专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

91. 发明授权

US08515200B2 System, software arrangement and method for segmenting an image 有权
标题翻译：用于分割图像的系统，软件安排和方法
公开(公告)号：US08515200B2
公开(公告)日：2013-08-20
申请号：US11264775
申请日：2005-10-31
申请人： Artem Mikheev , Henry Rusinek
发明人： Artem Mikheev , Henry Rusinek
IPC分类号： G06K9/42 , G06K9/00
CPC分类号： G06K9/4638 , A61B5/055 , A61B6/03 , G06K2209/05 , G06T7/12 , G06T2207/10081 , G06T2207/10088 , G06T2207/20036 , G06T2207/20104 , G06T2207/30016 , G06T2207/30032
摘要： A logic arrangement, system and method for segmentation using magnetic resonance imaging (“MRI”) are provided. For example, as an end product, an image associated with at least one portion of an anatomical structure is generated. In particular, first data associated with the at least one portion of the anatomical structure is received. Second data can be associated with at least one edge of at least one of the at least one portion is obtained based on the first data. The image can be generated based on the first data and the second data. In addition or as an alternative, it is also possible to generate the image using connected voxel components. Such components are created by processing information associated with an erosion of surface voxels of an image.
摘要翻译：提供了使用磁共振成像（“MRI”）进行分割的逻辑布置，系统和方法。例如，作为最终产品，生成与解剖结构的至少一部分相关联的图像。特别地，接收与解剖结构的至少一个部分相关联的第一数据。第二数据可以与基于第一数据获得的至少一个部分中的至少一个的至少一个边缘相关联。可以基于第一数据和第二数据生成图像。另外或作为替代，也可以使用连接的体元分量来生成图像。通过处理与图像的表面体素的侵蚀相关联的信息来创建这些组件。

92. 发明申请

US20130156337A1 METHOD FOR REMOVING NOISE OF IMAGE 审中-公开
标题翻译：消除图像噪声的方法
公开(公告)号：US20130156337A1
公开(公告)日：2013-06-20
申请号：US13420535
申请日：2012-03-14
申请人： Tae Hyeon Kwon , In Taek Song , Kyoung Joong Min
发明人： Tae Hyeon Kwon , In Taek Song , Kyoung Joong Min
IPC分类号： G06K9/40
CPC分类号： G06K9/40 , G06K9/00791 , G06K9/4638 , G06T5/002 , G06T7/13 , G06T2207/20192
摘要： A method for removing noise of an image. The method includes: (a) detecting a horizontal edge by applying a horizontal edge detection filter to a predetermined pixel field including a notice pixel and neighboring pixel in a vertical direction in image data; (b) judging whether horizontal line noise exists in the predetermined pixel field through the horizontal edge; (c) calculating the number of pixels determined as the horizontal line noise for each horizontal line of the image data by applying steps (a) and (b) to all horizontal lines of the image data; and (d) removing the horizontal line noise by applying a low pass filter to the horizontal line judged to have the horizontal line noise according to the calculation result of step (c).
摘要翻译：一种去除图像噪声的方法。该方法包括：（a）通过在水平边缘检测滤波器中对包括图像数据中的垂直方向上的通知像素和相邻像素的预定像素场进行检测来检测水平边缘; （b）通过水平边缘判断在预定像素场中是否存在水平线噪声; （c）通过对图像数据的所有水平行应用步骤（a）和（b））来计算确定为图像数据的每条水平线的水平线噪声的像素数量; 以及（d）根据步骤（c）的计算结果，对被判断为具有水平线噪声的水平线施加低通滤波器来去除水平线噪声。

