MR fingerprinting Deep RecOnstruction NEtwork (DRONE)
arXiv:1710.05267 · doi:10.1002/mrm.27198
Abstract
PURPOSE: Demonstrate a novel fast method for reconstruction of multi-dimensional MR Fingerprinting (MRF) data using Deep Learning methods. METHODS: A neural network (NN) is defined using the TensorFlow framework and trained on simulated MRF data computed using the Bloch equations. The accuracy of the NN reconstruction of noisy data is compared to conventional MRF template matching as a function of training data size, and quantified in a both simulated numerical brain phantom data and acquired data from the ISMRM/NIST phantom. The utility of the method is demonstrated in a healthy subject in vivo at 1.5 T. RESULTS: Network training required 10 minutes and once trained, data reconstruction required approximately 10 ms. Reconstruction of simulated brain data using the NN resulted in a root-mean-square error (RMSE) of 3.5 ms for T1 and 7.8 ms for T2. The RMSE for the NN trained on sparse dictionaries was approximately 6 fold lower for T1 and 2 fold lower for T2 than conventional MRF dot-product dictionary matching on the same dictionaries. Phantom measurements yielded good agreement (R2=0.99) between the T1 and T2 estimated by the NN and reference values from the ISMRM/NIST phantom. CONCLUSION: Reconstruction of MRF data with a NN is accurate, 300 fold faster and more robust to noise and undersampling than conventional MRF dictionary matching.
arXiv comment21 pages, 7 figures
References in corpus (3)
Cited by in corpus (47)
- An overview of deep learning in medical imaging focusing on MRI
- Rapid and Quantitative Chemical Exchange Saturation Transfer (CEST) Imaging with Magnetic Resonance Fingerprinting (MRF)
- Magnetization Transfer in Magnetic Resonance Fingerprinting
- CEST MR fingerprinting (CEST-MRF) for Brain Tumor Quantification Using EPI Readout and Deep Learning Reconstruction
- An End-to-End AI-Based Framework for Automated Discovery of CEST/MT MR Fingerprinting Acquisition Protocols and Quantitative Deep Reconstruction (AutoCEST)
- Optimized multi-axis spiral projection MR fingerprinting with subspace reconstruction for rapid whole-brain high-isotropic-resolution quantitative imaging
- Separation of water and fat signal in whole-body gradient echo scans using convolutional neural networks
- Deep MRI Reconstruction: Unrolled Optimization Algorithms Meet Neural Networks
- HYDRA: Hybrid Deep Magnetic Resonance Fingerprinting
- Magnetic Resonance Fingerprinting Reconstruction via Spatiotemporal Convolutional Neural Networks
- Mapping tissue microstructure of brain white matter in vivo in health and disease using diffusion MRI
- Cramér-Rao bound-informed training of neural networks for quantitative MRI
- Spatially Regularized Parametric Map Reconstruction for Fast Magnetic Resonance Fingerprinting
- Uncertainty Quantification in Deep Learning for Safer Neuroimage Enhancement
- Accelerated and Quantitative 3D Semisolid MT/CEST Imaging using a Generative Adversarial Network (GAN-CEST)
- -net: Systematic Evaluation of Iterative Deep Neural Networks for Fast Parallel MR Image Reconstruction
- Unconstrained quantitative magnetization transfer imaging: disentangling T1 of the free and semi-solid spin pools
- High-resolution myelin-water fraction and quantitative relaxation mapping using 3D ViSTa-MR fingerprinting
- Efficiency analysis for quantitative MRI of T1 and T2 relaxometry methods
- PINQI: An End-to-End Physics-Informed Approach to Learned Quantitative MRI Reconstruction
- Rapid quantitative magnetization transfer imaging: utilizing the hybrid state and the generalized Bloch model
- Deep Reinforcement Learning Designed Shinnar-Le Roux RF Pulse using Root-Flipping: DeepRF_SLR
- Amide Proton Transfer (APT) imaging in tumor with a machine learning approach using partially synthetic data
- Multi-Parameter Molecular MRI Quantification using Physics-Informed Self-Supervised Learning
- Bias-Reduced Neural Networks for Parameter Estimation in Quantitative MRI
- High-efficient Bloch simulation of magnetic resonance imaging sequences based on deep learning
- Greedy Approximate Projection for Magnetic Resonance Fingerprinting with Partial Volumes
- Latent Signal Models: Learning Compact Representations of Signal Evolution for Improved Time-Resolved, Multi-contrast MRI
- Only-Train-Once MR Fingerprinting for Magnetization Transfer Contrast Quantification
- Cramér-Rao Bound Optimized Subspace Reconstruction in Quantitative MRI
- Simultaneous Segmentation and Relaxometry for MRI through Multitask Learning
- Pattern-matching Unit for Medical Applications
- Quantitative multi-metabolite imaging of Parkinson's disease using AI boosted molecular MRI
- Compressive MRI quantification using convex spatiotemporal priors and deep auto-encoders
- A Fully Convolutional Network for MR Fingerprinting
- StoDIP: Efficient 3D MRF image reconstruction with deep image priors and stochastic iterations
- Magnetic Resonance Parameter Mapping using Self-supervised Deep Learning with Model Reinforcement
- Real-Time Mapping of Tissue Properties for Magnetic Resonance Fingerprinting
- Compressive MR Fingerprinting reconstruction with Neural Proximal Gradient iterations
- Learning Bloch Simulations for MR Fingerprinting by Invertible Neural Networks
- A Fast MR Fingerprinting Simulator for Direct Error Estimation and Sequence Optimization
- Rapid 3D Multiparametric Mapping of Brain Metastases with Deep Learning-Based Phase-Sensitive MR Fingerprinting
- Unsupervised learning of MRI tissue properties using MRI physics models
- Channel Attention Networks for Robust MR Fingerprinting Matching
- : Accelerated Modified Look-Locker Inversion Recovery Myocardial T1 Mapping via Neural Networks
- Fast Whole-Brain MR Multi-Parametric Mapping with Scan-Specific Self-Supervised Networks
- Decoding the human brain tissue response to radiofrequency excitation using a biophysical-model-free deep MRI on a chip framework