Siemens Aktiengesellschaft

Siemens Healthcare Gmbh

Centre Hospitalier Universitaire Vaudois

Siemens Healthineers Ag

Davide Piccini

Tobias Kober

Jérôme Yerly

Peter Speier

Michael Zenge

Robin Demesmaeker

Matthias Stuber

Jérôme Chaptinel

Marie-Pierre Jolly

Xiaoguang Lu

Jens Gühring

Christoph Guetter

Arne Littmann

Gunnar Krueger

Carmel Hayes

John Heerfordt

Christopher Roy

Bénédicte Maréchal

A method and a system automatically perform an image reconstruction of a biological object. The method includes acquiring at different time points t_i signal data for imaging the biological object and clustering a set of data in connection with the acquired signal data. The clustering includes constructing a matrix C, wherein an element Cof the matrix C is the value n_j of one of the data of the dataset acquired at the time point t_i, and then performing a similarity clustering based on the matrix C. At least one of the clusters is selected and determining for each of the time points t_i that are part of the cluster all acquired signal data that have been acquired within a predefined temporal threshold with respect to the considered time point t_i. The image reconstruction of the biological object is performed with the previously determined acquired signal data.

Method and system for improving magnetic resonance images

A method and system are provided for detecting a position of a periodically moving organ in a MRI examination. MR images of an examining person including a periodically moving organ are provided over a plurality of periodic cycles of the periodically moving organ. Based on the provided MR images, a pixel frequency is associated with each pixel of the MR images. Using the associated pixel frequencies and the positions of the pixels within the MR images, the position and the frequency of the periodically moving organ are determined.

Detection of position and frequency of a periodically moving organ in an MRI examination

The disclosure relates to a method for the interactive acquisition of data from an object under investigation by a magnetic resonance system. The data is acquired from the object under investigation with the magnetic resonance system and images are automatically reconstructed and displayed in real time based on the data. A time interval is determined during which a predetermined condition is met in the images. Quality images are automatically reconstructed based on the data acquired within the time interval. The temporal resolution during reconstruction of the quality images is higher than the temporal resolution during reconstruction of the images.

Interactive data acquisition and reconstruction by a magnetic resonance system

In order to reduce the time and effort required to generate high-quality image reconstructions, a machine-trained neural network may assign a quality score to an image at each iteration of a reconstruction. The neural network may confirm that the iterative reconstruction process increases image quality as each iteration converges to the solution of an optimization problem. The image quality score generated by the neural network may drive the reconstruction toward better image quality by contributing to a regularization term of a cost function minimized by the optimization problem. The neural network may allow for multiple reconstruction of image data to be performed rapidly and for the highest image quality reconstruction to be identified. Additionally, the neural network may provide exit criteria of the iterative reconstruction or may contribute to the optimization problem.

Machine learning in iterative image reconstruction

A method for acquiring raw data for generating image data of a target organ via a magnetic resonance system is described. In an embodiment, test raw data is initially acquired from a measurement region including at least the target organ using a plurality of magnetic resonance coils. Test image data is reconstructed from the test raw data. Furthermore, a mask defining the position and the dimensions of the target organ is generated using the reconstructed test image data. The magnetic resonance coils, to be used for the image acquisition, are then selected. This takes place on the basis of intensity values from a region covered by the mask and intensity values of a measurement region lying outside of the mask. Finally, the measurement is performed by acquiring raw data via the selected magnetic resonance coils. Furthermore, a device for acquiring raw data for generating image data is also described.

Method and control device for generating magnetic resonance images

A method and a magnetic resonance imaging apparatus provide subject/object motion detection and correction during a MRI scan. The method includes generating via a magnetic resonance scanner a magnetic field gradient and a radio-frequency signal for the MRI scan. The radio-frequency signal contains a successive repetition of pulse sequences, each pulse sequence starting with a radio-frequency excitation pulse. A time between two successive radio-frequency excitation pulses are defined as a repetition time. Detecting, from a readout signal emitted in response to the pulse sequence, time-points in which motion has occurred. Interleaves are automatically created. A sampling of the k-space is performed by arranging k-space MRI readout signals acquired over each repetition time of the pulse sequence into several groups of interleaves of uniform k-space sampling reconstructing separately each subset of interleaves for obtaining low resolution MR images.

Method and apparatus for performing guided and flexible self-navigated structural MRI for motion compensation

In a method and magnetic resonance (MR) apparatus for combining MR signals that were acquired with different acquisition coils from a region of an examination subject at least two MR signals that are based on MR signals acquired with at least two different acquisition coils are provided to a processor. Due to the spatially differing arrangement of the respective acquisition coils, the at least two MR signals image the region of the examination subject with different sensitivity profiles. The provided MR signals are combined, such that unwanted MR signal portions are suppressed, to form a combined MR signal with the suppression of unwanted MR signal portions being implemented by MR signal portions that were acquired with an acquisition coil that detects the unwanted MR signal portions with increased sensitivity in comparison to other acquisition coils being weighted less in the combined MR signal than other MR signal portions.

Method and magnetic resonance system for combining signals acquired from different acquisition coils

A system receives cardiac cine MR images consists of multiple slices of the heart over time. A series of short axis images slices are received. Long axis images are also received by the system, wherein a base plane defined by landmark points is detected. An intersection of the base plane with a contour of a heart chamber is determined for a plurality of slices in the short axis image. A volume for each of the contour slices covering the heart chamber, including for contours that are limited by base plane intersections, is evaluated. All slice volumes are summed to determine a total volume of the chamber. In one embodiment the chamber is a left ventricle and the landmark is a mitral valve. An ejection factor is determined.

Cardiac chamber volume computation from contours and base plane in cardiac MR Cine images

For radial data acquisition in three-dimensional k-space in an MR measurement for a magnetic resonance system, data in k-space are acquired along straight-line spokes. Each of the spokes is thereby defined by a point on a sphere and the center point of this sphere, wherein the center point corresponding to the center of k-space. The points are arranged on the sphere such that a distribution of the points obeys the spiral phyllotaxis, in particular the Fibonacci phyllotaxis.

Growing community of inventors

Prilly, Switzerland

Davide Piccini