公开(公告)号：US20110191283A1

公开(公告)日：2011-08-04

申请号：US13016259

申请日：2011-01-28

申请人： Ingmar Voigt ,  Dime Vitanovski ,  Razvan Ioan Ionasec ,  Alexey Tsymbal ,  Bogdan Georgescu ,  Shaohua Kevin Zhou ,  Martin Huber ,  Dorin Comaniciu

发明人： Ingmar Voigt ,  Dime Vitanovski ,  Razvan Ioan Ionasec ,  Alexey Tsymbal ,  Bogdan Georgescu ,  Shaohua Kevin Zhou ,  Martin Huber ,  Dorin Comaniciu

IPC分类号： G06N5/00 ,  G06G7/60

CPC分类号： G06G7/60 ,  G06N5/00

摘要： A method and system for providing medical decision support based on virtual organ models and learning based discriminative distance functions is disclosed. A patient-specific virtual organ model is generated from medical image data of a patient. One or more similar organ models to the patient-specific organ model are retrieved from a plurality of previously stored virtual organ models using a learned discriminative distance function. The patient-specific valve model can be classified into a first class or a second class based on the previously stored organ models determined to be similar to the patient-specific organ model.

摘要翻译： 公开了一种基于虚拟器官模型和基于学习的辨别距离函数提供医学决策支持的方法和系统。 从患者的医学图像数据生成患者特异性虚拟器官模型。 使用学习的鉴别距离函数从多个先前存储的虚拟器官模型检索与患者特异器官模型的一个或多个相似的器官模型。 基于先前存储的被确定为类似于患者特异器官模型的器官模型，患者特异性瓣膜模型可以分为第一类或第二类。

公开(公告)号：US08812431B2

公开(公告)日：2014-08-19

申请号：US13016259

申请日：2011-01-28

申请人： Ingmar Voigt ,  Dime Vitanovski ,  Razvan Ioan Ionasec ,  Alexey Tsymbal ,  Bogdan Georgescu ,  Shaohua Kevin Zhou ,  Martin Huber ,  Dorin Comaniciu

发明人： Ingmar Voigt ,  Dime Vitanovski ,  Razvan Ioan Ionasec ,  Alexey Tsymbal ,  Bogdan Georgescu ,  Shaohua Kevin Zhou ,  Martin Huber ,  Dorin Comaniciu

IPC分类号： G06F17/30 ,  G06F19/12 ,  G06F19/26 ,  A61B5/05 ,  G06N5/00 ,  G06G7/60

CPC分类号： G06G7/60 ,  G06N5/00

摘要： A method and system for providing medical decision support based on virtual organ models and learning based discriminative distance functions is disclosed. A patient-specific virtual organ model is generated from medical image data of a patient. One or more similar organ models to the patient-specific organ model are retrieved from a plurality of previously stored virtual organ models using a learned discriminative distance function. The patient-specific valve model can be classified into a first class or a second class based on the previously stored organ models determined to be similar to the patient-specific organ model.

摘要翻译： 公开了一种基于虚拟器官模型和基于学习的辨别距离函数提供医学决策支持的方法和系统。 从患者的医学图像数据生成患者特异性虚拟器官模型。 使用学习的鉴别距离函数从多个先前存储的虚拟器官模型检索与患者特异器官模型的一个或多个相似的器官模型。 基于先前存储的被确定为类似于患者特异器官模型的器官模型，患者特异性瓣膜模型可以分为第一类或第二类。

公开(公告)号：US09196049B2

公开(公告)日：2015-11-24

申请号：US13416168

申请日：2012-03-09

申请人： Razvan Ioan Ionasec ,  Dime Vitanovski ,  Alexey Tsymbal ,  Gareth Funka-Lea ,  Dorin Comaniciu ,  Andreas Greiser ,  Edgar Mueller

发明人： Razvan Ioan Ionasec ,  Dime Vitanovski ,  Alexey Tsymbal ,  Gareth Funka-Lea ,  Dorin Comaniciu ,  Andreas Greiser ,  Edgar Mueller

IPC分类号： A61B5/055 ,  G06T7/00

CPC分类号： G06T7/0083 ,  G06T7/12 ,  G06T2207/10088 ,  G06T2207/20076 ,  G06T2207/20081 ,  G06T2207/30048

摘要： A system and method for regression-based segmentation of the mitral valve in 2D+t cardiac magnetic resonance (CMR) slices is disclosed. The 2D+t CMR slices are acquired according to a mitral valve-specific acquisition protocol introduced herein. A set of mitral valve landmarks is detected in each 2D CMR slice and mitral valve contours are estimated in each 2D CMR slice based on the detected landmarks. A full mitral valve model is reconstructed from the mitral valve contours estimated in the 2D CMR slices using a trained regression model. Each 2D CMR slice may be a cine image acquired over a full cardiac cycle. In this case, the segmentation method reconstructs a patient-specific 4D dynamic mitral valve model from the 2D+t CMR image data.

