Siemens Healthcare Gmbh

Siemens Healthineers Ag

Siemens Aktiengesellschaft

New York University

Johns Hopkins University

The General Hospital Corporation

Esther Raithel

Sasa Grbic

Dana Lin

David Grodzki

Mariappan S Nadar

Marcel Dominik Nickel

Bernhard Geiger

Heiko Meyer

Mahmoud Mostapha

Daniel Polak

Jan Fritz

Gregor Körzdörfer

Guillaume Chabin

Michael Schwier

Mario Zeller

Boris Mailhe

Thomas Beck

Kawin Setsompop

Flavio Carinci

Matthias Fenchel

Mathias Nittka

Yiqiang Zhan

Simon Arberet

Qiu Wang

Liang Zhao

Jin-hyeong Park

Dingxin Wang

Theresa Bachschmidt

Florian Knoll

Yen Mei Lisa Chuah

Inge Brinkmann

Various techniques of reconstructing multiple Magnetic Resonance Imaging, MRI, images for multiple slices based on an MRI measurement dataset that is acquired using a simultaneous multi-slice protocol and undersampling and K-space are disclosed. A convolutional neural network can be used to implement a regularization operation of an iterative optimization for the reconstruction, i.e., an unrolled neural network or variational neural network. A combination with Dixon imaging, i.e., separation of multiple chemical species, is disclosed.

Simultaneous multi-slice protocol and deep-learning magnetic resonance imaging reconstruction

For reconstruction in medical imaging, such as reconstruction in MR imaging, scanning is accelerated by under-sampling. In iterative reconstruction, the input to the regularizer is altered provide for correlation of non-local aliasing artifacts. Duplicates of the input image are shifted by different amounts based on the level of acceleration. The resulting shifted images are used to form the input to the regularizer. Providing an input based on shifts allows the regularization to suppress non-local as well as local aliasing artifacts.

Accelerated medical image reconstruction with improved aliasing artifact reduction

Techniques of determining a quantification of at least one characteristic of a muscle structure comprising at least one muscle and at least one tendon are disclosed. The quantification of the at least one characteristic of the rotator cuff may be determined by using at least one artificial neural network and based on one or more medical images depicting the muscle structure of a patient.

Determining characteristics of muscle structures using artificial neural network

Systems and methods for an intuitive display of one or more anatomical objects are provided. One or more 3D medical images of one or more anatomical objects of a patient are received. Correspondences between the one or more 3D medical images and points on a 2D map representing the one or more anatomical objects are determined. The 2D map is updated with patient information extracted from the one or more 3D medical images. The updated 2D map with the determined correspondences is output.

Intuitive display for rotator cuff tear diagnostics

An embodiment of a method for recording diagnostic measurement data of a knee of an examination object in knee imaging by a magnetic resonance device, includes performing an overview scan of the knee of the examination object, wherein overview measurement data is acquired in the overview scan, and performing diagnostic scans of the knee of the examination object based on the acquired overview measurement data, wherein two-dimensional diagnostic measurement data is acquired in the diagnostic scans.

Method for recording diagnostic measurement data of a knee of an examination object in knee imaging by a magnetic resonance device

Medical image data is received at a data processing system, which is an artificial intelligence-based system. An identification process is performed at the data processing system to identify a subset of the medical image data representing a region of interest including one or more target tendons. A determination process is performed at the data processing system to determine one or more characteristics relating to one or more abnormalities of the one or more target tendons. Abnormality data is output, the abnormality data relating to the one or more abnormalities and being based on the one or more characteristics.

Medical image data

Techniques are disclosed to leverage the use of neural networks or similar machine learning algorithms to de-noise highly accelerated Wave-CAIPIRINHA scans. The described techniques facilitate the generation of 3D sequences using a greatly reduced scan time, with the resulting images having a high spatial resolution and an improved SNR compared to conventional approaches.

