1
|
Qin C, Duan J, Hammernik K, Schlemper J, Küstner T, Botnar R, Prieto C, Price AN, Hajnal JV, Rueckert D. Complementary time-frequency domain networks for dynamic parallel MR image reconstruction. Magn Reson Med 2021; 86:3274-3291. [PMID: 34254355 DOI: 10.1002/mrm.28917] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/10/2020] [Revised: 06/10/2021] [Accepted: 06/14/2021] [Indexed: 11/11/2022]
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 ( 16 × and 24 × 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.
Collapse
Affiliation(s)
- Chen Qin
- Institute for Digital Communications, School of Engineering, University of Edinburgh, Edinburgh, UK.,Department of Computing, Imperial College London, London, UK
| | - Jinming Duan
- School of Computer Science, University of Birmingham, Birmingham, UK
| | - Kerstin Hammernik
- Department of Computing, Imperial College London, London, UK.,Institute for AI and Informatics, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany
| | - Jo Schlemper
- Department of Computing, Imperial College London, London, UK.,Hyperfine Research Inc., Guilford, CT, USA
| | - Thomas Küstner
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, UK.,Department of Diagnostic and Interventional Radiology, Medical Image and Data Analysis, University Hospital of Tuebingen, Tuebingen, Germany
| | - René Botnar
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, UK
| | - Claudia Prieto
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, UK
| | - Anthony N Price
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, UK
| | - Joseph V Hajnal
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, UK
| | - Daniel Rueckert
- Department of Computing, Imperial College London, London, UK.,Institute for AI and Informatics, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany
| |
Collapse
|
2
|
Ghodrati V, Shao J, Bydder M, Zhou Z, Yin W, Nguyen KL, Yang Y, Hu P. MR image reconstruction using deep learning: evaluation of network structure and loss functions. Quant Imaging Med Surg 2019; 9:1516-1527. [PMID: 31667138 PMCID: PMC6785508 DOI: 10.21037/qims.2019.08.10] [Citation(s) in RCA: 40] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/02/2019] [Accepted: 08/12/2019] [Indexed: 11/06/2022]
Abstract
BACKGROUND To review and evaluate approaches to convolutional neural network (CNN) reconstruction for accelerated cardiac MR imaging in the real clinical context. METHODS Two CNN architectures, Unet and residual network (Resnet) were evaluated using quantitative and qualitative assessment by radiologist. Four different loss functions were also considered: pixel-wise (L1 and L2), patch-wise structural dissimilarity (Dssim) and feature-wise (perceptual loss). The networks were evaluated using retrospectively and prospectively under-sampled cardiac MR data. RESULTS Based on our assessments, we find that Resnet and Unet achieve similar image quality but that former requires only 100,000 parameters compared to 1.3 million parameters for the latter. The perceptual loss function performed significantly better than L1, L2 or Dssim loss functions as determined by the radiologist scores. CONCLUSIONS CNN image reconstruction using Resnet yields comparable image quality to Unet with 10X the number of parameters. This has implications for training with significantly lower data requirements. Network training using the perceptual loss function was found to better agree with radiologist scoring compared to L1, L2 or Dssim loss functions.
Collapse
Affiliation(s)
- Vahid Ghodrati
- Department of Radiological Sciences, David Geffen School of Medicine, University of California, Los Angeles, CA, USA
- Biomedical Physics Inter-Departmental Graduate Program, University of California, Los Angeles, CA, USA
| | - Jiaxin Shao
- Department of Radiological Sciences, David Geffen School of Medicine, University of California, Los Angeles, CA, USA
| | - Mark Bydder
- Department of Radiological Sciences, David Geffen School of Medicine, University of California, Los Angeles, CA, USA
| | - Ziwu Zhou
- Department of Radiological Sciences, David Geffen School of Medicine, University of California, Los Angeles, CA, USA
- Department of Bioengineering, University of California, Los Angeles, CA, USA
| | - Wotao Yin
- Department of Mathematics, University of California, Los Angeles, CA, USA
| | - Kim-Lien Nguyen
- Division of Cardiology, Department of Medicine, David Geffen School of Medicine, University of California, Los Angeles, CA, USA
| | - Yingli Yang
- Biomedical Physics Inter-Departmental Graduate Program, University of California, Los Angeles, CA, USA
- Department of Radiation Oncology, University of California, Los Angeles, CA, USA
| | - Peng Hu
- Department of Radiological Sciences, David Geffen School of Medicine, University of California, Los Angeles, CA, USA
- Biomedical Physics Inter-Departmental Graduate Program, University of California, Los Angeles, CA, USA
| |
Collapse
|