1
|
Wang S, Wu R, Jia S, Diakite A, Li C, Liu Q, Zheng H, Ying L. Knowledge-driven deep learning for fast MR imaging: Undersampled MR image reconstruction from supervised to un-supervised learning. Magn Reson Med 2024; 92:496-518. [PMID: 38624162 DOI: 10.1002/mrm.30105] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/03/2023] [Revised: 03/19/2024] [Accepted: 03/20/2024] [Indexed: 04/17/2024]
Abstract
Deep learning (DL) has emerged as a leading approach in accelerating MRI. It employs deep neural networks to extract knowledge from available datasets and then applies the trained networks to reconstruct accurate images from limited measurements. Unlike natural image restoration problems, MRI involves physics-based imaging processes, unique data properties, and diverse imaging tasks. This domain knowledge needs to be integrated with data-driven approaches. Our review will introduce the significant challenges faced by such knowledge-driven DL approaches in the context of fast MRI along with several notable solutions, which include learning neural networks and addressing different imaging application scenarios. The traits and trends of these techniques have also been given which have shifted from supervised learning to semi-supervised learning, and finally, to unsupervised learning methods. In addition, MR vendors' choices of DL reconstruction have been provided along with some discussions on open questions and future directions, which are critical for the reliable imaging systems.
Collapse
Affiliation(s)
- Shanshan Wang
- Paul C Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
| | - Ruoyou Wu
- Paul C Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
| | - Sen Jia
- Paul C Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
| | - Alou Diakite
- Paul C Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
- University of Chinese Academy of Sciences, Beijing, China
| | - Cheng Li
- Paul C Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
| | - Qiegen Liu
- Department of Electronic Information Engineering, Nanchang University, Nanchang, China
| | - Hairong Zheng
- Paul C Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
| | - Leslie Ying
- Department of Biomedical Engineering and Department of Electrical Engineering, The State University of New York, Buffalo, New York, USA
| |
Collapse
|
2
|
Chen S, Duan J, Ren X, Wang J, Liu Y. DFUSNN: zero-shot dual-domain fusion unsupervised neural network for parallel MRI reconstruction. Phys Med Biol 2024; 69:105028. [PMID: 38604186 DOI: 10.1088/1361-6560/ad3dbc] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/23/2023] [Accepted: 04/11/2024] [Indexed: 04/13/2024]
Abstract
Objective. Recently, deep learning models have been used to reconstruct parallel magnetic resonance (MR) images from undersampled k-space data. However, most existing approaches depend on large databases of fully sampled MR data for training, which can be challenging or sometimes infeasible to acquire in certain scenarios. The goal is to develop an effective alternative for improved reconstruction quality that does not rely on external training datasets.Approach. We introduce a novel zero-shot dual-domain fusion unsupervised neural network (DFUSNN) for parallel MR imaging reconstruction without any external training datasets. We employ the Noise2Noise (N2N) network for the reconstruction in the k-space domain, integrate phase and coil sensitivity smoothness priors into the k-space N2N network, and use an early stopping criterion to prevent overfitting. Additionally, we propose a dual-domain fusion method based on Bayesian optimization to enhance reconstruction quality efficiently.Results. Simulation experiments conducted on three datasets with different undersampling patterns showed that the DFUSNN outperforms all other competing unsupervised methods and the one-shot Hankel-k-space generative model (HKGM). The DFUSNN also achieves comparable results to the supervised Deep-SLR method.Significance. The novel DFUSNN model offers a viable solution for reconstructing high-quality MR images without the need for external training datasets, thereby overcoming a major hurdle in scenarios where acquiring fully sampled MR data is difficult.
