# Synthesizing Complex-Valued Multicoil MRI Data from Magnitude-Only Images

^{1}

^{2}

^{3}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Methods

#### 2.1. Preliminaries

#### 2.2. Generative Modeling

#### 2.2.1. Neural Network Architecture

#### 2.2.2. Synthetic Phase Generation

#### 2.2.3. Multi-Coil Data Generation

#### 2.3. Dataset

#### 2.4. Experiments

#### 2.4.1. Generative

#### 2.4.2. Evaluation: Physics-Based Image Reconstruction

## 3. Results

## 4. Discussion

## 5. Conclusions

## Supplementary Materials

## Author Contributions

## Funding

## Institutional Review Board Statement

## Informed Consent Statement

## Data Availability Statement

## Conflicts of Interest

## References

- Knoll, F.; Murrell, T.; Sriram, A.; Yakubova, N.; Zbontar, J.; Rabbat, M.; Defazio, A.; Muckley, M.J.; Sodickson, D.K.; Zitnick, C.L.; et al. Advancing machine learning for MR image reconstruction with an open competition: Overview of the 2019 fastMRI challenge. Magn. Reson. Med.
**2020**, 84, 3054–3070. [Google Scholar] [CrossRef] [PubMed] - Ong, F.; Amin, S.; Vasanawala, S.; Lustig, M. Mridata.org: An open archive for sharing MRI raw data. Proc. Intl. Soc. Mag. Reson. Med.
**2018**, 26, 1. [Google Scholar] - Calgary Campinas Public Dataset. 2020. Available online: https://sites.google.com/view/calgary-campinas-dataset/mr-reconstruction-challenge?authuser=0 (accessed on 22 March 2021).
- Desai, A.D.; Schmidt, A.M.; Rubin, E.B.; Sandino, C.M.; Black, M.S.; Mazzoli, V.; Stevens, K.J.; Boutin, R.; Re, C.; Gold, G.E.; et al. SKM-TEA: A Dataset for Accelerated MRI Reconstruction with Dense Image Labels for Quantitative Clinical Evaluation. In Proceedings of the Thirty-Fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2); Stanford University: Stanford, CA, USA, 2021. [Google Scholar]
- Lim, Y.; Toutios, A.; Bliesener, Y.; Tian, Y.; Lingala, S.G.; Vaz, C.; Sorensen, T.; Oh, M.; Harper, S.; Chen, W.; et al. A multispeaker dataset of raw and reconstructed speech production real-time MRI video and 3D volumetric images. arXiv
**2021**, arXiv:2102.07896. [Google Scholar] [CrossRef] [PubMed] - IXI Dataset. 2010. Available online: http://brain-development.org/ixi-dataset/ (accessed on 22 March 2021).
- The Human Connectome Project, University of Souterhn California. 2011. Available online: http://www.humanconnectomeproject.org/ (accessed on 22 March 2021).
- AccelMR Dataset. 2020. Available online: https://accelmrorg.wordpress.com/organizers/#jp-carousel-135/ (accessed on 2 May 2021).
- Oasis Dataset. 2007. Available online: https://www.oasis-brains.org/ (accessed on 2 May 2021).
- ADNI Dataset. 2004. Available online: http://adni.loni.usc.edu/data-samples/data-types/ (accessed on 2 May 2021).
- UC Biobank. 2006. Available online: https://www.ukbiobank.ac.uk/ (accessed on 2 May 2021).
- The Cancer Imaging Archive. 2010. Available online: http://www.cancerimagingarchive.net (accessed on 2 May 2021).
- Brain Tumor MRI Dataset. 2020. Available online: https://www.kaggle.com/shlezinger/brain-mri-data/ (accessed on 2 May 2021).
- Shimron, E.; Tamir, J.I.; Wang, K.; Lustig, M. Implicit data crimes: Machine learning bias arising from misuse of public data. Proc. Natl. Acad. Sci. USA
**2022**, 119, e2117203119. [Google Scholar] [CrossRef] - Hammernik, K.; Küstner, T.; Yaman, B.; Huang, Z.; Rueckert, D.; Knoll, F.; Akçakaya, M. Physics-Driven Deep Learning for Computational Magnetic Resonance Imaging. arXiv
**2022**, arXiv:2203.12215. [Google Scholar] [CrossRef] - Muckley, M.J.; Riemenschneider, B.; Radmanesh, A.; Kim, S.; Jeong, G.; Ko, J.; Jun, Y.; Shin, H.; Hwang, D.; Mostapha, M.; et al. Results of the 2020 fastMRI Challenge for Machine Learning MR Image Reconstruction. IEEE Trans. Med. Imaging
**2021**, 40, 2306–2317. [Google Scholar] [CrossRef] - Caliva’, F.; Shah, R.; Bharadwaj, U.U.; Majumdar, S.; Larson, P.; Pedoia, V. Breaking Speed Limits with Simultaneous Ultra-Fast {MRI} Reconstruction and Tissue Segmentation. In Proceedings of the Medical Imaging with Deep Learning; ML Research Press: Maastricht, The Netherlands, 2020. [Google Scholar]
- Eggers, H.; Börnert, P. Chemical shift encoding-based water-fat separation methods. J. Magn. Reson. Imaging