Noise suppression for wave-CAIPI

Magnetic resonance (MR) data are acquired by applying magnetic fields to an examination region concurrent with stimulated echo signals, such that trajectories, which are not straight lines, are generated in k-space. For this purpose, sequence of RF pulses is applied to generate the stimulated echo signals in the examination object, undersampled MR measurement data are detected during reception of the stimulated echo signals in the at least two receiving coils, along the curved k-space trajectories, and fully sampled MR measurement are generated from the undersampled MR measurement data using sensitivity information of the at least two receiving coils. Alternatively, the MR measurement data are fully sampled in a central region of k-space, and a region outside the central region is not fully sampled, and a phase correction with a Partial Fourier technique is executed on the MR measurement data using fully sampled MR measurement data from the central region of k-space.

Magnetic resonance imaging using dataset undersampling

In a method for alpha angle measurements of a bone joint based on magnetic resonance imaging (MRI) data of the bone joint, a three-dimensional (3D) bone surface image of the bone joint is generated based on two-dimensional (2D) segmentations on radial plane slices of the bone joint. Based on the 3D bone surface image, a head center of a head of the bone joint and a neck axis of a neck of the bone joint are estimated. An alpha angle model is constructed based on the estimated head center and neck axis. Further, the alpha angle measurement is determined for each of the radial plane slices of the bone joint based on the constructed alpha angle model.

System and method for angle measurements using magnetic resonance images

In a method and apparatus for the examination of a predetermined volume portion of an object with a magnetic resonance (MR) fingerprinting procedure, an MR signal curve for voxels of the volume portion is acquired, and a comparison of the MR signal curve of the respective voxel is made with stored MR signal curves in order to determine the stored MR signal curve that conforms most closely to the MR signal curve, with the result of the comparison then being made available as an output. The comparison with the MR signal curve of the voxel is (initially) performed with a specific number of signal points of the MR signal curve. A quality measure is determined with which the quality of the most closely conforming stored MR signal curves is determined. The performance of the comparison for the respective voxel is repeated if the quality measure is below a predetermined quality threshold value, with the number of signal points being first increased by a difference number.

Magnetic resonance method and apparatus for accelerating magnetic resonance fingerprinting

A method for sparse iterative phase correction for Magnetic Resonance (MR) partial Fourier reconstruction includes acquiring a partial Fourier k-space dataset using an MR scanner and estimating, by a control computer, a coil sensitivity map associated with the MR scanner from fully sampled k-space center. The control computer extracts a symmetrically sampled k-space center dataset from the partial Fourier k-space dataset and determines a low-resolution image based on the symmetrically sampled k-space center dataset and the coil sensitivity map. The control computer also determines phase corresponding to the low-resolution image. An iterative reconstruction process may then be applied to generate an image based on the partial Fourier k-space dataset. This iterative reconstruction process applies a Fast Iterative Shrinkage Thresholding Algorithm (FISTA) with phase correction based on the phase corresponding to the low-resolution image.

Sparse iterative phase correction for MR partial fourier reconstruction

In a method and apparatus for acquiring a magnetic resonance imaging dataset of an area to be examined of a patient by magnetic resonance data are acquired over a prespecified acquisition period which has been fixed for the acquisition process. This acquisition period is divided into a number of sub-periods. For each sub-dataset of the magnetic resonance data acquired by undersampling in a sub-period, at least one motion value describing the motion status of the area to be examined is determined, and the data subsets to be used for the reconstruction of the magnetic resonance imaging dataset are selected in dependence on the motion values in order to minimize motion artifacts.

Method and apparatus for acquiring a magnetic resonance imaging dataset

In a method and magnetic resonance apparatus for segmenting image data of an examination object, raw data of the examination object are achieved with the operation of a magnetic resonance scanner. Quantitative image data of the examination object are then calculated in a processor from the raw data. At least one physical variable of the examination object is quantitatively ascertained pixelwise and is displayed. The quantitative image data are segmented for identification of predetermined objects in the quantitative image data, and displayed in a display unit.

Growing community of inventors

Dormitz, Germany

Esther Raithel