摘要翻译： 公开了一种用于2D + t心脏磁共振（CMR）切片二尖瓣回归分割的系统和方法。 根据本文引入的二尖瓣特异性获取方案获取2D + t CMR切片。 在每个2D CMR切片中检测到一组二尖瓣地标，并且基于检测到的界标在每个2D CMR切片中估计二尖瓣轮廓。 使用训练有素的回归模型，从2D CMR切片中估算的二尖瓣轮廓重建完整的二尖瓣模型。 每个2D CMR切片可以是在整个心动周期上获取的电影图像。 在这种情况下，分割方法从2D + t CMR图像数据重建患者特有的4D动态二尖瓣模型。

公开(公告)号：US20120232379A1

公开(公告)日：2012-09-13

申请号：US13416168

申请日：2012-03-09

申请人： Razvan Ioan Ionasec ,  Dime Vitanovski ,  Alexey Tsymbal ,  Gareth Funka-Lea ,  Dorin Comaniciu ,  Andreas Greiser ,  Edgar Mueller

发明人： Razvan Ioan Ionasec ,  Dime Vitanovski ,  Alexey Tsymbal ,  Gareth Funka-Lea ,  Dorin Comaniciu ,  Andreas Greiser ,  Edgar Mueller

IPC分类号： A61B5/055

CPC分类号： G06T7/0083 ,  G06T7/12 ,  G06T2207/10088 ,  G06T2207/20076 ,  G06T2207/20081 ,  G06T2207/30048

摘要： A system and method for regression-based segmentation of the mitral valve in 2D+t cardiac magnetic resonance (CMR) slices is disclosed. The 2D+t CMR slices are acquired according to a mitral valve-specific acquisition protocol introduced herein. A set of mitral valve landmarks is detected in each 2D CMR slice and mitral valve contours are estimated in each 2D CMR slice based on the detected landmarks. A full mitral valve model is reconstructed from the mitral valve contours estimated in the 2D CMR slices using a trained regression model. Each 2D CMR slice may be a cine image acquired over a full cardiac cycle. In this case, the segmentation method reconstructs a patient-specific 4D dynamic mitral valve model from the 2D+t CMR image data.

摘要翻译： 公开了一种用于2D + t心脏磁共振（CMR）切片二尖瓣回归分割的系统和方法。 根据本文引入的二尖瓣特异性获取方案获取2D + t CMR切片。 在每个2D CMR切片中检测到一组二尖瓣地标，并且基于检测到的界标在每个2D CMR切片中估计二尖瓣轮廓。 使用训练有素的回归模型，从2D CMR切片中估算的二尖瓣轮廓重建完整的二尖瓣模型。 每个2D CMR切片可以是在整个心动周期上获取的电影图像。 在这种情况下，分割方法从2D + t CMR图像数据重建患者特定的4D动态二尖瓣模型。

公开(公告)号：US08526699B2

公开(公告)日：2013-09-03

申请号：US13040716

申请日：2011-03-04

申请人： Sushil Mittal ,  Yefeng Zheng ,  Bogdan Georgescu ,  Fernando Vega-Higuera ,  Shaohua Kevin Zhou ,  Dorin Comaniciu ,  Michael Kelm ,  Alexey Tsymbal ,  Dominik Bernhardt

发明人： Sushil Mittal ,  Yefeng Zheng ,  Bogdan Georgescu ,  Fernando Vega-Higuera ,  Shaohua Kevin Zhou ,  Dorin Comaniciu ,  Michael Kelm ,  Alexey Tsymbal ,  Dominik Bernhardt

IPC分类号： G06K9/00 ,  A61B5/05 ,  A61B5/02 ,  A61F2/06

CPC分类号： G06T7/0016 ,  G06T7/143 ,  G06T2207/10081 ,  G06T2207/20081 ,  G06T2207/30101 ,  G06T2207/30172

摘要： A method and system for providing detecting and classifying coronary stenoses in 3D CT image data is disclosed. Centerlines of coronary vessels are extracted from the CT image data. Non-vessel regions are detected and removed from the coronary vessel centerlines. The cross-section area of the lumen is estimated based on the coronary vessel centerlines using a trained regression function. Stenosis candidates are detected in the coronary vessels based on the estimated lumen cross-section area, and the significant stenosis candidates are automatically classified as calcified, non-calcified, or mixed.