**2014**, 40, 251–268. [Google Scholar] [CrossRef] - He, X.; Yablonskiy, D.A. Biophysical mechanisms of phase contrast in gradient echo MRI. Proc. Natl. Acad. Sci. USA
**2009**, 106, 13558–13563. [Google Scholar] [CrossRef][Green Version] - Markl, M.; Chan, F.P.; Alley, M.T.; Wedding, K.L.; Draney, M.T.; Elkins, C.J.; Parker, D.W.; Wicker, R.; Taylor, C.A.; Herfkens, R.J.; et al. Time-resolved three-dimensional phase-contrast MRI. J. Magn. Reson. Imaging
**2003**, 17, 499–506. [Google Scholar] [CrossRef][Green Version] - Zhuang, B.; Sirajuddin, A.; Zhao, S.; Lu, M. The role of 4D flow MRI for clinical applications in cardiovascular disease: Current status and future perspectives. Quant. Imaging Med. Surg.
**2021**, 11, 4193–4210. [Google Scholar] [CrossRef] - Duyn, J.H.; van Gelderen, P.; Li, T.Q.; de Zwart, J.A.; Koretsky, A.P.; Fukunaga, M. High-field MRI of brain cortical substructure based on signal phase. Proc. Natl. Acad. Sci. USA
**2007**, 104, 11796–11801. [Google Scholar] [CrossRef] [PubMed][Green Version] - Shimron, E.; Grissom, W.; Azhari, H. Temporal differences (TED) compressed sensing: A method for fast MRgHIFU temperature imaging. NMR Biomed.
**2020**, 33, e4352. [Google Scholar] [CrossRef] - Cole, E.; Cheng, J.; Pauly, J.; Vasanawala, S. Analysis of deep complex-valued convolutional neural networks for MRI reconstruction and phase-focused applications. Magn. Reson. Med.
**2021**, 86, 1093–1109. [Google Scholar] [CrossRef] [PubMed] - Bassey, J.; Qian, L.; Li, X. A Survey of Complex-Valued Neural Networks. arXiv
**2021**, arXiv:2101.12249. [Google Scholar] [CrossRef] - Ji, S.; Yang, D.; Lee, J.; Choi, S.H.; Kim, H.; Kang, K.M. Synthetic MRI: Technologies and Applications in Neuroradiology. J. Magn. Reson. Imaging
**2020**, 55, 1013–1025. [Google Scholar] [CrossRef] - Gulani, V.; Schmitt, P.; Griswold, M.A.; Webb, A.G.; Jakob, P.M. Towards a Single-Sequence Neurologic Magnetic Resonance Imaging Examination: Multiple-Contrast Images From an IR TrueFISP Experiment. Investig. Radiol.
**2004**, 39, 767–774. [Google Scholar] [CrossRef] - Warntjes, J.; Leinhard, O.D.; West, J.; Lundberg, P. Rapid magnetic resonance quantification on the brain: Optimization for clinical usage. Magn. Reson. Med.
**2008**, 60, 320–329. [Google Scholar] [CrossRef] - Chen, Y.; Liu, S.; Wang, Y.; Kang, Y.; Haacke, E.M. STrategically Acquired Gradient Echo (STAGE) imaging, part I: Creating enhanced T1 contrast and standardized susceptibility weighted imaging and quantitative susceptibility mapping. Magn. Reson. Imaging
**2018**, 46, 130–139. [Google Scholar] [CrossRef] - Wang, Y.; Chen, Y.; Wu, D.; Wang, Y.; Sethi, S.K.; Yang, G.; Xie, H.; Xia, S.; Haacke, E.M. STrategically Acquired Gradient Echo (STAGE) imaging, part II: Correcting for RF inhomogeneities in estimating T1 and proton density. Magn. Reson. Imaging
**2018**, 46, 140–150. [Google Scholar] [CrossRef] - Haacke, E.M.; Chen, Y.; Utriainen, D.; Wu, B.; Wang, Y.; Xia, S.; He, N.; Zhang, C.; Wang, X.; Lagana, M.M.; et al. STrategically Acquired Gradient Echo (STAGE) imaging, part III: Technical advances and clinical applications of a rapid multi-contrast multi-parametric brain imaging method. Magn. Reson. Imaging
**2020**, 65, 15–26. [Google Scholar] [CrossRef] - Callaghan, M.F.; Mohammadi, S.; Weiskopf, N. Synthetic quantitative MRI through relaxometry modelling. NMR Biomed.
**2016**, 29, 1729–1738. [Google Scholar] [CrossRef][Green Version] - Blystad, I.; Warntjes, J.; Smedby, O.; Landtblom, A.M.; Lundberg, P.; Larsson, E.M. Synthetic Mri of the Brain in a Clinical Setting. Acta Radiol.
**2012**, 53, 1158–1163. [Google Scholar] [CrossRef] [PubMed] - Loecher, M.; Perotti, L.E.; Ennis, D.B. Using synthetic data generation to train a cardiac motion tag tracking neural network. Med. Image Anal.
