Search

EP-4741864-A1 - IMAGE RECONSTRUCTION IN MAGNETIC RESONANCE IMAGING COMPRISING A DATA CONSISTENCY OPERATION AND A REGULARIZATION OPERATION

EP4741864A1EP 4741864 A1EP4741864 A1EP 4741864A1EP-4741864-A1

Abstract

For image reconstruction in MRI, MRI data (20) corresponding to an MRI acquisition according to a sampling scheme is received, wherein the sampling scheme defines a corresponding sampling number indicating how often the respective k-space point has been sampled in the MRI acquisition. Reconstructed image data (X) is generated by applying processing steps (24) comprising a data consistency operation (25) to initial image data (X 0 ). A projection matrix according to the sampling scheme is received and is modified by scaling its entries depending on the sampling numbers. The data consistency operation (25) is carried out depending on a forward operator (A) comprising the modified projection matrix.

Inventors

  • NICKEL, MARCEL DOMINIK
  • ZELLER, MARIO
  • LITTMANN, ARNE
  • MEIXNER, CHRISTIAN

Assignees

  • Siemens Healthineers AG

Dates

Publication Date
20260513
Application Date
20241111

Claims (15)

  1. Computer-implemented method for image reconstruction in magnetic resonance imaging, MRI, wherein - MRI data (20) is received, the MRI data (20) corresponding to an MRI acquisition according to a predefined sampling scheme, wherein the sampling scheme defines, for all k-space points (21), a corresponding sampling number indicating how often the respective k-space point has been sampled in the MRI acquisition; - reconstructed image data (X) is generated by applying processing steps (24) to predefined initial image data (X 0 ), the processing steps (24) comprising a data consistency operation (25) and a regularization operation (26); - a projection matrix according to the sampling scheme is received and the projection matrix is modified by scaling entries of the projection matrix depending on the respective sampling numbers defined by the sampling scheme; and - the data consistency operation (25) is carried out depending on a forward operator (A) comprising the modified projection matrix.
  2. Computer-implemented method according to claim 1, wherein the MRI acquisition comprises two or more acquisition shots (22a, 22b, 22c, 22d, 22e), each of the two or more acquisition shots (22a, 22b, 22c, 22d, 22e) corresponding to an incomplete sampling of the k-space.
  3. Computer-implemented method according to claim 2, wherein a subsampling scheme of a first acquisition shot (22a, 22b, 22c, 22d, 22e) of the two or more acquisition shots (22a, 22b, 22c, 22d, 22e) is identical or partially identical to a subsampling scheme of a second acquisition shot (22a, 22b, 22c, 22d, 22e) of the two or more acquisition shots (22a, 22b, 22c, 22d, 22e).
  4. Computer-implemented method according to one of the preceding claims, wherein the scaling of a respective entry of the projection matrix comprises multiplying the respective entry with a factor α , which is directly proportional to the corresponding sampling number.
  5. Computer-implemented method according to claim 4 and one of claims 2 or3, wherein the factor α is indirectly proportional to an acceleration factor of the respective acquisition shot (22a, 22b, 22c, 22d, 22e).
  6. Computer-implemented method according to one of the preceding claims, wherein the sampling number is at least two for a set of k-space points (23a) and the data consistency operation (25) comprises an averaging operation based on the MRI data (20) for the set of k-space points (23a).
  7. Computer-implemented method according claim 6, wherein averaged MRI data (20) is computed by averaging respective values of the MRI data (20) corresponding to the same k-space point of the set of k-space points (23a) and the data consistency operation (25) is carried out depending on the averaged MRI data.
  8. Computer-implemented method according to claim 7, wherein intermediate image data is determined depending on the initial image data (X 0 ) and the data consistency operation (25) comprises - computing intermediate k-space data depending on the intermediate image data and the forward operator (A); and - computing a difference between the intermediate k-space data and the averaged MRI data (20).
  9. Computer-implemented method according to claim 8, wherein the data consistency operation (25) comprises converting the difference into an image domain based on the forward operator (A) and computing a sum of the converted difference and the intermediate image data and the reconstructed image data (X) is generated depending on the sum.
  10. Computer-implemented method according to claim 9, wherein regularized image data is generated by the regularization operation (26) depending on the sum and the reconstructed image data (X) is generated depending on the regularized image data.
  11. Computer-implemented method according to one of the preceding claims, wherein the regularization operation (26) comprises a wavelet regularization or a total variation regularization.
  12. Computer-implemented method according to one of claims 1 to 11, wherein the regularization operation (26) comprises an application of a trained machine learning model, MLM, for image enhancement and/or for image denoising and/or image sharpening and/or image resolution enhancement and/or image artifact reduction.
  13. Data processing system (14), which is adapted to carry out a computer-implemented method according to one of the preceding claims.
  14. MRI arrangement (1) comprising a data processing system (14) according to claim 13 and an MRI device (7), which is configured to generate the MRI data (20) by carrying out the MRI acquisition.
  15. Computer program product comprising instructions, which, when executed by a data processing system (14), cause the data processing system (14) to carry out a computer-implemented method according to one of claims 1 to 12.

