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. 发明授权

US08989471B2 Method and system for automatic rib centerline extraction using learning based deformable template matching 有权
标题翻译：使用基于学习的可变形模板匹配的自动肋骨中心线提取的方法和系统
公开(公告)号：US08989471B2
公开(公告)日：2015-03-24
申请号：US13602730
申请日：2012-09-04
申请人： Dijia Wu , David Liu , Christian Tietjen , Grzegorz Soza , Shaohua Kevin Zhou , Dorin Comaniciu
发明人： Dijia Wu , David Liu , Christian Tietjen , Grzegorz Soza , Shaohua Kevin Zhou , Dorin Comaniciu
IPC分类号： G06K9/00 , G06K9/62 , G06T7/00
CPC分类号： G06K9/6207 , G06T7/12 , G06T7/149 , G06T2207/10072 , G06T2207/20081 , G06T2207/20116 , G06T2207/30008 , G06T2207/30172
摘要： A method and system for extracting rib centerlines in a 3D volume, such as a 3D computed tomography (CT) volume, is disclosed. Rib centerline voxels are detected in the 3D volume using a learning based detector. Rib centerlines or the whole rib cage are then extracted by matching a template of rib centerlines for the whole rib cage to the 3D volume based on the detected rib centerline voxels. Each of the extracted rib centerlines are then individually refined using an active contour model.
摘要翻译：公开了一种用于在3D体积中提取肋骨中心线的方法和系统，例如3D计算机断层摄影（CT）体积。使用基于学习的检测器在3D体积中检测肋中心线体素。然后通过将基于检测到的肋骨中心线体素的整个肋骨架的肋骨中心线的模板与3D体积匹配来提取肋中心线或整个肋骨笼。然后使用主动轮廓模型分别提取每个提取的肋中心线。

2. 发明授权

US08588519B2 Method and system for training a landmark detector using multiple instance learning 有权
标题翻译：使用多实例学习训练地标探测器的方法和系统
公开(公告)号：US08588519B2
公开(公告)日：2013-11-19
申请号：US13228509
申请日：2011-09-09
申请人： David Liu , Shaohua Kevin Zhou , Paul Swoboda , Dorin Comaniciu , Christian Tietjen
发明人： David Liu , Shaohua Kevin Zhou , Paul Swoboda , Dorin Comaniciu , Christian Tietjen
IPC分类号： G06K9/52
CPC分类号： G06K9/6257 , G06K2209/051
摘要： An apparatus and method for training a landmark detector receives training data which includes a plurality of positive training bags, each including a plurality of positively annotated instances, and a plurality of negative training bags, each including at least one negatively annotated instance. Classification function is initialized by training a first weak classifier based on the positive training bags and the negative training bags. All training instances are evaluated using the classification function. For each of a plurality of remaining classifiers, a cost value gradient is calculated based on spatial context information of each instance in each positive bag evaluated by the classification function. A gradient value associated with each of the remaining weak classifiers is calculated based on the cost value gradients, and a weak classifier is selected which has a lowest associated gradient value and given a weighting parameter and added to the classification function.
摘要翻译：用于训练地标检测器的装置和方法接收训练数据，训练数据包括多个正训练袋，每个正训练袋包括多个带有正面注释的实例，以及多个负训练袋，每个包括至少一个负注释实例。基于积极的训练袋和负面训练袋训练第一个弱分类器来初始化分类功能。使用分类函数评估所有训练实例。对于多个剩余分类器中的每一个，基于由分类函数评估的每个正包中的每个实例的空间上下文信息来计算成本值梯度。基于成本值梯度计算与剩余弱分类器中的每一个相关联的梯度值，并且选择具有最低相关梯度值并给出加权参数并加到分类函数的弱分类器。

3. 发明申请

US20130177230A1 IMPLANT POSE DETERMINATION IN MEDICAL IMAGING 有权
标题翻译：在医学成像中的植入位置确定
公开(公告)号：US20130177230A1
公开(公告)日：2013-07-11
申请号：US13735112
申请日：2013-01-07
申请人： Shaolei Feng , Shaohua Kevin Zhou , Gerhard Kleinszig , Rainer Graumann
发明人： Shaolei Feng , Shaohua Kevin Zhou , Gerhard Kleinszig , Rainer Graumann
IPC分类号： G06T7/00
CPC分类号： G06T7/0012 , G06T7/75 , G06T2207/10116 , G06T2207/30052
摘要： The pose of an implant represented in a medical image is determined from the medical image. The x-ray image of the implant is compared to a database of the implant viewed at different poses (e.g., viewed from different directions). The implant pose associated with the best match indicates the pose of the implant in the x-ray image.
摘要翻译：根据医学图像确定在医学图像中表示的植入物的姿势。将植入物的x射线图像与在不同姿势（例如从不同方向观察）观察的植入物的数据库进行比较。与最佳匹配关联的植入姿势表示植入物在X射线图像中的姿态。

