公开(公告)号：US20240095885A1

公开(公告)日：2024-03-21

申请号：US18038580

申请日：2021-12-02

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： NIKOLAS DAVID SCHNELLBÄCHER ,  CHRISTIAN WUELKER ,  FRANK BERGNER ,  KEVIN MARTIN BROWN ,  MICHAEL GRASS

IPC: G06T5/00 ,  G06T5/50

CPC classification number: G06T5/002 ,  G06T5/50 ,  G06T2207/10072 ,  G06T2207/20084 ,  G06T2207/20221

Abstract: A mechanism for generating a partially denoised image. A residual noise image, obtained by processing an image using a convolutional neural network, is weighted. The blending or combination of the weighted residual noise image and the (original) image generates the partially denoised image.

公开(公告)号：US20230419563A1

公开(公告)日：2023-12-28

申请号：US18036204

申请日：2021-11-04

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： CHRISTIAN HAASE ,  MICHAEL GRASS ,  THOMAS HEIKO STEHLE, Sr. ,  FRANK BERGNER ,  SEBASTIAN WILD

IPC: G06T11/00 ,  G06T7/33 ,  G06T7/38

CPC classification number: G06T11/006 ,  G06T7/337 ,  G06T7/38 ,  G06T2210/41 ,  G06T2207/10081 ,  G06T2207/30004 ,  G06T2207/20212

Abstract: A method for use in image reconstruction of CT projection data, which aims at reducing motion artefacts in reconstructed images caused by movement of anatomical bodies. Embodiments are based on mitigating motion artefacts based on restricting the range of data that is used for reconstructing each slice. More particularly, a sub-range of the projection data corresponding to each slice is selected, this sub-range being chosen based on determining one or more sub-windows of visibility of a target anatomical object or event within the projection data sequence. The event may be a particular phase of a movement cycle of the anatomical body. The structure could be a particular portion of the anatomical body which is of interest. Either approach leads to reduction of motion artefacts within a single slice, by restricting the data range, and focusing upon the data which is most relevant clinically.

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：US20210118569A1

公开(公告)日：2021-04-22

申请号：US16500207

申请日：2018-03-05

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： MICHAEL GRASS ,  SVEN PREVRHAL

IPC: G16H50/30 ,  A61B5/319 ,  A61B5/346 ,  A61B5/026 ,  G16H50/50 ,  G16H30/20 ,  G16H30/40 ,  G16H50/20 ,  G06N20/00 ,  G06T7/12 ,  G06T7/00

Abstract: A computing system (118) includes a computer readable storage medium (122) with computer executable instructions (124), including a biophysical simulator (126) and an electrocardiogram signal analyzer (128). The computing system further includes a processor (120) configured to execute the electrocardiogram signal analyzer determine myocardial infarction characteristics from an input electrocardiogram and to execute the biophysical simulator to simulate a fractional flow reserve or an instant wave-free ratio index from input cardiac image data and the determined myocardial infarction characteristics.

公开(公告)号：US20210093382A1

公开(公告)日：2021-04-01

申请号：US16499338

申请日：2018-04-01

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： MICHAEL GRASS ,  SVEN PREVRHAL

IPC: A61B34/10 ,  G16H50/50 ,  G16H20/40

Abstract: A computing system (118) includes a computer readable storage medium (122) with computer executable instructions (124), including: a biophysical simulator (126) configured to simulate coronary or carotid flow and pressure effects induced by a cardiac valve device implantation, using cardiac image data and a device model (212). The computing system further includes a processor (120) configured to execute the biophysical simulator to simulate the coronary or carotid flow and the pressure effects induced by the device implantation with the cardiac image data and the device model. The computing system further includes a display configured to display results of the simulation.

公开(公告)号：US20200341622A1

公开(公告)日：2020-10-29

申请号：US16955824

申请日：2018-12-11

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： JAVIER OLIVAN BESCOS ,  RAOUL FLORENT ,  ROMANE ISABELLE MARIE-BERNARD GAURIAU ,  CHRISTIAN HAASE ,  MICHAEL GRASS ,  VINCENT MAURICE ANDRE AUVRAY

IPC: G06F3/0484 ,  G06T7/13 ,  G06T7/187 ,  G06T7/149 ,  G06F3/0488

Abstract: The present invention relates to a device for interacting with vessel images, the device (14) comprising: an interface unit (22); a processing unit (20); wherein the interface unit (22) comprises: a display (21); and an input setup (23); wherein the display (21) is configured to display a vessel image (24); wherein the input setup (23) is configured to receive a user input in relation to the vessel image (24); wherein the processing unit (20) is configured to: determine, for at least one vessel (26) in the vessel image (24), a vessel contour (30); determine, from the user input, an identifier position (36) in the vessel image (24); indicate at least a portion (38) of the vessel contour (30) in the vessel image (24), if the determined identifier position (36) is spaced apart from the vessel contour (30) by a distance (37) within a predefined distance range; determine, from the user input, a drag direction (42); and move the indicated portion (38) along the vessel contour (30) based on the determined drag direction (42).

