Home Publications Research Grants Inventions & Patents Awards Additional Research Activities Faculties & Institutions Research Areas

Complementary time-frequency domain networks for dynamic parallel MR image reconstruction

Qin C, Duan J, Hammernik K, Schlemper J, Kuestner T, Botnar R, Prieto C, Price AN, Hajnal J, Rueckert D (2021)

---

Publication Type: Journal article

Publication year: 2021

Journal

Book Volume: 86

Pages Range: 3274-3291

Journal Issue: 6

DOI: 10.1002/mrm.28917

Abstract

Purpose: To introduce a novel deep learning-based approach for fast and high-quality dynamic multicoil MR reconstruction by learning a complementary time-frequency domain network that exploits spatiotemporal correlations simultaneously from complementary domains. Theory and Methods: Dynamic parallel MR image reconstruction is formulated as a multivariable minimization problem, where the data are regularized in combined temporal Fourier and spatial (x-f) domain as well as in spatiotemporal image (x-t) domain. An iterative algorithm based on variable splitting technique is derived, which alternates among signal de-aliasing steps in x-f and x-t spaces, a closed-form point-wise data consistency step and a weighted coupling step. The iterative model is embedded into a deep recurrent neural network which learns to recover the image via exploiting spatiotemporal redundancies in complementary domains. Results: Experiments were performed on two datasets of highly undersampled multicoil short-axis cardiac cine MRI scans. Results demonstrate that our proposed method outperforms the current state-of-the-art approaches both quantitatively and qualitatively. The proposed model can also generalize well to data acquired from a different scanner and data with pathologies that were not seen in the training set. Conclusion: The work shows the benefit of reconstructing dynamic parallel MRI in complementary time-frequency domains with deep neural networks. The method can effectively and robustly reconstruct high-quality images from highly undersampled dynamic multicoil data ((Formula presented.) and (Formula presented.) yielding 15 s and 10 s scan times respectively) with fast reconstruction speed (2.8 seconds). This could potentially facilitate achieving fast single-breath-hold clinical 2D cardiac cine imaging.

Involved external institutions

How to cite

APA:

Qin, C., Duan, J., Hammernik, K., Schlemper, J., Kuestner, T., Botnar, R.,... Rueckert, D. (2021). Complementary time-frequency domain networks for dynamic parallel MR image reconstruction. Magnetic Resonance in Medicine, 86(6), 3274-3291. https://doi.org/10.1002/mrm.28917

MLA:

Qin, Chen, et al. "Complementary time-frequency domain networks for dynamic parallel MR image reconstruction." Magnetic Resonance in Medicine 86.6 (2021): 3274-3291.

BibTeX: Download