**2021**, 74, 102223. [Google Scholar] [CrossRef] [PubMed] - Zhu, B.; Liu, J.Z.; Cauley, S.F.; Rosen, B.R.; Rosen, M.S. Image reconstruction by domain-transform manifold learning. Nature
**2018**, 555, 487–492. [Google Scholar] [CrossRef] [PubMed][Green Version] - Knoll, F.; Hammernik, K.; Kobler, E.; Pock, T.; Recht, M.P.; Sodickson, D.K. Assessment of the generalization of learned image reconstruction and the potential for transfer learning. Magn. Reson. Med.
**2018**, 81, 116–128. [Google Scholar] [CrossRef] [PubMed] - Goodfellow, I.; Pouget-Abadie, J.; Mirza, M.; Xu, B.; Warde-Farley, D.; Ozair, S.; Courville, A.; Bengio, Y. Generative Adversarial Nets. In Proceedings of the Advances in Neural Information Processing Systems; Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N., Weinberger, K., Eds.; Curran Associates, Inc.: Nice, France, 2014; Volume 27. [Google Scholar]
- Isola, P.; Zhu, J.Y.; Zhou, T.; Efros, A.A. Image-to-Image Translation with Conditional Adversarial Networks. In Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 21–26 July 2017. [Google Scholar] [CrossRef][Green Version]
- Sriram, A.; Zbontar, J.; Murrell, T.; Defazio, A.; Zitnick, C.L.; Yakubova, N.; Knoll, F.; Johnson, P. End-to-End Variational Networks for Accelerated MRI Reconstruction. In Medical Image Computing and Computer Assisted Intervention—MICCAI 2020; Springer International Publishing: Berlin/Heidelberg, Germany, 2020; pp. 64–73. [Google Scholar] [CrossRef]
- Ronneberger, O.; Fischer, P.; Brox, T. U-Net: Convolutional Networks for Biomedical Image Segmentation. In Lecture Notes in Computer Science; Springer International Publishing: Berlin/Heidelberg, Germany, 2015; pp. 234–241. [Google Scholar] [CrossRef][Green Version]
- Kingma, D.P.; Ba, J. Adam: A Method for Stochastic Optimization. arXiv
**2014**, arXiv:1412.6980. [Google Scholar] [CrossRef] - Uecker, M.; Lai, P.; Murphy, M.J.; Virtue, P.; Elad, M.; Pauly, J.M.; Vasanawala, S.S.; Lustig, M. ESPIRiT-an eigenvalue approach to autocalibrating parallel MRI: Where SENSE meets GRAPPA. Magn. Reson. Med.
**2013**, 71, 990–1001. [Google Scholar] [CrossRef][Green Version] - Wang, Z.; Bovik, A.C.; Sheikh, H.R.; Simoncelli, E.P. Image quality assessment: From error visibility to structural similarity. IEEE Trans. Image Process.
**2004**, 13, 600–612. [Google Scholar] [CrossRef][Green Version] - Saharia, C.; Chan, W.; Chang, H.; Lee, C.; Ho, J.; Salimans, T.; Fleet, D.; Norouzi, M. Palette: Image-to-Image Diffusion Models. In Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Proceedings; ACM: New York, NY, USA, 2022. [Google Scholar] [CrossRef]
- Angelopoulos, A.N.; Kohli, A.P.; Bates, S.; Jordan, M.; Malik, J.; Alshaabi, T.; Upadhyayula, S.; Romano, Y. Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imaging. In Proceedings of the 39th International Conference on Machine Learning, Baltimore, MD, USA, 17–23 July 2022; Volume 162, pp. 717–730. [Google Scholar]
- Borji, A. Pros and Cons of GAN Evaluation Measures. arXiv
**2018**, arXiv:1802.03446. [Google Scholar] [CrossRef][Green Version] - Salimans, T.; Goodfellow, I.; Zaremba, W.; Cheung, V.; Radford, A.; Chen, X.; Chen, X. Improved Techniques for Training GANs. In Proceedings of the Advances in Neural Information Processing Systems; Lee, D., Sugiyama, M., Luxburg, U., Guyon, I., Garnett, R., Eds.; Curran Associates, Inc.: Nice, France, 2016; Volume 29. [Google Scholar]
- Heusel, M.; Ramsauer, H.; Unterthiner, T.; Nessler, B.; Hochreiter, S. GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium. In Proceedings of the Advances in Neural Information Processing Systems; Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R., Eds.; Curran Associates, Inc.: Nice, France, 2017; Volume 30. [Google Scholar]
- Mei, X.; Liu, Z.; Robson, P.M.; Marinelli, B.; Huang, M.; Doshi, A.; Jacobi, A.; Cao, C.; Link, K.E.; Yang, T.; et al. RadImageNet: An Open Radiologic Deep Learning Research Dataset for Effective Transfer Learning. Radiol. Artif. Intell.
**2022**, 4. [Google Scholar] [CrossRef]