4. 发明授权

US08407267B2 Apparatus, method, system and computer-readable medium for storing and managing image data 有权
标题翻译：用于存储和管理图像数据的装置，方法，系统和计算机可读介质
公开(公告)号：US08407267B2
公开(公告)日：2013-03-26
申请号：US12554436
申请日：2009-09-04
申请人： Johannes Feulner , Shaohua Kevin Zhou
发明人： Johannes Feulner , Shaohua Kevin Zhou
IPC分类号： G06F17/30
CPC分类号： G06F19/321 , G06F19/00
摘要： An apparatus, method, system and computer-readable medium store and manage image data with automatic labeling of image data corresponding to body slices, such as obtained by a computed tomography scanner. The labels include a body coordinate value along the body axis. The respective body coordinate value can be determined by comparing received image data sets with reference data sets with known attached coordinate values utilizing pattern recognition techniques. Applications include medical image data management in hospitals or operating and providing medical networks. Queries for images that include particular body regions are processed more efficiently. This results in less local memory required and narrower bandwidth resources of transmission networks.
摘要翻译：一种装置，方法，系统和计算机可读介质利用计算机断层摄影扫描器获得的对身体切片的图像数据进行自动标注来存储和管理图像数据。标签包括身体轴线上的身体坐标值。可以通过使用模式识别技术将接收到的图像数据集与具有已知附加坐标值的参考数据集进行比较来确定相应的身体坐标值。应用包括医院的医学图像数据管理或运营和提供医疗网络。对包含特定身体区域的图像的查询进行更有效的处理。这导致需要较少的本地存储器和较窄的传输网络的带宽资源。

5. 发明申请

US20120203530A1 Method and System for Patient-Specific Computational Modeling and Simulation for Coupled Hemodynamic Analysis of Cerebral Vessels 有权
标题翻译：用于患者特异性计算建模和脑血管耦合血流动力学分析的方法和系统
公开(公告)号：US20120203530A1
公开(公告)日：2012-08-09
申请号：US13366677
申请日：2012-02-06
申请人： Puneet Sharma , Tommaso Mansi , Viorel Mihalef , Jingdan Zhang , David Liu , Shaohua Kevin Zhou , Bogdan Georgescu , Dorin Comaniciu
发明人： Puneet Sharma , Tommaso Mansi , Viorel Mihalef , Jingdan Zhang , David Liu , Shaohua Kevin Zhou , Bogdan Georgescu , Dorin Comaniciu
IPC分类号： G06G7/60
CPC分类号： G06F19/3437 , G06F19/00 , G16H50/50
摘要： A method and system for patient-specific computational modeling and simulation for coupled hemodynamic analysis of cerebral vessels is disclosed. An anatomical model of a cerebral vessel is extracted from 3D medical image data. The anatomical model of the cerebral vessel includes an inner wall and an outer wall of the cerebral vessel. Blood flow in the cerebral vessel and deformation of the cerebral vessel wall are simulated using coupled computational fluid dynamics (CFD) and computational solid mechanics (CSM) simulations based on the anatomical model of the cerebral vessel.
摘要翻译：公开了一种用于脑血管耦合血流动力学分析的患者特异性计算建模和模拟方法和系统。从3D医学图像数据中提取脑血管的解剖模型。脑血管的解剖模型包括脑血管的内壁和外壁。基于脑血管解剖模型，使用耦合计算流体动力学（CFD）和计算固体力学（CSM）模拟模拟脑血管中的血流和脑血管壁的变形。