93. 发明授权

US08433113B2 Automatic recovery of the left ventricular blood pool in cardiac cine magnetic resonance images 有权
标题翻译：自动恢复心肌电磁共振图像中的左心室血液池
公开(公告)号：US08433113B2
公开(公告)日：2013-04-30
申请号：US12398425
申请日：2009-03-05
申请人： Marie-Pierre Jolly
发明人： Marie-Pierre Jolly
IPC分类号： G06K9/00
CPC分类号： G06K9/342 , G06K9/4638 , G06K2209/05 , G06T7/12 , G06T7/162 , G06T2207/10076 , G06T2207/30048 , G06T2207/30101
摘要： An exemplary embodiment of the present invention includes a method of detecting a left ventricle blood pool. The method includes: localizing a region of interest (ROI) in a three-dimensional temporal (3D+T) image based on motion information of each slice of the 3D image over time, thresholding the ROI to determine pixels of the ROI that correspond to blood, extracting connected components from the determined pixels, clustering the extracted connected components into groups based on criteria that are indicative of a blood pool of a left ventricle, and selecting one of the groups as the left ventricle blood pool.
摘要翻译：本发明的示例性实施例包括检测左心室血液池的方法。该方法包括：基于3D图像的每个片段的运动信息，在三维时间（3D + T）图像中定位感兴趣区域（ROI），阈值化ROI以确定ROI对应的ROI的像素血液，从确定的像素中提取连接的组分，基于指示左心室血液池的标准，将所提取的连接的组件聚类成组，并且选择组中的一组作为左心室血液池。

94. 发明授权

US08358845B2 Method for labeling connected components and computer system using the method 失效
标题翻译：使用该方法标记连接组件和计算机系统的方法
公开(公告)号：US08358845B2
公开(公告)日：2013-01-22
申请号：US12837515
申请日：2010-07-16
申请人： Chin-Shyurng Fahn , Keng-Li Lin
发明人： Chin-Shyurng Fahn , Keng-Li Lin
IPC分类号： G06K9/34 , G06K9/00
CPC分类号： G06K9/4638 , G06T7/11 , G06T7/187
摘要： A method for labeling connected components and a computer system using the method are provided. With the method, during a process of scanning an image for the first time, each object pixel in the image is assigned a temporary label, and a relationship between each temporary label and a representative label is established after the completion of the process of scanning the image for the first time. Thereafter, the temporary label of each object pixel is replaced by the corresponding representative label during a process of scanning the image for the second time. As a result, the labeling of the connected components can be accomplished by only scanning the image twice such that the efficiency of labeling the connected components can be significantly improved.
摘要翻译：提供了一种使用该方法标记连接的部件和计算机系统的方法。使用该方法，在第一次扫描图像的处理期间，向图像中的每个对象像素分配临时标签，并且在扫描完成之后建立每个临时标签与代表标签之间的关系形象第一次。此后，在第二次扫描图像的处理期间，由相应的代表标签替换每个对象像素的临时标签。结果，可以通过仅扫描图像两次来实现连接的部件的标记，使得可以显着地提高对连接部件的标记效率。

95. 发明申请

US20120321169A1 Shape Based Conditional Random Fields for Segmenting Intracranial Aneurysms 有权
标题翻译：基于形状的条件随机场分割颅内动脉瘤
公开(公告)号：US20120321169A1
公开(公告)日：2012-12-20
申请号：US13456542
申请日：2012-05-30
申请人： Sajjad Hussain Baloch , Erkang Cheng , Tong Fang , Ying Zhu
发明人： Sajjad Hussain Baloch , Erkang Cheng , Tong Fang , Ying Zhu
IPC分类号： G06K9/34
CPC分类号： G06T7/0083 , G06K9/4638 , G06K9/468 , G06K2209/05 , G06T7/12 , G06T7/143 , G06T7/149 , G06T2207/10072 , G06T2207/20076 , G06T2207/20124 , G06T2207/30101
摘要： A method for segmenting intracranial aneurysms in digital medical images includes extracting a mesh representing a vessel surface from a volumetric digital image, the mesh comprising a set of points {pi} and edges {eij} respective points, and finding a set of binary labelings that minimizes an energy functional of the labelings and of shape descriptors of each point in the mesh, where the binary labelings segments an aneurysm from the surface by associating one of two labels with each point pi, where a label indicates whether an associated point is on a vessel or on an aneurysm, where the energy functional includes a unary potential term summed over all points that represent a posterior distribution of the labels over the points, and a pairwise potential term summed over all edges that represents neighborhood labeling relationships.
摘要翻译：用于在数字医学图像中分割颅内动脉瘤的方法包括从体积数字图像中提取表示血管表面的网格，所述网格包括一组点{pi}和边缘{eij}各自的点，并且找到一组二进制标记，最小化网格中每个点的标签和形状描述符的能量功能，其中二进制标签通过将两个标签中的一个与每个点pi相关联来从表面分割动脉瘤，其中标签指示关联点是否在血管或动脉瘤，其中能量功能包括表示标记在点上的后验分布的所有点上的一元潜在项，以及表示邻域标记关系的所有边缘上的成对潜在项。

