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

US11861839B2 Preprocessing medical image data for machine learning 有权
公开(公告)号：US11861839B2
公开(公告)日：2024-01-02
申请号：US17055255
申请日：2019-05-08
申请人： KONINKLIJKE PHILIPS N.V.
发明人： Rolf Jürgen Weese , Alexandra Groth , Tom Brosch , Jochen Peters
IPC分类号： G06T7/11 , G06N20/00 , G06T7/00 , G06V10/82 , G06V10/46 , G06V20/64
CPC分类号： G06T7/11 , G06N20/00 , G06T7/0012 , G06V10/469 , G06V10/82 , G06V20/64 , G06T2207/20081 , G06T2207/30048
摘要： A system and computer-implemented method are provided for preprocessing medical image data for machine learning. Image data is accessed which comprises an anatomical structure. The anatomical structure in the image data is segmented to obtain a segmentation of the anatomical structure as a delineated part of the image data. A grid is assigned to the delineated part of the image data, the grid representing a partitioning of an exterior and interior of the type of anatomical structure using grid lines, wherein said assigning comprises adapting the grid to fit the segmentation of the anatomical structure in the image data. A machine learning algorithm is then provided with an addressing to the image data in the delineated part on the basis of coordinates in the assigned grid. In some embodiments, the image data of the anatomical structure may be resampled using the assigned grid. Advantageous, a standardized addressing to the image data of the anatomical structure is provided, which may reduce the computational overhead of the machine learning, require fewer training data, etc.

2. 发明授权

US11830197B2 Generating shape difference data between multiple imaging modalities 有权
公开(公告)号：US11830197B2
公开(公告)日：2023-11-28
申请号：US17840708
申请日：2022-06-15
申请人： KONINKLIJKE PHILIPS N.V.
发明人： Rolf Jürgen Weese , Alexandra Groth , Jochen Peters
IPC分类号： G06T7/149 , G06F17/16 , G06T7/12 , G06T7/174 , G06T5/00
CPC分类号： G06T7/12 , G06F17/16 , G06T5/006 , G06T7/149 , G06T7/174 , G06T2207/30004
摘要： Systems and methods are provided for generating and using statistical data which is indicative of a difference in shape of a type of anatomical structure between images acquired by a first imaging modality and images acquired by a second imaging modality. This statistical data may then be used to modify a first segmentation of the anatomical structure which is obtained from an image acquired by the first imaging modality so as to predict the shape of the anatomical structure in the second imaging modality, or in general, to generate a second segmentation of the anatomical structure as it may appear in the second imaging modality based on the statistical data and the first segmentation.

3. 发明授权

US11593691B2 Information retrieval apparatus 有权
公开(公告)号：US11593691B2
公开(公告)日：2023-02-28
申请号：US16313035
申请日：2017-06-30
申请人： KONINKLIJKE PHILIPS N.V.
发明人： Rolf Jurgen Weese , Alexandra Groth , Tilman Wekel , Vincent Maurice Andre Auvray , Raoul Florent , Romane Isabelle Marie-Bernard Gauriau
IPC分类号： G09G5/00 , G06N7/00 , G06F16/904 , G06F16/901 , G06F16/907 , G06F16/26 , G06F16/36 , G16H70/60 , G16H50/50 , G06T15/00 , G06T17/20 , G16H50/20 , G16H40/63
摘要： An information retrieval system (IPS). The system comprises an input interface (IN) for receiving a query related to an object of interest. A concept mapper (CM) is configured to map the query to one or more associated concept entries of a hierarchic graph data structure (ONTO). The entries in said structure encode linguistic descriptors of components of a model (GM) for said object (OB). A metric-mapper (MM) is configured to map the query to one or more metric relationship descriptors. A geo-mapper (GEO) is configured to map said concept entries against the geometric model linked to the hierarchic graph data structure to obtain spatio-numerical data associated with said linguistic descriptors. A metric component (MTC) is configured to compute one or more metric or spatial relationships between said object components based on the spatio-numerical data and the one or more metric relationship descriptors.

4. 发明申请

US20150110369A1 IMAGE PROCESSING APPARATUS 审中-公开
标题翻译：图像处理设备
公开(公告)号：US20150110369A1
公开(公告)日：2015-04-23
申请号：US14371305
申请日：2012-12-28
申请人： KONINKLIJKE PHILIPS N.V.
发明人： Axel Saalbach , Alexandra Groth , Juergen Weese
IPC分类号： G06T7/00
CPC分类号： G06T7/10 , G06T7/0012 , G06T2207/20112
摘要： Image processing apparatus 100 comprising an input 110 for obtaining an image 102 and segmentation data 112 configured for use in segmenting a region of interest in a predetermined type of image, the input being arranged for further obtaining a segmentation data descriptor 116 of the segmentation data, the segmentation data descriptor being indicative of the predetermined type of image, and a processor 120 for (i) obtaining, based on the image, an image descriptor indicative of an actual type of the image, (ii) comparing the image descriptor to the segmentation data descriptor, and (iii) establishing, based on said comparing, a suitability indication 122 for using the segmentation data in segmenting the region of interest in the image to avoid the use of the segmentation data when the predetermined type of image insufficiently matches the actual type of the image.
摘要翻译：图像处理装置100包括用于获得图像102的输入110和被配置为用于分割预定类型图像中的感兴趣区域的分割数据112，该输入被设置用于进一步获得分割数据的分割数据描述符116，所述分割数据描述符指示所述预定类型的图像;以及处理器120，用于（i）基于所述图像获得指示所述图像的实际类型的图像描述符，（ii）将所述图像描述符与所述分割进行比较数据描述符，以及（iii）基于所述比较建立适用性指示122，用于在分割图像中的感兴趣区域时使用分割数据，以避免当预定类型的图像与实际的图像不匹配时使用分割数据图像的类型。

