公开(公告)号：US20170372007A1

公开(公告)日：2017-12-28

申请号：US15524322

申请日：2015-10-22

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： KONGKUO LU ,  ALEXANDRA GROTH ,  YUECHEN QIAN ,  AXEL SAALBACH ,  RANJITH NAVEEN TELLIS ,  DANIEL BYSTROV ,  RAN COHEN ,  BELA FADIDA ,  LIOR WOLLOCH

IPC: G06F19/00 ,  G06K9/46 ,  G06F17/30 ,  G06K9/66 ,  G06F17/27

CPC classification number: G06F19/321 ,  G06F16/5866 ,  G06F17/2785 ,  G06K9/4676 ,  G06K9/66

Abstract: The present application describes a system (100) and method for detecting and labeling structures of interest. The system includes a current patient study database (102) containing a current patient study (200) with clinical contextual information (706). The system also includes 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), and a display device (108) configured to display findings from the current patient study. The anatomical structure detection and labeling engine (718) is configured to identify and label one or more structures of interest (716) from the extracted metadata and clinical context information (706). The processor (112) is also configured to aggregate series level data. The method detects, label and prioritize anatomical structures (710). Specifically, once patient information is received from the current patient study (108), the labeled anatomical structures (710) and the high risk anatomical structures (714) are combined to form an optimized prioritized list of structures of interest (716).

公开(公告)号：US20190006032A1

公开(公告)日：2019-01-03

申请号：US15780431

申请日：2016-12-20

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： ALEXANDRA GROTH ,  IVO MATHIEU JACOBUS CANJELS ,  VINCENT MAURICE ANDRE AUVRAY ,  JUERGEN WEESE ,  RAOUL FLORENT

IPC: G16H15/00 ,  G16H10/60 ,  G16H30/20

Abstract: Interventional medical procedures involve a complex sequence of actions, often involving many different medical professionals and items of equipment. These actions, and their notable attributes, should be recorded in detail, in case they are required during a consultation in the future. A typical medical interventional procedure could require hundreds, or even thousands, of actions to be recorded. This places demands on a medical practitioner during the intervention. Typically, important information is dictated into a report after an intervention. Attempting to produce the report by traditional means, such as by dictation, after the intervention is time-consuming. The proposed approach enables the formation of clinical reports based on structured interventional medical reporting data recorded during a medical intervention in an easier, and more accurate way. Interventional procedure status indications are used which may be derived from existing medical equipment, or information inputs.

公开(公告)号：US20170213338A1

公开(公告)日：2017-07-27

申请号：US15038834

申请日：2014-11-26

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： ALEXANDRA GROTH ,  JOCHEN PETERS ,  JUERGEN WEESE ,  AXEL SAALBACH

IPC: G06T7/00 ,  G06T7/12

CPC classification number: G06T7/0012 ,  G06T7/12 ,  G06T7/149 ,  G06T2207/30048

Abstract: A system (100) is provided for performing a model-based segmentation of an anatomical structure in a medical image. The system comprises a processor (140) configured for performing a model-based segmentation of the anatomical structure by applying a deformable model to image data (042). Moreover, definition data (220) is provided which defines a geometric relation between a first part and a second part of the deformable model of which a corresponding first part of the anatomical structure is presumed to be better visible in the image data than a corresponding second part of the anatomical structure. The definition data is then used to adjust a fit of the second part of the deformable model. As a result, a better fit of the second part of the deformable model to the second part of the anatomical structure is obtained despite said part being relatively poorly visible in the image data.