96. 发明授权

US08306111B2 Image analysis using a hybrid connected component labeling process 有权
标题翻译：使用混合连接组件标注过程的图像分析
公开(公告)号：US08306111B2
公开(公告)日：2012-11-06
申请号：US12456226
申请日：2009-06-11
申请人： Sheng-Yan Yang , Chih-Hao Chang
发明人： Sheng-Yan Yang , Chih-Hao Chang
IPC分类号： H04N11/02 , H04N7/18
CPC分类号： G06K9/4638
摘要： A hybrid connected component labeling process for analyzing digitized or binary images includes the following steps. Firstly, a forward scan is executed to assign a forward label to each foreground pixel in the image. Then, a backward scan is executed to assign a backward label to each foreground. The backward labels are rearranged and label connection is recorded. A label allocation table including final labels and reference labels is provided for recording the use of the labels. When an object is considered as noise, the label corresponds to the pixels of the object is released by updating the label allocation table.
摘要翻译：用于分析数字化或二进制图像的混合连接分量标记过程包括以下步骤。首先，执行正向扫描以向图像中的每个前景像素分配前向标签。然后，执行反向扫描以向每个前景分配反向标签。重新排列后退标签，并记录标签连接。提供包括最终标签和参考标签的标签分配表，用于记录标签的使用。当对象被视为噪声时，标签对应于通过更新标签分配表来释放对象的像素。

97. 发明申请

US20120237094A1 NETWORK CONSTRUCTION APPARATUS, METHOD AND PROGRAM 有权
标题翻译：网络结构设备，方法与程序
公开(公告)号：US20120237094A1
公开(公告)日：2012-09-20
申请号：US13422576
申请日：2012-03-16
申请人： Yuichi KURIHARA , Yoshiro KITAMURA
发明人： Yuichi KURIHARA , Yoshiro KITAMURA
IPC分类号： G06K9/46
CPC分类号： G06K9/4638 , G06T7/13 , G06T7/162 , G06T7/181 , G06T2207/20164 , G06T2207/30101
摘要： A likelihood of a cross segment is calculated based on a cross segment characteristic condition defining a characteristic that a portion corresponding to an intermingled portion of a structure is present as a cross segment, and that at least two pairs of segments connectable in a straight line are present in the neighborhood of the cross segment. A likelihood of a straight line representing a probability that each segment is connected, in a straight line, to another segment is calculated based on a straight line connection condition defining a characteristic that each segment is connected, in a straight line, to another segment in the neighborhood thereof. A strength of connection between the segments is set based on the likelihood of a cross segment and the likelihood of a straight line, and plural network structures are constructed by connecting the segments based on the strength of connection.
摘要翻译：基于定义与结构的混合部分对应的部分作为横截面存在的特征的横截面特征条件来计算横截面的可能性，并且可以在直线上连接的至少两对分段是目前在交叉段附近。基于直线连接条件计算出直线表示每个段以直线连接到另一段的概率的可能性，该直线连接条件将每个段以直线连接在一条直线上的特性连接到另一段其邻里。基于跨段的可能性和直线的可能性来设定段之间的连接强度，并且基于连接的强度通过连接段来构造多个网络结构。