5. 发明申请

US20150025364A1 APPARATUS AND METHOD FOR VISUALIZING A CONDUCTION TRACT OF HEART 审中-公开
标题翻译：用于可视化心脏导管的装置和方法
公开(公告)号：US20150025364A1
公开(公告)日：2015-01-22
申请号：US14380982
申请日：2013-03-01
申请人： KONINKLIJKE PHILIPS N.V.
发明人： Alexandra Groth , Juergen Weese , Helko Lehmann , Hans Barschdorf
IPC分类号： A61B5/04 , A61B5/00 , A61B5/055 , A61B6/03 , A61B5/06 , A61B5/042
CPC分类号： A61B5/04011 , A61B5/0066 , A61B5/0084 , A61B5/0402 , A61B5/042 , A61B5/055 , A61B5/061 , A61B5/6852 , A61B5/6886 , A61B5/7425 , A61B5/743 , A61B6/032 , A61B8/44 , A61B8/445 , A61B2576/023 , G06T17/00 , G06T2210/41
摘要： The invention relates to an apparatus, a method and a computer program for visualizing a conduction tract of a heart. In order to provide a visualization which is helpful in avoiding or finding the conduction tract in, for example, an invasive procedure like ablation of heart tissue, a generic heart model is adapted to geometrical data of the patient's heart, wherein model data indicating a shape and/or position of the conduction tract is modifying in accordance to the adaptation. The modification of the model data is further refined based on electrophysiological data and the refined model is used for generating a visualization.
摘要翻译：本发明涉及一种可视化心脏传导道的装置，方法和计算机程序。为了提供有助于避免或发现例如像心脏组织消融这样的侵入性手术的传导路径的可视化，通用心脏模型适应于患者心脏的几何数据，其中指示形状的模型数据和/或传导道的位置根据适应性进行修改。基于电生理数据进一步改进模型数据的修改，并且使用精细模型来生成可视化。

6. 发明公开

US20240127432A1 IMAGE SEQUENCE ANALYSIS 审中-公开
公开(公告)号：US20240127432A1
公开(公告)日：2024-04-18
申请号：US18276482
申请日：2022-01-24
申请人： KONINKLIJKE PHILIPS N.V.
发明人： Alexandra Groth , Tanja Lossau , Irina Waechter-Stehle , Frank Michael Weber , Jochen Peters , Sebastian Wild , Arne Ewald , Andre Goossen
IPC分类号： G06T7/00 , G06T1/60 , G06T7/12 , G06V10/764
CPC分类号： G06T7/0012 , G06T1/60 , G06T7/12 , G06V10/764 , G06T2207/10016 , G06T2207/10132 , G06T2207/20081 , G06T2207/20084 , G06T2207/30004 , G06T2207/30168
摘要： A system and method for achieving more accurate results when applying an image processing task to a series of medical images of a patient, without significantly increasing processing resource. The proposed system and method is based on receiving a plurality of image sequences of a particular anatomical region, each capturing cyclical movement of an anatomical object. Each image sequence is supplied to a classifier module which employs use of one or more machine learning algorithms to derive at least one score for each image sequence indicative of predicted success or quality of a result of the image processing task if applied to the given image series. This permits an assessment to be made in advance of which of the plurality of image series is most likely to result in the best (e.g. highest quality, or greatest amount of information) results from the image processing task. This allows maximization of the quality of image processing results, without the need to actually process each of the image series with the image processing task, which would consume a large amount of processing resource and consume time.

7. 发明授权

US11183293B2 Optimized anatomical structure of interest labelling 有权
公开(公告)号：US11183293B2
公开(公告)日：2021-11-23
申请号：US15524322
申请日：2015-10-22
申请人： KONINKLIJKE PHILIPS N.V.
发明人： Kongkuo Lu , Alexandra Groth , Yuechen Qian , Axel Saalbach , Ranjith Naveen Tellis , Daniel Bystrov , Ran Cohen , Bela Fadida , Lior Wolloch
IPC分类号： G16H30/20 , G06F16/58 , G06F40/30 , G16H70/60 , G06K9/46 , G06K9/66
摘要： A system (100) for detecting and labeling structures of interest includes a current patient study database (102) containing a current patient study (200) with clinical contextual information (706), a statistical model patient report database (104) containing at least one or more prior patient documents containing clinical contextual information (706), an image metadata processing engine (118) configured to extract metadata for preparing an input for an anatomical structure classifier (608), a natural language processing engine (120) configured to extract clinical context information (706) from the prior patient documents, an anatomical structure detection and labeling engine (718) or processor (112), and a display device (108) configured to display findings from the current patient study. The anatomical structure detection and labeling engine (718) or processor (112) is configured to identify and label one or more structures of interest (716) from the extracted metadata and clinical context information (706) and aggregate series level data.

