Siemens Healthineers Ag

Siemens Healthcare Gmbh

Simon Arberet

Mariappan S Nadar

Boris Mailhe

Mahmoud Mostapha

Marcel Dominik Nickel

Thomas Benkert

Xiao Chen

Peter Speier

Mathias Nittka

Dorin Comaniciu

Gregor Körzdörfer

Guillaume Daval Frerot

Nirmal Janardhanan

Esther Raithel

Qiaoying Huang

Kelvin Chow

Laszlo Lazar

Michael Bush

Anatole Louis Jerome Moreau

Hongki Lim

Florent Billy Romaric Gbelidji

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

For reconstruction in medical imaging, such as reconstruction in MR imaging, an iterative, hierarchal network for regularization may decrease computational complexity. To further maintain computational complexity while improving robustness, auxiliary information is used in the regularization and corresponding reconstruction. The auxiliary information is in put to the machine-learned network.

Iterative hierarchal network for regulating medical image reconstruction

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

A computer-implemented method includes, based on an input dataset 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 determines, for multiple K-space positions at which the input dataset comprises respective source data, a contribution of respective K-space values associated with the input dataset to a K-space representation of the reconstructed image.

Data-consistency for image reconstruction

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

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, self-consistency using data augmentation is improved by including data consistency. Artificial intelligence is trained based on self-consistency and data consistency, allowing training without supervision. Fully sampled data and/or ground truth is not needed but may be used. The machine-trained model is less likely to reconstruct images with motion artifacts, and/or the training data may be more easily gathered by not requiring full sampling.

Self-supervised machine learning for medical image reconstruction

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

For correction of an image from an imaging system, an inverse solution uses an imaging prior as a regularizer and a physics model of the imaging system. An invertible network is used as the deep-learnt generative model in the regularizer of the inverse solution with the physics model of the degradation behavior of the imaging system. The prior model based on the invertible network provides a closed-form expression of the prior probability, resulting in a more versatile or accurate probability prediction.

Image correction using an invertable network

For magnetic resonance (MR) reconstruction using artificial intelligence (AI), the AI-based reconstruction for MR imaging systems is offloaded to one or more servers. A remote server performs AI-based reconstruction. A library of recent, old, custom, and/or publicly available AI-based reconstruction processes may be rapidly deployed and available to the server, which has the memory and processing resources for AI-based reconstruction. Load balancing of the data and/or between servers may improve performance.

Architecture for artificial intelligence-based magnetic resonance reconstruction

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

For reconstruction in medical imaging, such as reconstruction in MR imaging, an iterative, hierarchal network for regularization may decrease computational complexity. The machine-learned network of the regularizer is unrolled or made iterative. For each iteration, nested U-blocks form a hierarchy so that some of the down-sampling and up-sampling of some U-blocks begin and end with lower resolution data or features, reducing computational complexity.

Growing community of inventors

Princeton, NJ, United States of America

Simon Arberet