Collapse
Affiliation(s)
- Shengyi Chen
- Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, People's Republic of China
| | - Jizhong Duan
- Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, People's Republic of China
| | - Xinmin Ren
- Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, People's Republic of China
| | - Junfeng Wang
- Department of Hepatobiliary Surgery, First People's Hospital of Yunnan Province, Kunming 650030, People's Republic of China
| | - Yu Liu
- School of Microelectronics, Tianjin University, Tianjin 300072, People's Republic of China
| |
Collapse
|
3
|
Liu C, Cui ZX, Jia S, Cheng J, Liu Y, Lin L, Hu Z, Xie T, Zhou Y, Zhu Y, Liang D, Zeng H, Wang H. DPP: deep phase prior for parallel imaging with wave encoding. Phys Med Biol 2024; 69:105013. [PMID: 38608645 DOI: 10.1088/1361-6560/ad3e5d] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/20/2023] [Accepted: 04/12/2024] [Indexed: 04/14/2024]
Abstract
Objective.In Magnetic Resonance (MR) parallel imaging with virtual channel-expanded Wave encoding, limitations are imposed on the ability to comprehensively and accurately characterize the background phase. These limitations are primarily attributed to the calibration process relying solely on center low-frequency Auto-Calibration Signals (ACS) data for calibration.Approach.To tackle the challenge of accurately estimating the background phase in wave encoding, a novel deep neural network model guided by deep phase priors is proposed with integrated virtual conjugate coil (VCC) extension. Concretely, within the proposed framework, the background phase is implicitly characterized by employing a carefully designed decoder convolutional neural network, leveraging the inherent characteristics of phase smoothness and compact support in the transformed domain. Furthermore, the proposed model with wave encoding benefits from additional priors, which incorporate transmission sparsity of the latent image and coil sensitivity smoothness.Main results.Ablation experiments were conducted to ascertain the proposed method's capability to implicitly represent CSM and the background phase. Subsequently, the superiority of the proposed method is demonstrated through confidence comparisons with competing methods, employing 4-fold and 5-fold acceleration experiments. In achieving 4-fold and 5-fold acceleration, the optimal quantitative metrics (PSNR/SSIM/NMSE) are 44.1359 dB/0.9863/0.0008 (4-fold) and 41.2074/0.9846/0.0017 (5-fold), respectively. Furthermore, the generalizability of the proposed method is further validated by conducting acceleration experiments with T1, T2, T2*, and various undersampling patterns. In addition, the DPP delivered much better performance than the conventional methods by exploring accelerated phase-sensitive SWI imaging. In SWI accelerated imaging, it also surpasses the optimal competing method in terms of (PSNR/SSIM/NMSE) with 0.096%/0.009%/0.0017%.Significance.The proposed method enables precise characterization of the background phase in the integrated VCC and wave encoding framework, supported via theoretical analysis and empirical findings. Our code is available at:https://github.com/sober235/DPP.
Collapse
Affiliation(s)
- Congcong Liu
- Paul C Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, People's Republic of China
- Shenzhen College of Advanced Technology, University of Chinese Academy of Sciences, Shenzhen, Guangdong, People's Republic of China
| | - Zhuo-Xu Cui
- Research Center for Medical AI, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, People's Republic of China
| | - Sen Jia
- Paul C Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, People's Republic of China
| | - Jing Cheng
- Paul C Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, People's Republic of China
| | - Yuanyuan Liu
- Paul C Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, People's Republic of China
| | - Ling Lin
- Paul C Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, People's Republic of China
- Shenzhen College of Advanced Technology, University of Chinese Academy of Sciences, Shenzhen, Guangdong, People's Republic of China
| | - Zhanqi Hu
- Department of Neurology, Shenzhen Children's Hospital, Shenzhen, Guangdong, People's Republic of China
| | - Taofeng Xie
- Inner Mongolia University, Hohhot, Inner Mongolia, People's Republic of China
- Inner Mongolia Medical University, Hohhot, Inner Mongolia, People's Republic of China
| | - Yihang Zhou
- Paul C Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, People's Republic of China
- Shenzhen College of Advanced Technology, University of Chinese Academy of Sciences, Shenzhen, Guangdong, People's Republic of China