8. 发明授权

US09519949B2 Determining transformation between different coordinate systems 有权
标题翻译：确定不同坐标系之间的转换
公开(公告)号：US09519949B2
公开(公告)日：2016-12-13
申请号：US14656765
申请日：2015-03-13
申请人： KONINKLIJKE PHILIPS N.V.
发明人： Stéphane Allaire , Alexandra Groth , Juergen Weese
IPC分类号： G06K9/00 , G06T3/00 , G06T7/00 , G06K9/52 , G06K9/46 , G06K9/62
CPC分类号： G06T3/00 , G06K9/46 , G06K9/52 , G06K9/6201 , G06K2009/4666 , G06T7/0012 , G06T7/33 , G06T2207/10072 , G06T2207/10132 , G06T2207/30048
摘要： A system (100) is provided for determining a transformation between different coordinate systems associated with different medical data. In determining the transformation, the system (100) makes use of a third set of anatomical landmarks (040) defined in a reference coordinate system to match a first set of anatomical landmarks (010) defined in a first coordinate system to a second set of anatomical landmarks (020) defined in a second coordinate system. Effectively, the third set of anatomical landmarks is used as an intermediary in obtaining the transformation between both input sets of coordinate systems. As the third set of anatomical landmarks includes the anatomical landmarks of both input sets, it is not needed for both input sets to be identical or even to overlap. Rather, even in case both input sets are entirely disjunct, i.e., not-overlapping, it is still possible to determine the transformation between the different coordinate systems.
摘要翻译：提供了一种用于确定与不同医学数据相关联的不同坐标系之间的变换的系统（100）。在确定变换时，系统（100）利用在参考坐标系中定义的第三组解剖学标志（040）来将在第一坐标系中定义的第一组解剖标志（010）与第二组在第二坐标系中定义的解剖标志（020）。有效地，第三组解剖标志被用作获得两个输入坐标系集之间的变换的中介。由于第三组解剖标志包括两个输入集合的解剖标志，因此两个输入集合不需要相同或甚至重叠。相反，即使在两个输入集合完全分离的情况下，即不重叠的情况下，仍然可以确定不同坐标系之间的变换。

9. 发明授权

US11200750B2 Three dimensional model of a body part 有权
公开(公告)号：US11200750B2
公开(公告)日：2021-12-14
申请号：US16066424
申请日：2016-12-21
申请人： KONINKLIJKE PHILIPS N.V.
发明人： Vincent Maurice André Auvray , Raoul Florent , Romane Isabelle Marie-Bernard Gauriau , Alexandra Groth , Juergen Weese
IPC分类号： G06T19/20 , G06T7/33 , G06T7/30 , G06T7/73 , G06T7/00
摘要： An apparatus provides a patient specific 3D model of a body part. At least one 2D X-ray image including 2D X-ray image data of a vascular structure of a patient's body part is provided. A 3D model of the body part is provided, the 3D model including a 3D modelled vascular structure. At least one parameter commands an appearance of the 3D modelled vascular structure. The 3D modelled vascular structure is compared with the 2D X-ray image data of the vascular structure to determine the at least one parameter. The 3D model is updated as a function of the determined at least one parameter. A medical report is generated based on information determined from the 3D model.

10. 发明申请

US20210217164A1 PREPROCESSING MEDICAL IMAGE DATA FOR MACHINE LEARNING 有权
公开(公告)号：US20210217164A1
公开(公告)日：2021-07-15
申请号：US17055255
申请日：2019-05-08
申请人： KONINKLIJKE PHILIPS N.V.
发明人： Rolf Jürgen Weese , Alexandra Groth , Tom Brosch , Jochen Peters
IPC分类号： G06T7/00 , G06T7/11 , G06N20/00
摘要： A system and computer-implemented method are provided for preprocessing medical image data for machine learning. Image data is accessed which comprises an anatomical structure. The anatomical structure in the image data is segmented to obtain a segmentation of the anatomical structure as a delineated part of the image data. A grid is assigned to the delineated part of the image data, the grid representing a partitioning of an exterior and interior of the type of anatomical structure using grid lines, wherein said assigning comprises adapting the grid to fit the segmentation of the anatomical structure in the image data. A machine learning algorithm is then provided with an addressing to the image data in the delineated part on the basis of coordinates in the assigned grid. In some embodiments, the image data of the anatomical structure may be resampled using the assigned grid. Advantageous, a standardized addressing to the image data of the anatomical structure is provided, which may reduce the computational overhead of the machine learning, require fewer training data, etc.

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