Siemens Healthcare Gmbh

Siemens Healthineers Ag

Siemens Aktiengesellschaft

University of California

Siemens Medical Solutions Usa, Inc.

Duke University

Siemens Aktiengesellchaft

Marcel Dominik Nickel

Stephan Kannengiesser

Mariappan S Nadar

Xiaodong Zhong

Boris Mailhe

Simon Arberet

Berthold Kiefer

Mahmoud Mostapha

Thomas Benkert

Vibhas S Deshpande

Qiu Wang

Robert Grimm

Brian Dale

Gregor Körzdörfer

Tommaso Mansi

Michael Zenge

Xiao Chen

Esther Raithel

Simon Bauer

Li Pan

Holden H Wu

Nirmal Janardhanan

Mustafa R Bashir

Manuel Schneider

Tess Armstrong

Dominik Paul

Thorsten Feiweier

Peter Speier

Li Zhang

Alto Stemmer

Matthias Fenchel

Edgar Mueller

Ingmar Voigt

Ti-chiun Chang

Hui Xue

Xiaoming Bi

Christoph Forman

Jun Liu

Thomas Pheiffer

Edgar Müller

Alban Lefebvre

Nadine Dispenza

Jan Fritz

Stephan Kannengießer

Kai Tobias Block

Tongbai Meng

Fei Han

Florian Knoll

Sebastien Piat

Zhili Yang

Jyotipriya Das

Mahesh Bharath Keerthivasan

Sajan Goud Lingala

Fasil Gadjimuradov

Derya Gol Gungor

Inge Brinkmann

Julia Traechtler

Sebastian Fürst

Isabel Dregely

Claudia Fellner

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

The disclosure relates to MRI reconstruction of multiple MRI measurement datasets acquired throughout a measurement time duration. Patient motion can occur during the measurement time duration. Warping operators, sometimes also referred to as motion field, are incorporated into an iterative optimization of the MRI reconstruction.

Magnetic resonance imaging reconstruction using machine learning and motion compensation

Systems and methods for reconstruction for a medical imaging system. An adapter is used to adapt scan data so that different quantities of repetitions or directions may be used to train and implement a single multichannel backbone network.

Multichannel deep learning reconstruction of multiple repetitions

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 are provided for determining magnetic resonance images showing different contrasts in an examination. Magnetic resonance data for all magnetic resonance images are acquired using the same acquisition technique and the magnetic resonance images are reconstructed from their magnetic resonance data sets using at least one reconstruction algorithm. The reconstruction comprises at least one de-noising step. After acquisition of the magnetic resonance data, at least one noise strength measure is determined for the magnetic resonance data sets for each contrast, and de-noising strengths for the de-noising step are chosen individually for each contrast depending on the respective at least one noise strength measure.

Computer-implemented method for determining magnetic resonance images showing different contrasts, magnetic resonance device, computer program and electronically readable storage medium

For reconstruction, a machine-learned model is adapted to allow for reconstruction based on the repetitions available in some scanning. The reconstruction for one or more subsets is performed during the scanning. The machine-learned model is trained to reconstruction separately or independently for each repetition or to use information from previous repetitions without requiring waiting for completion of scanning. The reconstructed image may be displayed much more rapidly after completion of the acquisition since the reconstruction begins during the reconstruction.

Deep learning-based realtime reconstruction

Techniques are provided for determining a magnetic resonance imaging (MRI) image using multiple measurement data sets that form a propeller pattern. Partial MRI images are reconstructed for each measurement data set. The partial MRI images are then combined.

Propeller magnetic resonance acquisition and blade-specific reconstruction

In a method for generating combined image data based on first magnetic resonance (MR) data and second MR data, the first MR data and the second MR data are provided, the first MR data having been generated by a first actuation of a magnetic resonance device from an examination area of an examination object using a first sequence module, and the second MR data having been generated by a second actuation of the magnetic resonance device from the examination area of the examination object using the first sequence module, the first MR data and the second MR data are registered to one another to generate first registered MR data and second registered MR data; the first registered MR data and the second registered MR data are statistically combined to generate combined image data, and the combined image data is provided as an output in electronic form as a data file.

