A1 Method and system for motion compensation in magnetic resonance (MR) imaging 有权
公开(公告)号：US20060183999A1
公开(公告)日：2006-08-17
申请号：US11313598
申请日：2005-12-21
申请人： Christine Lorenz , Maneesh Dewan
发明人： Christine Lorenz , Maneesh Dewan
IPC分类号： A61B5/05
CPC分类号： G01R33/5673 , A61B5/0037 , A61B5/055 , G01R33/5676
摘要： A method and system are provided for imaging by predicting, from multiple real time MR imaging data, motion of an object and subsequently obtaining high-resolution imaging data of the object using the predicted motion of the object. Thus, the process uses real time images to derive a history of the motion of the object and thereby generate a predicted trajectory of the object and then uses this trajectory to determine the projected position of the object during a subsequent, separate, high-resolution data acquisition phase.

10. 发明授权

US09336457B2 Adaptive anatomical region prediction 有权
标题翻译：自适应解剖区域预测
公开(公告)号：US09336457B2
公开(公告)日：2016-05-10
申请号：US14096206
申请日：2013-12-04
申请人： Vikas C. Raykar , Yiqiang Zhan , Maneesh Dewan , Gerardo Hermosillo Valadez , Zhigang Peng , Xiang Sean Zhou
发明人： Vikas C. Raykar , Yiqiang Zhan , Maneesh Dewan , Gerardo Hermosillo Valadez , Zhigang Peng , Xiang Sean Zhou
IPC分类号： G06K9/62 , G06T7/00
CPC分类号： G06K9/6202 , G06K9/6211 , G06K9/629 , G06T7/33 , G06T2207/10072 , G06T2207/30016 , G06T2207/30096
摘要： Disclosed herein is a framework for facilitating adaptive anatomical region prediction. In accordance with one aspect, a set of exemplar images including annotated first landmarks is received. User definitions of first anatomical regions in the exemplar images are obtained. The framework may detect second landmarks in a subject image. It may further compute anatomical similarity scores between the subject image and the exemplar images based on the first and second landmarks, and predict a second anatomical region in the subject image by adaptively combining the first anatomical regions based on the anatomical similarity scores.
摘要翻译：本文公开了一种用于促进适应性解剖区域预测的框架。根据一个方面，接收包括注释的第一地标的一组示例图像。获得示例图像中的第一解剖区域的用户定义。框架可以检测主题图像中的第二地标。它还可以基于第一和第二界标进一步计算对象图像和样本图像之间的解剖学相似性得分，并且基于解剖学相似性得分来自适应地组合第一解剖区域来预测对象图像中的第二解剖区域。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式