摘要翻译： 公开了一种在3D CT图像数据中提供冠状动脉狭窄检测和分类的方法和系统。 从CT图像数据中提取冠脉血管的中心线。 从血管中心线检测和移除非血管区域。 使用经过训练的回归函数，基于冠状血管中心线估计管腔的横截面面积。 基于估计的管腔横截面积在冠状血管中检测狭窄候选物，并且显着狭窄候选物被自动分类为钙化，非钙化或混合。

公开(公告)号：US20110224542A1

公开(公告)日：2011-09-15

申请号：US13040716

申请日：2011-03-04

申请人： Sushil Mittal ,  Yefeng Zheng ,  Bogdan Georgescu ,  Fernando Vega-Higuera ,  Shaohua Kevin Zhou ,  Dorin Comaniciu ,  Michael Kelm ,  Alexey Tsymbal ,  Dominik Bernhardt

发明人： Sushil Mittal ,  Yefeng Zheng ,  Bogdan Georgescu ,  Fernando Vega-Higuera ,  Shaohua Kevin Zhou ,  Dorin Comaniciu ,  Michael Kelm ,  Alexey Tsymbal ,  Dominik Bernhardt

IPC分类号： A61B6/03

CPC分类号： G06T7/0016 ,  G06T7/143 ,  G06T2207/10081 ,  G06T2207/20081 ,  G06T2207/30101 ,  G06T2207/30172

摘要： A method and system for providing detecting and classifying coronary stenoses in 3D CT image data is disclosed. Centerlines of coronary vessels are extracted from the CT image data. Non-vessel regions are detected and removed from the coronary vessel centerlines. The cross-section area of the lumen is estimated based on the coronary vessel centerlines using a trained regression function. Stenosis candidates are detected in the coronary vessels based on the estimated lumen cross-section area, and the significant stenosis candidates are automatically classified as calcified, non-calcified, or mixed.

摘要翻译： 公开了一种在3D CT图像数据中提供冠状动脉狭窄检测和分类的方法和系统。 从CT图像数据中提取冠脉血管的中心线。 从血管中心线检测和移除非血管区域。 使用经过训练的回归函数，基于冠状血管中心线估计管腔的横截面面积。 基于估计的管腔横截面积在冠状血管中检测狭窄候选物，并且显着狭窄候选物被自动分类为钙化，非钙化或混合。

公开(公告)号：US20120321174A1

公开(公告)日：2012-12-20

申请号：US13160744

申请日：2011-06-15

申请人： Alexey Tsymbal ,  Michael Kelm ,  Maria Jimena Costa ,  Shaohua Kevin Zhou ,  Dorin Comaniciu ,  Yefeng Zheng ,  Alexander Schwing

发明人： Alexey Tsymbal ,  Michael Kelm ,  Maria Jimena Costa ,  Shaohua Kevin Zhou ,  Dorin Comaniciu ,  Yefeng Zheng ,  Alexander Schwing

IPC分类号： G06K9/62

CPC分类号： G06K9/6219 ,  G06F17/30247 ,  G06F17/30268 ,  G06K9/6263 ,  G06K9/6282

摘要： A method of performing image retrieval includes training a random forest RF classifier based on low-level features of training images and a high-level feature, using similarity values generated by the RF classifier to determine a subset of the training images that are most similar to one another, and classifying input images for the high-level feature using the RF classifier and the determined subset of images.