Description

The present invention is directed to a computer-implemented method for image reconstruction in magnetic resonance imaging, MRI, wherein MRI data is received, the MRI data corresponding to an MRI acquisition according to a predefined sampling scheme, wherein the sampling scheme defines, for all k-space points, a corresponding sampling number indicating how often the respective k-space point has been sampled in the MRI acquisition, and wherein reconstructed image data is generated by applying processing steps to predefined initial image data, the processing steps comprising a data consistency operation and a regularization operation. The invention is further directed to a corresponding data processing system, to MRI arrangement comprising said data processing system, and to a corresponding computer program product. Here and in the following, the term "image data" denotes image data in position space, also denoted as image space or image domain, unless stated otherwise. In MRI, image reconstruction denotes the process to generate a two-dimensional image or a three-dimensional image, typically in form of multiple two-dimensional images for multiple positions along the so-called slice direction, in position space from MRI data acquired in k-space depending on MR signals being emitted by an object to be imaged. In general, the k-space and the position space are related to each other via Fourier transformation. When parallel MRI is pursued, datasets are received from multiple receiver coils, which receive the emitted MR signals. Furthermore, k-space subsampling techniques may be employed, where the k-space is sampled with a sampling rate that is too low to fulfil the Nyquist criterion. The latter is also denoted as undersampling or incomplete sampling. The multiple coils or the datasets provided by them, respectively, are denoted as coil channels. The reconstructed image data can therefore not be obtained solely by Fourier transforming the acquired k-space data. Rather, more sophisticated reconstruction techniques need to be used. Various methods for MR image reconstruction are known, which may for example involve iterative processes and/or optimizations based on physical relations. Furthermore, trained machine learning models, MLMs, for example artificial neural networks, ANNs, in particular deep convolutional neural networks, CNNs, may be used for the MR image reconstruction, for example in combination with conventional reconstruction approaches. Therein, "conventional" refers to the fact that no MLM is involved. Such methods are sometimes called deep learning, DL, reconstructions. A review of the topic is presented in the publication G. Zeng et al.: "A review on deep learning MRI reconstruction without fully sampled k-space." BMC Med Imaging 21, 195 (2021). U-Net, introduced in the publication of O. Ronneberger et al.: "U-Net: Convolutional Networks for Biomedical Image Segmentation" (arXiv:1505.04597v1), is a well-known CNN usable for example for image segmentation or image enhancement. The publication by K. Hammernik et al.: "Σ-net: Systematic Evaluation of Iterative Deep Neural Networks for Fast Parallel MR Image Reconstruction" (arXiv:1912.09278v1) describes a deep-learning enabled unrolled neural network Σ-net and systematically investigates the influence of various data consistency layers, (semi-)supervised learning and ensembling strategies, defined in a Σ-net, for accelerated parallel MR image reconstruction using deep learning. The Σ-net may be considered as a deep-learning enabled unrolled neural network. Another example for such unrolled neural network is implemented in the product solution Deep Resolve Boost, DRB, (https://www.siemens-healthineers.com/magnetic-resonance-imaging/options-and-upgrades/clinical-applications/deep-resolve-boost, retrieved on October 25, 2024, 08:24am). The underlying concept is described in the publication J. Hermann et al.: "Feasibility and Implementation of a Deep Learning MR Reconstruction for TSE Sequences in Musculoskeletal Imaging", Diagnostics 2021, 11, 1484 (see for example Figure 2 and the corresponding description therein). Such deep-learning enabled unrolled neural networks outperform conventional parallel imaging methods in the achievable acceleration of data acquisition. Such networks consist of cascades of gradient update and regularization steps. While the regularization is for example enabled by an MLM, such as U-net or a Down-Up network, the gradient update steps typically use the measured MRI data in k-space to ensure data consistency. The publication by S.H. Joshi et al.: "MRI resolution enhancement using total variation regularization", Proc IEEE Int Symp Biomed Imaging, 2009:161-164, describes the total variation regularization technique for MRI applications. The publication by M. Guerquin-Kern et al.: "Wavelet-regularized reconstruction for rapid MRI" 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Boston, MA, USA, pp. 19