- Key Laboratory of Biomedical Imaging Science and System, Chinese Academy of Sciences, People's Republic of China
- Key Laboratory for Magnetic Resonance and Multimodality Imaging of Guangdong Province, Shenzhen, People's Republic of China
| | - Yanjie Zhu
- Paul C Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, People's Republic of China
- Shenzhen College of Advanced Technology, University of Chinese Academy of Sciences, Shenzhen, Guangdong, People's Republic of China
- Key Laboratory of Biomedical Imaging Science and System, Chinese Academy of Sciences, People's Republic of China
- Key Laboratory for Magnetic Resonance and Multimodality Imaging of Guangdong Province, Shenzhen, People's Republic of China
| | - Dong Liang
- Paul C Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, People's Republic of China
- Shenzhen College of Advanced Technology, University of Chinese Academy of Sciences, Shenzhen, Guangdong, People's Republic of China
- Research Center for Medical AI, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, People's Republic of China
- Key Laboratory of Biomedical Imaging Science and System, Chinese Academy of Sciences, People's Republic of China
- Key Laboratory for Magnetic Resonance and Multimodality Imaging of Guangdong Province, Shenzhen, People's Republic of China
| | - Hongwu Zeng
- Department of Radiology, Shenzhen Children's Hospital, Shenzhen, Guangdong, People's Republic of China
| | - Haifeng Wang
- Paul C Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, People's Republic of China
- Shenzhen College of Advanced Technology, University of Chinese Academy of Sciences, Shenzhen, Guangdong, People's Republic of China
- Key Laboratory of Biomedical Imaging Science and System, Chinese Academy of Sciences, People's Republic of China
- Key Laboratory for Magnetic Resonance and Multimodality Imaging of Guangdong Province, Shenzhen, People's Republic of China
| |
Collapse
|
4
|
Zhang H, Xiang Y, Liu B, Li G, Dun C, Huang H, Zou Q, Xiong L, Wu X. Fe doping mechanism of Na 0.44MnO 2 tunnel phase cathode electrode in sodium-ion batteries. J Colloid Interface Sci 2024; 661:389-400. [PMID: 38306748 DOI: 10.1016/j.jcis.2024.01.165] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/11/2023] [Revised: 01/21/2024] [Accepted: 01/24/2024] [Indexed: 02/04/2024]
Abstract
Due to its stability and low cost, the tunnel-style sodium-manganese oxide (Na0.44MnO2) material is deemed a popular cathode choice for sodium-ion rechargeable batteries. However, the Jahn-Teller effect caused by Mn3+ in the material results in poor capacity and cycling stability. The purpose of this experimental study is to partially replace Mn3+ with Fe3+, in order to reduce the Jahn-Teller effect of the material during charging and discharging process. The results of Raman spectroscopy and X-ray photoelectron spectroscopy confirmed that the content of Mn3+ decreased after Fe3+ doping. Electrochemical studies show that the Na0.44Mn0.994Fe0.006O2 cathode has better rate performance (exhibits a reversible capacity of 87.9 mAh/g at 2 C) and cycle stability in sodium-ion batteries. The diffusion coefficient of sodium ions increases by Fe3+ doping. The excellent rate performance and capacity improvement are verified by density functional theory (DFT) calculation. After doping, the band gap decreases significantly, and the results show that the state density of O 2p increases near the Fermi level, which promotes the oxidation-reduction of oxygen. This work provides a straightforward approach to enhance the performance of Na0.44MnO2 nanorods, and this performance improvement has guiding significance for the design of other materials in the energy storage domain.
Collapse
Affiliation(s)
- Huiyu Zhang
- College of Physics and Electromechanical Engineering, Jishou University, Jishou 416000, Hunan, China
| | - Yanhong Xiang
- College of Physics and Electromechanical Engineering, Jishou University, Jishou 416000, Hunan, China.
| | - Baocheng Liu
- College of Physics and Electromechanical Engineering, Jishou University, Jishou 416000, Hunan, China
| | - Guang Li
- College of Physics and Electromechanical Engineering, Jishou University, Jishou 416000, Hunan, China
| | - Chen Dun
- College of Physics and Electromechanical Engineering, Jishou University, Jishou 416000, Hunan, China
| | - Haoyu Huang
- College of Physics and Electromechanical Engineering, Jishou University, Jishou 416000, Hunan, China
| | - Qiuling Zou
- College of Physics and Electromechanical Engineering, Jishou University, Jishou 416000, Hunan, China
| | - Lizhi Xiong
- School of Pharmaceutical Sciences, Jishou University, Jishou 416000, Hunan, China
| | - Xianwen Wu
- College of Chemistry and Chemical Engineering, Jishou University, Jishou 416000, Hunan, China
| |
Collapse
|