公开(公告)号：US20250014188A1

公开(公告)日：2025-01-09

申请号：US18711698

申请日：2022-11-15

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： IRINA WAECHTER-STEHLE ,  NICK FLÄSCHNER ,  ALEXANDRA GROTH ,  ROLF JÜRGEN WEESE

IPC: G06T7/13 ,  G06T7/00 ,  G06T7/149 ,  G06T19/20 ,  G06V20/69 ,  G06V20/70

Abstract: According to an aspect, there is provided a computer implemented method for boundary detection of an object of interest in an image (200), the method comprising: for a volume of the image corresponding to a portion of a three-dimensional. 3D, mesh, representing the object of interest, predicting, by a regression network, at least one predicted distance from the portion of the 3D mesh to a boundary of the object of interest in the image, the at least one predicted distance corresponding to a class (202); and determining a distance of the portion of the 3D mesh to the boundary based on at least one probability of the volume corresponding to a class and the at least one predicted distance (204).

公开(公告)号：US20240282461A1

公开(公告)日：2024-08-22

申请号：US18580698

申请日：2022-07-11

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： ROLF JÜRGEN WEESE ,  IRINA WAECHTER-STEHLE ,  ALEXANDRA GROTH ,  MATTHIJS JOSEPH MARIA CLUITMANS

IPC: G16H50/50 ,  G16H15/00 ,  G16H50/30

CPC classification number: G16H50/50 ,  G16H15/00 ,  G16H50/30

Abstract: A mechanism for generating information usable for identifying a risk of arrhythmia. A plurality of heart models are constructed from medical imaging data of a subject's heart. each heart model being defined by a set of different values for one or more modifiable properties. The modifiable properties are those used in the generation of the heart model or in the definition of the heart model, and influence or affect simulation results using the heart model. Each heart model undergoes a plurality of simulations, each simulation being a simulation of a response of the heart model to a (simulated) stimulation of electricity at a different pacing location of the heart. Output data is generated containing indicators of all simulation results.

公开(公告)号：US20210390707A1

公开(公告)日：2021-12-16

申请号：US17287142

申请日：2019-10-14

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： ALEXANDRA GROTH ,  ROLF JURGEN WEESE

IPC: G06T7/12 ,  G16H30/40 ,  G06N5/02

Abstract: A prediction model is provided which is capable of predicting a correctness of a segmentation by a segmentation algorithm. The prediction model may be trained using a machine learning technique, and after training used to predict the correctness of a segmentation of a boundary in respective image portions of an image by the segmentation algorithm. The predicted correctness may then be visualized, for example as an overlay of the segmentation.

公开(公告)号：US20230011809A1

公开(公告)日：2023-01-12

申请号：US17784957

申请日：2020-12-21

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： ALEXANDRA GROTH ,  FRANK MICHAEL WEBER ,  JOCHEN PETERS ,  ROLF JÜRGEN WEESE

IPC: G06T17/20 ,  G06T19/20 ,  G06T7/10 ,  G06V10/74 ,  G06F3/14

Abstract: The invention relates to a system and computer-implemented method for enabling correction of a segmentation of an anatomical structure in 3D image data. The segmentation may be provided by a mesh which is applied to the 3D image data to segment the anatomical structure. The correction may for example involve a user directly or indirectly selecting a mesh part, such as a mesh point, that needs to be corrected. The behaviour of the correction, e.g., in terms of direction, radius/neighbourhood or strength, may then be dependent on the mesh normal direction, and in some embodiments, on a difference between the mesh normal direction and the orientation of the viewing plane.

公开(公告)号：US20220319160A1

公开(公告)日：2022-10-06

申请号：US17620142

申请日：2020-06-25

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： ALEXANDRA GROTH ,  AXEL SAALBACH ,  IVO MATTEO BALTRUSCHAT ,  JENS VON BERG ,  MICHAEL GRASS

IPC: G06V10/82 ,  G06T7/00 ,  G06V10/774 ,  G06V20/70 ,  G06V10/96

Abstract: Multi-task deep learning method for a neural network for automatic pathology detection, comprising the steps: receiving first image data (I) for a first image recognition task; receiving (S2) second image data (V) for a second image recognition task; wherein the first image data (I) is of a first datatype and the second image data (V) is of a second datatype, different from the first datatype; determining (S3) first labeled image data (IL) by labeling the first image data (I) and determining second synthesized labeled image data (ISL) by synthesizing and labeling the second image data (V); training (S4) the neural network based on the received first image data (I), the received second image data (V), the determined first labeled image data (IL) and the determined second labeled synthesized image data (ISL); wherein the first image recognition task and the second image recognition task relate to a same anatomic region where the respective image data is taken from and/or relate to a same pathology to be recognized in the respective image data.