摘要翻译： 执行图像检索的方法包括基于训练图像的低级特征和高级特征来训练随机森林RF分类器，使用由RF分类器生成的相似性值来确定最相似的训练图像的子集 并且使用RF分类器和确定的图像子集对高级特征的输入图像进行分类。

公开(公告)号：US08744172B2

公开(公告)日：2014-06-03

申请号：US13160744

申请日：2011-06-15

申请人： Alexey Tsymbal ,  Michael Kelm ,  Maria Jimena Costa ,  Shaohua Kevin Zhou ,  Dorin Comaniciu ,  Yefeng Zheng ,  Alexander Schwing

发明人： Alexey Tsymbal ,  Michael Kelm ,  Maria Jimena Costa ,  Shaohua Kevin Zhou ,  Dorin Comaniciu ,  Yefeng Zheng ,  Alexander Schwing

IPC分类号： G06K9/00

CPC分类号： G06K9/6219 ,  G06F17/30247 ,  G06F17/30268 ,  G06K9/6263 ,  G06K9/6282

摘要： A method of performing image retrieval includes training a random forest RF classifier based on low-level features of training images and a high-level feature, using similarity values generated by the RF classifier to determine a subset of the training images that are most similar to one another, and classifying input images for the high-level feature using the RF classifier and the determined subset of images.

摘要翻译： 执行图像检索的方法包括基于训练图像的低级特征和高级特征来训练随机森林RF分类器，使用由RF分类器生成的相似性值来确定最相似的训练图像的子集 并且使用RF分类器和确定的图像子集对高级特征的输入图像进行分类。

公开(公告)号：US20100094874A1

公开(公告)日：2010-04-15

申请号：US12457592

申请日：2009-06-16

申请人： Martin Huber ,  Alexey Tsymbal ,  Sonja Zillner

发明人： Martin Huber ,  Alexey Tsymbal ,  Sonja Zillner

IPC分类号： G06F17/30

CPC分类号： G06F19/325 ,  G06F16/93 ,  G06Q50/22 ,  G16H50/20

摘要： A method and an apparatus retrieve additional information regarding a patient record. Applying the subject-matter of the present invention clinical experts, such as doctors, can be provided with domain specific background knowledge, and can, hence, be supported in making decisions regarding the treatment of patients. Said additional information can be structured and visualised, which makes the retrieved information understandable also for persons without advanced knowledge regarding data processing. The retrieval of additional information is accomplished by a comparison of data being stored in the patient record and data being stored in a predefined textual resource, such as a ontology, and an identification of further terms describing attributes of the patient record. This finds application in supporting the diagnosis of patients and healthcare related information retrieval tasks.

摘要翻译： 一种方法和装置检索关于病人记录的附加信息。 应用本发明的主题，诸如医生的临床专家可以被提供具有领域特异性的背景知识，并且因此可以被支持来做出关于患者治疗的决定。 所述附加信息可以被构造和可视化，这使得检索到的信息也对于没有关于数据处理的高级知识的人也是可以理解的。 通过比较存储在患者记录中的数据和存储在预定义的文本资源（例如本体）中的数据以及描述患者记录的属性的进一步的术语的标识来实现附加信息的检索。 这可以应用于支持患者的诊断和与医疗相关的信息检索任务。

公开(公告)号：US07899764B2

公开(公告)日：2011-03-01

申请号：US11763717

申请日：2007-06-15

申请人： Huber Martin ,  Alexey Tsymbal ,  Sonja Zillner

发明人： Huber Martin ,  Alexey Tsymbal ,  Sonja Zillner

IPC分类号： G06F15/18

CPC分类号： G06N99/005 ,  G06F19/00 ,  G06Q50/24 ,  G16H50/20 ,  G16H50/70

摘要： A medical ontology may be used for computer assisted clinical decision support. Multi-level and/or semantically grouped medical ontology is incorporated into a machine learning algorithm. The resulting machine-learnt algorithm outputs information to assist in clinical decisions. For example, a patient record is input to the algorithm. Based on the incorporated medical ontology, similarities are aggregated in different groups. An aggregate similarity of at least one group is a function of an aggregate similarity of at least another group. One or more similar patients and/or outcomes are identified based on similarity. Probability based outputs may be provided.

摘要翻译： 医学本体可用于计算机辅助临床决策支持。 多级和/或语义分组的医学本体被并入机器学习算法中。 所得到的机器学习算法输出信息以辅助临床决策。 例如，患者记录被输入到算法中。 基于并入的医学本体，相似之处汇总在不同的组中。 至少一个组的聚合相似性是至少另一个组的聚合相似度的函数。 基于相似性来鉴定一种或多种类似的患者和/或结果。 可以提供基于概率的输出。