Max-planck-gesellschaft Zur F&#xf6;rderung Der Wissenschaften E. V.

Eberhard Karls Universitaet Tuebingen

Eberhard Karls Universitat Tubingen Medizinische F Akultat

Klaus Scheffler

Moritz Zaiss

Jens Hoffmann

Felix Glang

Anagha Deshmane

Ali Aghaeifar

Rolf Pohmann

Sergey Prokudin

Alexander Loktyushin

Kai Buckenmaier

Jonas Bause

Shajan Gunamony

Martin Eschelbach

A method of processing magnetic resonance data of a sample under investigation includes the steps of provision of the MR data being collected with an MRI scanner apparatus, and machine learning based data analysis of the MR data by supplying the MR data to an artificial neural network being trained with predetermined training data, wherein at least one image parameter of the sample and additionally at least one uncertainty quantification measure representing a prediction error of the at least one image parameter are provided by output elements of the neural network. Furthermore, a magnetic resonance imaging (MRI) scanner apparatus being adapted for employing the method of processing MR data is described.

Machine learning based processing of magnetic resonance data, including an uncertainty quantification

A method of magnetic resonance tomography includes arranging an object in a static magnetic field, subjecting it to radiofrequency (RF) pulses and magnetic field gradients for creating spatial encoding of magnetic resonance signals, acquiring the signals with at least two RF receive coils, each with a self-resonance frequency and a spatially restricted sensitivity profile, and reconstructing an object image. Spatial encoding of the signals by the gradients and the profiles is utilized, wherein the profile of at least one of the coils is subjected to a temporal sensitivity profile modulation while acquiring the signal. The self-resonance frequency of the at least one coil is set within a predetermined receive bandwidth of a constant resonance frequency value during the modulation. The reconstructing further utilizes the modulation for obtaining additional spatial information to the spatial encoding of the signals by the gradients. Furthermore, an MRI device is described.

Magnetic resonance tomography (MRT) imaging, employing RF receive coils with temporal sensitivity profile modulation

A method of processing magnetic resonance (MR) data of a sample under investigation, includes the steps of providing the MR data being collected with an MRI scanner apparatus, and subjecting the MR data to a multi-parameter nonlinear regression procedure being based on a non-linear MR model and employing a set of input parameters, wherein the regression procedure results in creating a parameter map of model parameters of the sample, wherein the input parameters (initial values and possibly boundaries) of the regression procedure are estimated by a machine learning based estimation procedure applied to the MR data. The machine learning based estimation procedure preferably includes at least one of at least one neural network and a support vector machine. Furthermore, an MRI scanner apparatus is described.

Method and apparatus for processing magnetic resonance data

The invention relates to an MRI apparatus for magnetic resonance imaging of a subject of investigation, comprising: a coil arrangement () for transmitting an excitation signal into the subject and for receiving a response signal from the subject; a high-power radio-frequency amplifier () for generating the excitation signal; and a low-noise amplifier (LNA) for amplifying the response signal. The invention provides a transmit/receive switch () which is alternatively operable in a transmit mode or in a receive mode. In the transmit mode, the transmit/receive switch () transmits the excitation signal to the coil arrangement () and protects the low-noise amplifier (LNA) from the outgoing excitation signal. In the receive mode, the transmit/receive switch () routes the in coming response signal to the low-noise amplifier (LNA).

Transmit/receive switch, a transmit coil array and a receive coil array for MRI

Growing community of inventors

Tuebingen, Germany

Klaus Scheffler