RECORD
HYDRA: Hybrid Deep Magnetic Resonance Fingerprinting
Image and Video Processing · Submitted 7 Feb 2019
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Conclusions: Our approach demonstrates advantages in terms of inference speed, accuracy and storage requirements over competing MRF methods
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Purpose: Magnetic resonance fingerprinting (MRF) methods typically rely on dictio-nary matching to map the temporal MRF signals to quantitative tissue parameters. Such approaches suffer from inherent discretization errors, as well as high computational complexity as the dictionary size grows. To alleviate these issues, we propose a HYbrid Deep magnetic ResonAnce fingerprinting approach, referred to as HYDRA. Methods: HYDRA involves two stages: a model-based signature restoration phase and a learning-based parameter restoration phase. Signal restoration is implemented using low-rank based de-aliasing techniques while parameter restoration is performed using a deep nonlocal residual convolutional neural network. The designed network is trained on synthesized MRF data simulated with the Bloch equations and fast imaging with steady state precession (FISP) sequences. In test mode, it takes a temporal MRF signal as input and produces the corresponding tissue parameters. Results: We validated our approach on both synthetic data and anatomical data generated from a healthy subject. The results demonstrate that, in contrast to conventional dictionary-matching based MRF techniques, our approach significantly improves inference speed by eliminating the time-consuming dictionary matching operation, and alleviates discretization errors by outputting continuous-valued parameters. We further avoid the need to store a large dictionary, thus reducing memory requirements. Conclusions: Our approach demonstrates advantages in terms of inference speed, accuracy and storage requirements over competing MRF methods
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Purpose: Magnetic resonance fingerprinting (MRF) methods typically rely on dictio-nary matching to map the temporal MRF signals to quantitative tissue parameters. | background 1.00 | 0.04 | 0.01 | asserted 0.98 |
| s1 | Such approaches suffer from inherent discretization errors, as well as high computational complexity as the dictionary size grows. | background 0.85 | 0.06 | 0.02 | asserted 1.00 |
| s2 | To alleviate these issues, we propose a HYbrid Deep magnetic ResonAnce fingerprinting approach, referred to as HYDRA. | contribution 1.00 | 0.72 | 0.04 | asserted 0.91 |
| s3 | Methods: HYDRA involves two stages: a model-based signature restoration phase and a learning-based parameter restoration phase. | method 0.97 | 0.81 | 0.02 | asserted 1.00 |
| s4 | Signal restoration is implemented using low-rank based de-aliasing techniques while parameter restoration is performed using a deep nonlocal residual convolutional neural network. | method 1.00 | 0.85 | 0.02 | asserted 1.00 |
| s5 | The designed network is trained on synthesized MRF data simulated with the Bloch equations and fast imaging with steady state precession (FISP) sequences. | method 1.00 | 0.90 | 0.02 | asserted 1.00 |
| s6 | In test mode, it takes a temporal MRF signal as input and produces the corresponding tissue parameters. | method 1.00 | 0.54 | 0.02 | asserted 1.00 |
| s7 | Results: We validated our approach on both synthetic data and anatomical data generated from a healthy subject. | method 0.77 | 0.96 | 0.04 | asserted 0.93 |
| s8 | The results demonstrate that, in contrast to conventional dictionary-matching based MRF techniques, our approach significantly improves inference speed by eliminating the time-consuming dictionary matching operation, and alleviates discretization errors by outputting continuous-valued parameters. | result 0.87 | 0.95 | 0.35 | asserted 1.00 |
| s9 | We further avoid the need to store a large dictionary, thus reducing memory requirements. | result 0.85 | 0.79 | 0.07 | asserted 0.99 |
| s10 | Conclusions: Our approach demonstrates advantages in terms of inference speed, accuracy and storage requirements over competing MRF methods | interpretation 0.83 | 0.86 | 0.96 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v2
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Purpose: Magnetic resonance fingerprinting (MRF) methods typically rely on dictio-nary matching to map the temporal MRF signals to quantitative tissue parameters. Such approaches suffer from inherent discretization errors, as well as high computational complexity as the dictionary size grows. To alleviate these issues, we propose a HYbrid Deep magnetic ResonAnce fingerprinting approach, referred to as HYDRA. Methods: HYDRA involves two stages: a model-based signature restoration phase and a learning-based parameter restoration phase. Signal restoration is implemented using low-rank based de-aliasing techniques while parameter restoration is performed using a deep nonlocal residual convolutional neural network. The designed network is trained on synthesized MRF data simulated with the Bloch equations and fast imaging with steady state precession (FISP) sequences. In test mode, it takes a temporal MRF signal as input and produces the corresponding tissue parameters. Results: We validated our approach on both synthetic data and anatomical data generated from a healthy subject. The results demonstrate that, in contrast to conventional dictionary-matching based MRF techniques, our approach significantly improves inference speed by eliminating the time-consuming dictionary matching operation, and alleviates discretization errors by outputting continuous-valued parameters. We further avoid the need to store a large dictionary, thus reducing memory requirements. Conclusions: Our approach demonstrates advantages in terms of inference speed, accuracy and storage requirements over competing MRF methods
Human review
How the literature uses it
2 arXiv papers cite this in 3 sentences
Papers citing it · 2 sentences without a confident label
Cites it as background 1 paper
-
A more complex architecture was proposed by [ref] using residual learning combined with attention mechanisms.
Spatially Regularized Parametric Map Reconstruction for Fast Magnetic Resonance Fingerprinting · Introduction · 0.92
What it cites · 1 sentence without a confident label
Uses the method or tool of 1 paper
-
The resulting RMSE loss is then backpropagated from the output layer to the first layer to update the weights and bias by using Adam [ref] as the optimization algorithm.
Adam: A Method for Stochastic Optimization · Learning-based parameter restoration · 1.00
Cites as background 1 paper
-
By introducing convolution, local receptive field and weight sharing design, a CNN is capable of taking advantage of local spatial coherence and translation invariance characteristics in the input signal, thus become especially well suited to extract relevant information at a low computational cost [ref] .
Convolutional Sequence to Sequence Learning · Learning-based parameter restoration · 0.80
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.