98. 发明授权

US08260020B2 Image based computed tomography number and volume corrections for thin objects in computed tomography systems 有权
标题翻译：基于图像的计算机断层扫描数量和计算机断层摄影系统中薄物体的体积校正
公开(公告)号：US08260020B2
公开(公告)日：2012-09-04
申请号：US12130269
申请日：2008-05-30
申请人： Walter Garms
发明人： Walter Garms
IPC分类号： G06K9/00
CPC分类号： G06K9/4638 , G06T7/62 , G06T2207/10081 , G06T2207/30112
摘要： Methods, apparatuses, and computer-readable media are provided for image based CT Number and volume corrections for thin objects in computed tomography systems. For example, in one embodiment a method is provide which computes an average computed tomography (“CT”) value and volume of voxels that are part of an object. Thereafter, a surface area and a surface CT Number, a boundary area and a boundary CT Number, and a corrected CT Number and a corrected volume for the object are computed. Embodiments of the invention also include other methods, computer-readable mediums, apparatuses, and systems that contain features similar to the features in the above described method.
摘要翻译：为计算机断层摄影系统中的薄物体提供了基于图像的CT数量和体积校正的方法，装置和计算机可读介质。例如，在一个实施例中，提供了一种计算作为对象的一部分的体素的平均计算机断层摄影（“CT”）值和体积的方法。此后，计算表面积和表面CT数，边界区域和边界CT数，以及校正的CT数量和对象的修正体积。本发明的实施例还包括其它方法，计算机可读介质，装置和系统，其包含与上述方法中的特征相似的特征。

99. 发明授权

US08249366B2 Multi-label multi-instance learning for image classification 有权
标题翻译：用于图像分类的多标签多实例学习
公开(公告)号：US08249366B2
公开(公告)日：2012-08-21
申请号：US12140247
申请日：2008-06-16
申请人： Tao Mei , Xian-Sheng Hua , Shipeng Li , Zheng-Jun Zha
发明人： Tao Mei , Xian-Sheng Hua , Shipeng Li , Zheng-Jun Zha
IPC分类号： G06K9/00
CPC分类号： G06K9/4638 , G06K9/342
摘要： Described is a technology by which an image is classified (e.g., grouped and/or labeled), based on multi-label multi-instance data learning-based classification according to semantic labels and regions. An image is processed in an integrated framework into multi-label multi-instance data, including region and image labels. The framework determines local association data based on each region of an image. Other multi-label multi-instance data is based on relationships between region labels of the image, relationships between image labels of the image, and relationships between the region and image labels. These data are combined to classify the image. Training is also described.
摘要翻译：基于根据语义标签和区域的基于多标签多实例数据学习的分类，描述了图像被分类（例如，分组和/或标记）的技术。图像在集成框架中被处理成多标签多实例数据，包括区域和图像标签。该框架基于图像的每个区域确定局部关联数据。其他多标签多实例数据基于图像的区域标签之间的关系，图像的图像标签之间的关系以及区域和图像标签之间的关系。组合这些数据以对图像进行分类。培训也被描述。

100. 发明授权

US08229201B2 Systems, methods and apparatus for plaque visualization and quantification using fuzzy and adaptive region classes 有权
标题翻译：使用模糊和自适应区域类别的斑块可视化和量化的系统，方法和装置
公开(公告)号：US08229201B2
公开(公告)日：2012-07-24
申请号：US11764150
申请日：2007-06-15
申请人： Paul E. Licato
发明人： Paul E. Licato
IPC分类号： G06K9/00
CPC分类号： G06K9/4638 , G06K2209/05 , G06T7/0012 , G06T2207/10081 , G06T2207/30101
摘要： Systems, methods and apparatus are provided through which carotid plaque is classified in an image and visually displayed using an iterative adaptive process, such as an expectation maximization process.
摘要翻译：提供了系统，方法和装置，颈动脉斑块被分类到图像中并且使用迭代自适应过程（例如期望最大化过程）进行视觉显示。

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