公开(公告)号：US20220196769A1

公开(公告)日：2022-06-23

申请号：US17604454

申请日：2020-04-09

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： KARSTEN SOMMER ,  STEFFEN WEISS ,  HOLGER EGGERS

IPC: G01R33/48 ,  G01R33/56 ,  G01R33/565

Abstract: Disclosed herein is a medical system (100, 300, 500) comprising a memory (110) storing machine executable instructions (120) and a convolutional neural network (122). The convolutional neural network is configured for receiving an initial Dixon magnetic resonance image (124, 126) as input. The convolutional neural network is configured for identifying one or more water-fat swap regions (128) in the initial Dixon magnetic resonance image. The medical system further comprises a processor (104) for controlling the medical system. Execution of the machine executable instructions causes the processor to: receive (200) the initial Dixon magnetic resonance image; and receive (204) the one or more water-fat swap regions from the convolutional neural network in response to inputting the initial Dixon magnetic resonance image into the convolutional neural network.

公开(公告)号：US20220012876A1

公开(公告)日：2022-01-13

申请号：US17294698

申请日：2019-11-19

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： KARSTEN SOMMER ,  MICHAEL GUNTER HELLE

IPC: G06T7/00 ,  G01R33/54 ,  G01R33/56 ,  G01R33/563

Abstract: The invention provides for a method of training a neural network (322) configured for providing a further processing location (326). The method comprises providing (200) a labeled medical image (100), wherein the labeled medical image comprises multiple labels each indicating a truth processing location (102, 104, 106). The method further comprises inputting (202) the labeled medical image into the neural network to obtain one trial processing location. The one trial processing location comprises a most likely trial processing location (108). The method further comprises determine (204) the closest truth processing location (106) for the most likely trial processing location. The method further comprises calculating (206) an error vector (110) using the closest truth processing location and the most likely trial processing location. The method further comprises training (208) the neural network using the error vector.

公开(公告)号：US20200050819A1

公开(公告)日：2020-02-13

申请号：US16339858

申请日：2017-10-09

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： KARSTEN SOMMER ,  MICHAEL GUNTER HELLE ,  THOMAS ERIK AMTHOR ,  PETER BOERNERT

IPC: G06K9/00 ,  A61B5/00 ,  A61B5/055

Abstract: The invention provides for a method of operating a magnetic resonance imaging system for imaging a subject. The method comprises acquiring (700) tagged magnetic resonance data (642) and a first portion (644) of fingerprinting magnetic resonance data by controlling the magnetic resonance imaging system with tagging pulse sequence commands (100). The tagging pulse sequence commands comprise a tagging inversion pulse portion (102) for spin labeling a tagging location within the subject. The tagging pulse sequence commands comprise a background suppression portion (104). The background suppression portion comprises MRF pulse sequence commands for acquiring fingerprinting magnetic resonance data according to a magnetic resonance fingerprinting protocol. The tagging pulse sequence commands comprise an image acquisition portion (106). The method comprises acquiring (702) control magnetic resonance data (646) and a second portion (648) of the fingerprinting magnetic resonance data by controlling the magnetic resonance imaging system with control pulse sequence commands. The control pulse sequence commands comprise a control inversion pulse portion (202). The control pulse sequence commands comprise the background suppression portion (104′). The control pulse sequence commands comprise the image acquisition portion (106). The method comprises reconstructing (704) tagged magnitude images (650) using the tagged magnetic resonance data. The method comprises reconstructing (706) a control magnitude images (652) using the control magnetic resonance data. The method comprises constructing (708) an ASL image by subtracting the control magnitude images and the tagged magnitude images from each other. The method comprises reconstructing (710) a series of magnetic resonance fingerprinting images (656) using the first portion of the fingerprinting magnetic resonance data and/or the second portion of the fingerprinting magnetic resonance data. The method comprises generating (712) at least one magnetic resonance parametric map (658) by comparing the series of magnetic resonance fingerprinting images with a magnetic resonance fingerprinting dictionary.