Methods and systems for generating combined image data based on MR data

For reconstruction in medical imaging using phase correction, a machine learning model is trained for reconstruction of an image. The reconstruction may be for a sequence without repetitions or may be for a sequence with repetitions. Where repetitions are used, rather than using just a loss for that repetition in training, the loss based on an aggregation of images reconstructed from multiple repetitions may used to train the machine learning model. In either approach, a phase correction is applied in machine training. A phase map is extracted from output of the model in training or extracted from the ground truth of the training data. The phase correction, based on the phase map, is applied to the ground truth and/or the output of the model in training. The resulting machine-learned model may better reconstruct an image as a result of having been trained using phase correction.

Machine learning for medical image reconstruction with phase correction

For reconstruction in medical imaging, user control of a characteristic (e.g., noise level) of the reconstructed image is provided. A machine-learned model alters the reconstructed image to enhance or reduce the characteristic. The user selected level of characteristic is then provided by combining the reconstructed image with the altered image based on the input level of the characteristic. Personalized or more controllable impression for medical imaging reconstruction is provided without requiring different reconstructions.

Reconstruction with user-defined characteristic strength

A computer implemented method of processing a medical image is disclosed. The method includes receiving a medical image comprising a first plurality of pixels each having an initial pixel value. For each of the first plurality of pixels, a filtering operation is applied to the pixel to generate a filtered pixel value for the pixel based on the initial pixel values of pixels that surround the pixel in the medical image. For each of the first plurality of pixels, a comparison of the initial pixel value with the filtered pixel value is performed. The method comprises, for each of the first plurality of pixels, determining, based on the comparison, whether or not to categorize the pixel as an erroneous pixel; and for each of the first plurality of pixels for which it is determined to categorize the pixel as an erroneous pixel, categorizing the pixel as an erroneous pixel.

Method and apparatus for processing a medical image

DCE MR images are obtained from a MR scanner and under a free-breathing protocol is provided. A neural network assigns a perfusion metric to DCE MR images. The neural network includes an input layer configured to receive at least one DCE MR image representative of a first contrast enhancement state and of a first respiratory motion state and at least one further DCE MR image representative of a second contrast enhancement state and of a second respiratory motion state. The neural network further includes an output layer configured to output at least one perfusion metric based on the at least one DCE MR image and the at least one further DCE MR image. The neural network with interconnections between the input layer and the output layer is trained by a plurality of datasets, each of the datasets having an instance of the at least one DCE MR image and of the at least one further DCE MR image for the input layer and the at least one perfusion metric for the output layer.

Technique for assigning a perfusion metric to DCE MR images

For reconstruction in medical imaging using a scan protocol with repetition, a machine learning model is trained for reconstruction of an image for each repetition. Rather than using a loss for that repetition in training, the loss based on an aggregation of images reconstructed from multiple repetitions is used to train the machine learning model. This loss for reconstruction of one repetition based on aggregation of reconstructions for multiple repetitions is based on deep set-based deep learning. The resulting machine-learned model may better reconstruct an image from a given repetition and/or a combined image from multiple repetitions than a model learned from a loss per repetition.

Aggregation based on deep set learning in magnetic resonance reconstruction

Magnetic resonance imaging (MRI) image reconstruction using machine learning is described. A variational or unrolled deep neural network can be used in the context of an iterative optimization. In particular, a regularization operation can be based on a deep neural network. The deep neural network can take, as an input, an aliasing data structure being indicative of aliasing artifacts in one or prior images of the iterative optimization. The deep neural networks can be trained to suppress aliasing artifacts.

Magnetic resonance imaging reconstruction using machine learning

A computer-implemented method includes, based on scan data defining an input image, determining a reconstructed image using a reconstruction algorithm, and executing a data consistency operation for enforcing consistency between the input image and the reconstructed image. The data consistency operation includes using a norm ball projection that takes into account the available noise level information in order to automatically adjust the balance between the network prediction and the input measurements.

Noise adaptive data consistency in deep learning image reconstruction via norm ball projection

Growing community of inventors

Herzogenaurach, Germany

Marcel Dominik Nickel