公开(公告)号：US20170301096A1

公开(公告)日：2017-10-19

申请号：US15510096

申请日：2015-09-11

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： JUERGEN WEESE ,  ALEXANDRA GROTH ,  JOCHEN PETERS ,  IRINA WACHTER-STEHLE ,  SABINE MOLLUS

IPC: G06T7/12 ,  G06T7/00

CPC classification number: G06T7/12 ,  G06T7/0012 ,  G06T15/10 ,  G06T19/00 ,  G06T2207/10072 ,  G06T2207/30048 ,  G06T2207/30101 ,  G06T2207/30172 ,  G06T2210/41 ,  G06T2215/08 ,  G06T2219/021

Abstract: A system and a method are provided for analyzing an image of an aortic valve structure to enable assessment of aortic valve calcifications. The system comprises an image interface for obtaining an image of an aortic valve structure, the aortic valve structure comprising aortic valve leaflets and an aortic bulbus. The system further comprises a segmentation subsystem for segmenting the aortic valve structure in the image to obtain a segmentation of the aortic valve structure. The system further comprises an identification subsystem for identifying a calcification on the aortic valve leaflets by analyzing the image of the aortic valve structure. The system further comprises an analysis subsystem configured for determining a centerline of the aortic bulbus by analyzing the segmentation of the aortic valve structure, and for projecting the calcification from the centerline of the aortic bulbus onto the aortic bulbus, thereby obtaining a projection indicating a location of the calcification as projected onto the aortic bulbus. The system further comprises an output unit for generating data representing the projection. Provided information on the accurate location of calcifications after a valve replacement may be advantageously used, for example, to effectively analyze the risk of paravalvular leakages of Transcatheter aortic valve implantation (TAVI) interventions for assessing the suitability of a patient for TAVI procedure.

公开(公告)号：US20160379372A1

公开(公告)日：2016-12-29

申请号：US15039899

申请日：2014-12-02

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： ALEXANDRA GROTH ,  HANNES NICKISCH ,  FRANK MICHAEL WEBER ,  JUERGEN WEESE ,  HANS BARSCHDORF

IPC: G06T7/00

CPC classification number: G06T7/149 ,  G06T7/12 ,  G06T2207/10028 ,  G06T2207/10072 ,  G06T2207/30048

Abstract: A method is provided for generating a deformable model (300) for segmenting an anatomical structure in a medical image. The anatomical structure comprises a wall. The deformable model (300) is generated such that it comprises, in addition to two surface meshes (320, 360), an intermediate layer mesh (340) for being applied in-between a first surface layer of the wall and a second surface layer of the wall. In generating the intermediate layer mesh (340), the mesh topology of at least part (400) of the intermediate layer mesh is matched to the mesh topology of one of the surface meshes (320, 360), thereby establishing matching mesh topologies. The deformable model (300), as generated, better matches the composition of such walls, thereby providing a more accurate segmentation.

Abstract translation: 提供了一种用于生成用于分割医学图像中的解剖结构的可变形模型（300）的方法。 解剖结构包括一个墙壁。 生成可变形模型（300），使得除了两个表面网格（320,360）之外，还包括用于施加在壁的第一表面层和第二表面层之间的中间层网格（340） 的墙。 在生成中间层网格（340）时，中间层网格的至少部分（400）的网格拓扑与一个表面网格（320,360）的网格拓扑匹配，从而建立匹配的网格拓扑。 所产生的可变形模型（300）更好地匹配这种壁的组成，从而提供更准确的分割。