公开(公告)号：US20200170709A1

公开(公告)日：2020-06-04

申请号：US16623130

申请日：2018-06-29

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： TOBIAS WISSEL ,  HERNAN GUILLERMO MORALES VARELA ,  MICHAEL GRASS

IPC: A61B34/10 ,  G06T19/20 ,  G06T7/33 ,  G06T7/149 ,  G16H30/40 ,  G16H50/50 ,  G16H20/40 ,  A61B34/20 ,  A61B90/00 ,  A61F2/24

Abstract: The present invention relates to a device for predicting an unfolded state of a foldable implant in biological tissue, the device comprising: a receiving unit configured to receive pre -treatment 3D planning image data and treatment image data, the treatment image data comprising catheter image data, the catheter image data comprising landmark image data; a segmentation module configured to segment the pre-treatment 3D planning image data resulting in segmented 3D planning image data; a search unit configured to locate the landmark image data within the treatment image data resulting in a known landmark position and a known landmark orientation; a registration module configured to register the segmented 3D planning image data to the treatment image data resulting in registered treatment image data; and a simulation unit configured to simulate an unfolded state of a foldable implant in biological tissue based on the known landmark position and the known landmark orientation in the biological tissue resulting in a simulated unfolded implant positioned in biological tissue. The present invention provides the knowledge of the unfolded implant in the biological tissue as well as its interaction with the anatomical placement domain at the current landmark position prior to the real deployment.

公开(公告)号：US20170367645A1

公开(公告)日：2017-12-28

申请号：US15543466

申请日：2016-01-07

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： TOBIAS KLINDER ,  EBERHARD SEBASTIAN HANSIS ,  MICHAEL GRASS ,  DIRK SCHAEFER ,  HANNO HEYKE HOMANN ,  CHRISTIAN HAASE

IPC: A61B5/00 ,  G06T7/00 ,  G06T19/00 ,  G06K9/00 ,  A61B6/00 ,  A61B6/03

CPC classification number: A61B5/4566 ,  A61B5/055 ,  A61B6/032 ,  A61B6/04 ,  A61B6/466 ,  A61B6/487 ,  A61B6/505 ,  A61B6/5217 ,  A61B6/54 ,  A61B2576/02 ,  G06K9/00214 ,  G06K2209/055 ,  G06T7/0014 ,  G06T19/00 ,  G06T19/006 ,  G06T2207/10072 ,  G06T2207/30012 ,  G06T2210/41

Abstract: Minimally-invasive spinal inventions are often performed using fluoroscopic imaging methods, which can give a real-time impression of the location of a surgical instrument, at the expense of a small field of view. When operating on a spinal column, a small field of view can be a problem, because a medical professional is left with no reference vertebra in the fluoroscopy image, from which to identify a vertebra, which is the subject of the intervention. Identifying contiguous vertebrae is difficult because such contiguous vertebrae are similar in shape. However, characteristic features, which differentiate one vertebra from other vertebra, and which are visible in the fluoroscopic view, may be used to provide a reference.

公开(公告)号：US20170340299A1

公开(公告)日：2017-11-30

申请号：US15535667

申请日：2015-12-17

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： MICHAEL GRASS ,  EBERHARD SEBASTIAN HANSIS ,  DIRK SCHÄFER ,  TOBIAS KLINDER ,  CHRISTIAN HAASE ,  HANNO HEYKE HOMANN

IPC: A61B6/00 ,  A61B6/03

CPC classification number: A61B6/4441 ,  A61B6/03 ,  A61B6/504 ,  A61B6/5205 ,  A61B6/5241

Abstract: The invention relates to an imaging system (10) for imaging an elongated region of interest of an object, an imaging method for imaging an elongated region of interest of an object, a computer program element for controlling such system for performing such method and a computer readable medium having stored such computer program element. The imaging system (10) comprises an acquisition unit (11) and a processing unit (13). The acquisition unit (11) is a C-arm acquisition unit and configured to acquire first image data of the object to be imaged with a first imaging parameter. The acquisition unit (11) is further configured to acquire second, different image data of an object to be imaged with a second imaging parameter. The second geometric imaging parameter is defined based on object specific data for the volume data to be aligned with the elongated region of interest of the object to be imaged. The processing unit (13) is configured to combine the first and second image data into volume data.

公开(公告)号：US20170150935A1

公开(公告)日：2017-06-01

申请号：US15316215

申请日：2015-06-01

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： EBERHARD SEBASTIAN HANSIS ,  DIRK SCHAEFER ,  MICHAEL GRASS

IPC: A61B6/00 ,  G06T11/60 ,  G06T7/73 ,  A61B5/00

CPC classification number: A61B6/505 ,  A61B5/4566 ,  A61B6/4441 ,  A61B6/4464 ,  A61B6/5241 ,  A61B6/5276 ,  A61B6/547 ,  G06T7/73 ,  G06T11/60 ,  G06T2207/10116 ,  G06T2207/30012

Abstract: The present invention relates to an imaging system (10) for a vertebral level, an identification method for a vertebral level, a computer program element for controlling such system and a computer readable medium having stored such computer program element. The imaging system (10) comprises a determination unit (11), a definition unit (12), an imaging unit (13), and a processing unit (14). The determination unit (11) determines a target vertebral level. The definition unit (12) defines an anatomical landmark of a spine. The imaging unit (13) provides a series of X-ray images along the spine based on the landmark. The processing unit (14) identifies the target vertebral level in at least one of the X-ray images. The processing unit (14) further stitches the X-ray images to a continuous panoramic image of the spine and identifies the target vertebral level in the panoramic image.