6. 发明申请

US20120106810A1 Automated Rib Ordering and Pairing 有权
标题翻译：自动排序和配对
公开(公告)号：US20120106810A1
公开(公告)日：2012-05-03
申请号：US13274515
申请日：2011-10-17
申请人： Sowmya Ramakrishnan , Christopher V. Alvino , Dijia Wu , David Liu , Shaohua Kevin Zhou
发明人： Sowmya Ramakrishnan , Christopher V. Alvino , Dijia Wu , David Liu , Shaohua Kevin Zhou
IPC分类号： G06K9/00
CPC分类号： G06T7/73 , G06T2207/10081 , G06T2207/30012 , G06T2207/30064 , G06T2207/30172
摘要： Ribs are automatically ordered and paired. After ordering ribs on each side, magnetic and spring functions are used to solve for rib pairing. The magnetic function is used to constrain possible pairs across sides, and the spring function is used to maintain the order on each side while accounting for missing or fused ribs.
摘要翻译：肋骨自动排序并配对。在每侧排列肋后，使用磁力和弹簧功能来解决肋配对。磁功能用于限制双方的可能对，弹簧功能用于维护每侧的顺序，同时考虑到缺失或融合的肋骨。

7. 发明申请

US20120071755A1 Method and System for Automatic Native and Bypass Coronary Ostia Detection in Cardiac Computed Tomography Volumes 有权
标题翻译：心脏计算机断层扫描中自动本机和旁路冠状动脉检测的方法和系统
公开(公告)号：US20120071755A1
公开(公告)日：2012-03-22
申请号：US13233220
申请日：2011-09-15
申请人： Yefeng Zheng , Fernando Vega-Higuera , Shaohua Kevin Zhou , Dorin Comaniciu
发明人： Yefeng Zheng , Fernando Vega-Higuera , Shaohua Kevin Zhou , Dorin Comaniciu
IPC分类号： A61B6/03
CPC分类号： G06T7/0081 , G06T7/11 , G06T7/12 , G06T2207/10072 , G06T2207/30048 , G06T2207/30101 , G06T2207/30172
摘要： A method and system for detection of native and bypass coronary ostia in a 3D volume, such as a CT volume, is disclosed. Native coronary ostia are detected by detecting a bounding box defining locations of a left native coronary ostium and a right native coronary ostium in the 3D volume using marginal space learning (MSL), and locally refining the locations of the left native coronary ostium and the right native coronary ostium using a trained native coronary ostium detector. Bypass coronary ostia are detected by segmenting an ascending aorta surface mesh in the 3D volume, generating a search region of a plurality of mesh points on the ascending aorta surface mesh based on a distribution of annotated bypass coronary ostia in a plurality of training volumes, and detecting the bypass coronary ostia by searching the plurality of mesh points in the search region.
摘要翻译：公开了用于检测3D体积中的天然和旁路冠状动脉口腔的方法和系统，例如CT体积。通过使用边缘空间学习（MSL）检测在3D体积中定义左天然冠状动脉口和右天然冠状动脉口的位置的边界框来检测本地冠状动脉，并且局部改善左天然冠状动脉口和右侧的位置使用训练有素的本地冠状动脉口腔检测器进行本地冠状动脉口。通过分割3D体积中的上升主动脉表面网格来检测旁路冠状动脉口腔，基于多个训练体积中注释旁路冠状动脉口腔的分布，生成升主动脉表面网格上的多个网格点的搜索区域，以及通过搜索搜索区域中的多个网格点来检测旁路冠状动脉口。

8. 发明申请

US20120070074A1 Method and System for Training a Landmark Detector using Multiple Instance Learning 有权
标题翻译：使用多实例学习训练地标检测器的方法和系统
公开(公告)号：US20120070074A1
公开(公告)日：2012-03-22
申请号：US13228509
申请日：2011-09-09
申请人： David Liu , Shaohua Kevin Zhou
发明人： David Liu , Shaohua Kevin Zhou
IPC分类号： G06K9/62
CPC分类号： G06K9/6257 , G06K2209/051
摘要： An apparatus and method for training a landmark detector receives training data which includes a plurality of positive training bags, each including a plurality of positively annotated instances, and a plurality of negative training bags, each including at least one negatively annotated instance. Classification function is initialized by training a first weak classifier based on the positive training bags and the negative training bags. All training instances are evaluated using the classification function. For each of a plurality of remaining classifiers, a cost value gradient is calculated based on spatial context information of each instance in each positive bag evaluated by the classification function. A gradient value associated with each of the remaining weak classifiers is calculated based on the cost value gradients, and a weak classifier is selected which has a lowest associated gradient value and given a weighting parameter and added to the classification function.
摘要翻译：用于训练地标检测器的装置和方法接收训练数据，训练数据包括多个正训练袋，每个正训练袋包括多个带有正面注释的实例，以及多个负训练袋，每个包括至少一个负注释实例。基于积极的训练袋和负面训练袋训练第一个弱分类器来初始化分类功能。使用分类函数评估所有训练实例。对于多个剩余分类器中的每一个，基于由分类函数评估的每个正包中的每个实例的空间上下文信息来计算成本值梯度。基于成本值梯度计算与剩余弱分类器中的每一个相关联的梯度值，并且选择具有最低相关梯度值并给出加权参数并加到分类函数的弱分类器。