**Figure 1.**The proposed synthetic raw data generation and image reconstruction pipeline. The generative model takes magnitude images as an input seed and produces plausible synthetic phase images as output, which are trained to match ground truth phase images from the dataset. Synthetic complex-valued data is obtained by combining the input (ground truth) magnitude image and synthetic phase image to yield real and imaginary components. Estimated sensitivity maps calculated with ESPIRiT from the training dataset are then applied to synthetic complex-valued multi-coil data to compute multi-coil k-space encoded with synthetic phase information. The synthetic raw data were evaluated by training a Variational Network using undersampled k-space data.

**Figure 2.**Representative ground truth magnitude, ground truth phase, and synthetic phase images generated from the conditional GAN. Synthetic phase images show expected features, including appropriate noise patterns, low spatial-frequency components and tissue contrast between the ventricles and nearby brain tissue, but exhibit some blocking artifacts possibly from the patchGAN discriminator.

**Figure 3.**Sample image comparisons at 4× and 8× acceleration factors for the 20-coil dataset. The columns compare the zero-filled image, reconstructed image, and error maps generated with 2 Variational Networks trained on ground truth and synthetic k-space.

**Figure 4.**Sample image comparisons at 4× and 8× acceleration factors for the 16-coil dataset. The columns compare the zero-filled image, reconstructed image, and error maps generated with 2 Variational Networks trained on ground truth and synthetic k-space.

**Figure 5.**Performance of ground truth-trained and synthetically trained Variational Network reconstruction models at different acceleration factors for 16-coil and 20-coil datasets. At up to 10× acceleration factors, synthetically trained models show comparable performance to ground-truth trained models. These data are also shown in tables in the Supplementary Material.

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |

© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Deveshwar, N.; Rajagopal, A.; Sahin, S.; Shimron, E.; Larson, P.E.Z. Synthesizing Complex-Valued Multicoil MRI Data from Magnitude-Only Images. *Bioengineering* **2023**, *10*, 358.
https://doi.org/10.3390/bioengineering10030358

**AMA Style**

Deveshwar N, Rajagopal A, Sahin S, Shimron E, Larson PEZ. Synthesizing Complex-Valued Multicoil MRI Data from Magnitude-Only Images. *Bioengineering*. 2023; 10(3):358.
https://doi.org/10.3390/bioengineering10030358

**Chicago/Turabian Style**

Deveshwar, Nikhil, Abhejit Rajagopal, Sule Sahin, Efrat Shimron, and Peder E. Z. Larson. 2023. "Synthesizing Complex-Valued Multicoil MRI Data from Magnitude-Only Images" *Bioengineering* 10, no. 3: 358.
https://doi.org/10.3390/bioengineering10030358