One for multiple: Physics-informed synthetic data boosts generalizable deep learning for fast MRI reconstruction.
Authors
Affiliations (22)
Affiliations (22)
- Department of Electronic Science, Xiamen University-Neusoft Medical Magnetic Resonance Imaging Joint Research and Development Center, Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance, National Institute for Data Science in Health and Medicine, Xiamen University, China; Department of Bioengineering and Imperial-X, Imperial College London, United Kingdom.
- Department of Electronic Science, Xiamen University-Neusoft Medical Magnetic Resonance Imaging Joint Research and Development Center, Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance, National Institute for Data Science in Health and Medicine, Xiamen University, China.
- Shanghai Pudong Hospital and Human Phenome Institute, Fudan University, China; International Human Phenome Institute (Shanghai), China.
- Philips Healthcare, China.
- Siemens Healthineers Ltd., China.
- United Imaging Research Institute of Intelligent Imaging, China.
- Department of Nuclear Medicine, Nanjing First Hospital, China.
- Shandong Aoxin Medical Technology Company, China.
- Department of Radiology, The First Affiliated Hospital of Xiamen University, China.
- Department of Radiology, Zhongshan Hospital Affiliated to Xiamen University, China.
- Department of Neurosurgery, Zhongshan Hospital, Fudan University (Xiamen Branch), China.
- Department of Cardiology, Shanghai Institute of Cardiovascular Diseases, Zhongshan Hospital, Fudan University, China.
- Department of Radiology, Zhongshan Hospital, Fudan University, China.
- Department of Cardiovascular Medicine, Heart Failure Center, Ruijin Hospital Lu Wan Branch, Shanghai Jiaotong University School of Medicine, China.
- Department of Radiology, Ruijin Hospital, Shanghai Jiaotong University School of Medicine, China.
- Medical Imaging Department, The First Affiliated Hospital of Kunming Medical University, China.
- Department of Radiology, Zhongshan Hospital, Fudan University (Xiamen Branch), Fujian Province Key Clinical Specialty Construction Project (Medical Imaging Department), Xiamen Key Laboratory of Clinical Transformation of Imaging Big Data and Artificial Intelligence, China.
- Department of Applied Marine Physics and Engineering, Xiamen University, China.
- Department of Microelectronics and Integrated Circuit, Xiamen University, China.
- School of Computer and Information Engineering, Xiamen University of Technology, China.
- Department of Bioengineering and Imperial-X, Imperial College London, United Kingdom; National Heart and Lung Institute, Imperial College London, United Kingdom; Cardiovascular Research Centre, Royal Brompton Hospital, United Kingdom; School of Biomedical Engineering & Imaging Sciences, King's College London, United Kingdom.
- Department of Electronic Science, Xiamen University-Neusoft Medical Magnetic Resonance Imaging Joint Research and Development Center, Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance, National Institute for Data Science in Health and Medicine, Xiamen University, China. Electronic address: [email protected].
Abstract
Magnetic resonance imaging (MRI) is a widely used radiological modality renowned for its radiation-free, comprehensive insights into the human body, facilitating medical diagnoses. However, the drawback of prolonged scan times hinders its accessibility. The k-space undersampling offers a solution, yet the resultant artifacts necessitate meticulous removal during image reconstruction. Although deep learning (DL) has proven effective for fast MRI image reconstruction, its broader applicability across various imaging scenarios has been constrained. Challenges include the high cost and privacy restrictions associated with acquiring large-scale, diverse training data, coupled with the inherent difficulty of addressing mismatches between training and target data in existing DL methodologies. Here, we present a novel Physics-Informed Synthetic data learning Framework for fast MRI, called PISF. PISF marks a breakthrough by enabling generalizable DL for multi-scenario MRI reconstruction through a single trained model. Our approach separates the reconstruction of a 2D image into many 1D basic problems, commencing with 1D data synthesis to facilitate generalization. We demonstrate that training DL models on synthetic data, coupled with enhanced learning techniques, yields in vivo MRI reconstructions comparable to or surpassing those of models trained on matched realistic datasets, reducing the reliance on real-world MRI data by up to 96 %. With a single trained model, our PISF supports the high-quality reconstruction under 4 sampling patterns, 5 anatomies, 6 contrasts, 5 vendors, and 7 centers, exhibiting remarkable generalizability. Its adaptability to 2 neuro and 2 cardiovascular patient populations has been validated through evaluations by 10 experienced medical professionals. In summary, PISF presents a feasible and cost-effective way to significantly boost the widespread adoption of DL in various fast MRI applications.