Koninklijke Philips Corporation N.v.

Michael Gunter Helle

Steffen Weiss

Karsten Sommer

Gereon Vogtmeier

Thomas Lindner

Christoph G Leussler

Peter Boernert

Daniel Wirtz

Axel Saalbach

Thomas Erik Amthor

Eberhard Sebastian Hansis

Thomas Netsch

Rajendra Singh Sisodia

Tim Philipp Harder

Johan Partomo Djajadiningrat

Sunil Kumar Vuppala

Jaap Knoester

Christophe Michael Jean Schulke

Christophe Schuelke

Matthias Johannes Paulus Van Osch

Kim Cornelia Carolina Van De Ven

The invention may improve image quality of magnetic resonance imaging (MRI). The invention is directed to a coil arrangement () for magnetic resonance imaging. It comprises a base structure having a variable shape, an RF coil arranged on or in the base structure, an actuator means at least partially extending along the base structure such that the base structure is deformable along and/or about at least one axis, a position detecting means adapted to detect a current position of at least a portion of the subject to be examined relative to the RF coil, and control means coupled to the position detecting means and the actuator means, wherein the control means is adapted to adjust the shape of the base structure to maintain a contact of an outer surface of the base structure () and/or the RF coil () with the at least portion of the subject by driving the actuator means in response to a detected change of the current position relative to a previous position. The invention is further directed to a (MRI) system, a method for positioning an RF coil for a magnetic resonance imaging system relative to a subject to be examined, and a non-transitory computer-readable medium.

Coil arrangement for magnetic resonance imaging system

The invention provides for a method of training a neural network () configured for providing a further processing location (). The method comprises providing () a labeled medical image (), wherein the labeled medical image comprises multiple labels each indicating a truth processing location (). The method further comprises inputting () 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 (). The method further comprises determine () the closest truth processing location () for the most likely trial processing location. The method further comprises calculating () an error vector () using the closest truth processing location and the most likely trial processing location. The method further comprises training () the neural network using the error vector.

Determination of a further processing location in magnetic resonance imaging

Embodiments of the present application provide a radio frequency head coil (), RE head coil. The RE head coil () comprises a coil former () comprising at least a first leg and a second leg arranged at a distance from each other to define a space there between, the coil former () being at least sectionally flexible and having at least one first fastening portion () arranged adjacent to the space (), and a respiratory mask () comprising a gas outlet () and at least one second fastening portion (), wherein in an operable condition in which the RE head coil () is adapted to be arranged at least in sections around a head of a patient (S) and in which the second fastening portion () is adapted to be fastened to the first fastening portion (), the gas outlet () is disposed within the space ().

Radio frequency head coil with respiratory mask

The invention is directed to a sensor system () for increasing security of a use of at least one magnetic object () in vicinity of an MR imaging device (), wherein at least one magnetic property of the magnetic object () can be measure and evaluated in order to increase the safe use of the magnetic object () within MR environments.

Sensor system for increasing security in MR environments

A magnetic resonance imaging system including a memory configured to store machine executable instructions, pulse sequence commands, and a first machine learning model including a first deep learning network. The pulse sequence commands are configured for controlling the magnetic resonance imaging system to acquire a set of magnetic resonance imaging data. The first machine learning model includes a first input and a first output, a processor, wherein execution of the machine executable instructions causes the processor to control the magnetic resonance imaging system to repeatedly perform an acquisition and analysis process including: acquiring a dataset including a subset of the set of magnetic resonance imaging data from an imaging zone of the magnetic resonance imaging system according to the pulse sequence commands, providing the dataset to the first input of the first machine learning model, in response to the providing, receiving a prediction of a motion artifact level of the acquired magnetic resonance imaging data from the first output of the first machine learning model, the motion artifact level characterizing a number and/or extent of motion artifacts present in the acquired magnetic resonance imaging data.

Motion artifact prediction during data acquisition

The present disclosure relates to a method for configuring a medical device. The method comprises: providing a set of one or more parameters for configuring the medical device. Each parameter of the set has predefined values. A set of values of the set of parameters may be selected from the predefined values. Using the selected values the set of parameters may be set, which results in an operational configuration of the medical device. The medical device may be controlled to operate in accordance with the operational configuration, thereby an operating status of the medical device may be determined. Based on at least the operating status the operational configuration may be maintained or the selecting, setting and controlling may be repeatedly performed until a desired operating status of the medical device can be determined based on the operating statuses resulting from the controlling.

Method for configuring a medical device

The invention provides for a medical imaging system () comprising a processor () for controlling the medical imaging system. Execution of machine executable instructions () causes the processor to receive () a static angiographic image () of a region of interest (), receive () a time series of angiographic images (') of the region of interest, construct () an image mask () using the static angiographic image, determine () a time dependent signal () for each voxel within the image mask using the time series of angiographic images, construct () a composite angiographic image by: assigning () a fill time () to each voxel within the image mask using an extremum () of the time dependent signal if the extremum deviates from an average of the time dependent signal more than a predetermined threshold, and identifying () voxels within the image mask as being unfilled voxels.