9. 发明申请

US20120070046A1 Method and System for Detection and Tracking of Coronary Sinus Catheter Electrodes in Fluoroscopic Images 有权
标题翻译：用于检查和跟踪冠状动脉窦导管电极在荧光镜图像中的方法和系统
公开(公告)号：US20120070046A1
公开(公告)日：2012-03-22
申请号：US13229855
申请日：2011-09-12
申请人： Wen Wu , Terrence Chen , Peng Wang , Norbert Strobel , Shaohua Kevin Zhou , Dorin Comaniciu
发明人： Wen Wu , Terrence Chen , Peng Wang , Norbert Strobel , Shaohua Kevin Zhou , Dorin Comaniciu
IPC分类号： G06K9/00
CPC分类号： G06T7/0014 , A61B2034/2065 , A61B2090/376 , G06K2209/057 , G06T7/20 , G06T2207/10121 , G06T2207/30021 , G06T2207/30048
摘要： A method and system for detecting and tracking coronary sinus (CS) catheter electrodes in a fluoroscopic image sequence is disclosed. An electrode model is initialized in a first frame of the fluoroscopic image sequence based on input locations of CS sinus catheter electrodes in the first frame. The electrode model is tracked in subsequent frames of the fluoroscopic image sequence by detecting electrode position candidates in the subsequent frames of the fluoroscopic image sequence using at least one trained electrode detector, generating electrode model candidates in the subsequent frames based on the detected electrode position candidates, calculating a probability score for each of the electrode model candidates, and selecting an electrode model candidate based on the probability score.
摘要翻译：公开了一种用于在荧光镜图像序列中检测和跟踪冠状窦（CS）导管电极的方法和系统。基于第一帧中的CS窦导管电极的输入位置，在荧光镜图像序列的第一帧中初始化电极模型。通过使用至少一个经过训练的电极检测器检测荧光镜像图像序列的后续帧中的电极位置候选物，在荧光图像序列的后续帧中跟踪电极模型，基于检测到的电极位置候选产生后续帧中的电极模型候选计算每个电极模型候选的概率分数，并且基于概率分数来选择电极模型候选。

10. 发明授权

US08092388B2 Automated view classification with echocardiographic data for gate localization or other purposes 有权
标题翻译：用于门定位或其他目的的超声心动图数据的自动视图分类
公开(公告)号：US08092388B2
公开(公告)日：2012-01-10
申请号：US12210419
申请日：2008-09-15
申请人： Jin Hyeong Park , Shaohua Kevin Zhou , Constantine Simopoulos , Joanne Otsuki , Dorin Comaniciu
发明人： Jin Hyeong Park , Shaohua Kevin Zhou , Constantine Simopoulos , Joanne Otsuki , Dorin Comaniciu
IPC分类号： A61B8/00 , A61B8/08
CPC分类号： G06K9/6257 , G06K9/6292 , G06K2209/05
摘要： A view represented by echocardiographic data is classified. A probabilistic boosting network is used to classify the view. The probabilistic boosting network may include multiple levels where each level has a multi-class local structure classifier and a plurality of local-structure detectors corresponding to the respective multiple classes. In each level, the local structure is classified as a particular view and then the local structure is detected to determine whether the currently selected local structure corresponds to the class. The view classification may be used to determine gate locations, such as a gate for spectral Doppler analysis.
摘要翻译：以超声心动图数据为代表的视图进行分类。概率增强网络用于对视图进行分类。概率增强网络可以包括多个级别，其中每个级别具有多类本地结构分类器和对应于相应的多个类别的多个局部结构检测器。在每个级别中，将本地结构分类为特定视图，然后检测本地结构以确定当前选择的本地结构是否对应于该类。视图分类可用于确定门位置，例如用于频谱多普勒分析的门。

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