Combination of temporally resolved angiographic images with a spatially resolved angiographic image

The invention provides for a magnetic resonance imaging system (). The execution of machine executable instructions causes a processor () controlling the magnetic resonance imaging system to control () the magnetic resonance imaging system to acquire the magnetic resonance imaging data () using pulse sequence commands () and reconstruct () a magnetic resonance image (). Execution of the machine executable instructions causes the processor to receive () a list of suggested pulse sequence command changes () by inputting the magnetic resonance image and image metadata () into an MRI artifact detection module (&#x2033;). The MRI artifact detection module comprises at least one neural network, which has been trained using images from failed magnetic resonance imaging protocols and/or magnetic resonance data extracted from the magnetic resonance imaging protocols labeled as failed accessed from a log file () which logs the execution of previous magnetic resonance imaging protocols. Execution of the machine executable instructions further causes the processor to receive () a selection of a chosen pulse sequence command change () from the list of suggested pulse sequence command changes. Execution of the machine executable instructions further causes the processor to modify () the pulse sequence commands using the chosen pulse sequence command change.

Automatic artifact detection and pulse sequence modification in magnetic resonance imaging

The invention provides for a method of operating a magnetic resonance imaging system for imaging a subject. The method comprises acquiring () tagged magnetic resonance data () and a first portion () of fingerprinting magnetic resonance data by controlling the magnetic resonance imaging system with tagging pulse sequence commands (). The tagging pulse sequence commands comprise a tagging inversion pulse portion () for spin labeling a tagging location within the subject. The tagging pulse sequence commands comprise a background suppression portion (). 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 (). The method comprises acquiring () control magnetic resonance data () and a second portion () 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 (). The control pulse sequence commands comprise the background suppression portion ('). The control pulse sequence commands comprise the image acquisition portion (). The method comprises reconstructing () tagged magnitude images () using the tagged magnetic resonance data. The method comprises reconstructing () a control magnitude images () using the control magnetic resonance data. The method comprises constructing () an ASL image by subtracting the control magnitude images and the tagged magnitude images from each other. The method comprises reconstructing () a series of magnetic resonance fingerprinting images () 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 () at least one magnetic resonance parametric map () by comparing the series of magnetic resonance fingerprinting images with a magnetic resonance fingerprinting dictionary.

Combined arterial spin labeling and magnetic resonance fingerprinting

The present invention provides a method for magnetic resonance (MR) imaging of a subject of interest () using arterial spin labeling, comprising the steps of performing a labeling module () by applying magnetic and/or radio frequency (RF) fields to the subject of interest () for labeling arterial blood in at least a labeling region () thereof, performing a first readout module () to obtain first MR information of the subject of interest () in a region of interest () using first parameters, performing a second readout module () to obtain second MR information of the subject of interest () in a region of interest () using second parameters, and performing MR image generation of a region of interest () based on the first and second MR information, wherein the first and second parameters of the first and second readout module () are chosen to be different parameters. The invention also provides a MR imaging system () adapted to perform the above method and a software package for upgrading a MR imaging system (), whereby the software package contains instructions for controlling the MR imaging system () according to the above method.

MRI involving the acquisition of an angiography weighted image and of a perfusion weighted image

The invention relates to a method of MR imaging of at least a portion of a body () placed in a main magnetic field within the examination volume of a MR device (). It is an object of the invention to facilitate the planning of an arterial spin labeling (ASL) MR imaging session and to improve the image quality in perfusion weighted MR imaging. The method of the invention comprises the following steps: acquiring angiographic MR signal data by subjecting the portion of the examined body () to one or more MR angiography scans; deriving quantitative blood flow parameters from the angiographic MR signal data; &#x2014;computing a labeling efficiency of an ASL sequence from the sequence parameters of the ASL sequence and from the quantitative blood flow parameters; optimizing the sequence parameters by maximizing the labeling efficiency; acquiring perfusion weighted MR signal data by subjecting the portion of the body to the ASL sequence; and&#x2014;reconstructing a MR image from the perfusion weighted MR signal data. Moreover, the invention relates to a MR device () and to a computer program for a MR device ().

Planning support for selective arterial spin labeling MR imaging methods

A method of magnetic resonance imaging () includes acquiring () tagged magnetic resonance data () by controlling the magnetic resonance imaging system with tagging pulse sequence commands (). The tagging pulse sequence commands include a tagging inversion pulse portion () for spin labeling a tagging location (') within a subject (). The tagging pulse sequence commands comprise a phase-contrast readout portion () which phase-contrast encodes in at least one direction. The control pulse sequence commands include a control inversion pulse portion () and the phase-contrast readout portion. A tagged magnitude image () is reconstructed () using the tagged magnetic resonance data. A control magnitude image () is reconstructed () using the control magnetic resonance data. An arterial image () is reconstructed () by subtracting the control magnitude image and the tagged magnitude image. At least one phase image () is reconstructed () using either the tagged magnetic resonance data and/or the control magnetic resonance data.

Magnetic resonance imaging of arterial structures

A medical imaging system () includes a memory () for storing machine executable instructions (), and a processor () for controlling the medical imaging system. Execution of the machine executable instructions causes the processor to: receive () a tagged arterial spin labeled (ASL) magnitude image () of a region of interest of a subject (); receive () a control ASL magnitude image () of the region of interest of the subject; construct () an arterial image () by subtracting the control ASL magnitude image and the tagged ASL magnitude image; construct () an arterial mask () using the arterial image by identifying arteries in the arterial image; receive () a phase contrast magnetic resonance image () of at least a portion of the region of interest of the subject; and construct a venous image () at least partially by setting voxels of the phase contrast image within the at least a portion of the region of interest that are within the arterial mask to a predetermined background value.

Growing community of inventors

Hamburg, Germany

Michael Gunter Helle