Deep learning–based MR fingerprinting ASL ReconStruction (DeepMARS)

Zhang, Qiang; Pan, Su‐Shu; Chen, Zhensen; Liao, Ying; Chen, Shuo; Guo, Rui; Qi, Haikun; Li, Xuesong; Zhang, Xue; Hu, Zhangxuan; Lu, Hanzhang; Chen, Huijun

doi:10.1002/mrm.28166

Cited by 25 publications

(40 citation statements)

References 32 publications

(50 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Two previous reports have applied ANN to the reconstruction of MRF-ASL parametric maps. 4,6 The method proposed in present study is different from previous studies in the following areas. The training data of previous studies were generated by numerical simulations with additional Gaussian noise, whereas the approach undertaken in the present work was to collect a set of high fidelity in vivo data for training purposes.…”

Section: Comparison With Literaturementioning

confidence: 72%

“…Finally, in order to compare ANN trained with high‐SNR experimental data with that trained with simulation data, we conduct an additional study in which the ANN was trained with a set of simulation data generated by perfusion kinetic model. Random Gaussian noise with four separate noise levels (0%, 0.1%, 0.5%, and 1% of M 0 , respectively) was added to the simulation data, following previous work by Zhang et al 6 The testing (experimental) data were then analyzed with these ANNs. Results from the simulation‐trained and experiment‐trained ANNs were compared in terms of their accuracy and precision.…”

Section: Methodsmentioning

confidence: 99%

“…Cohen et al proposed a fully connected ANN for T 1 and T 2 estimation and demonstrated that it was up to 5000‐fold faster compared with DM 5 . Lahiri et al 4 and Zhang et al 6 applied a similar ANN architecture to MRF‐ASL data for the estimation of hemodynamic parameters. Both studies used simulated data for the training of ANN.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multi‐band MR fingerprinting (MRF) ASL imaging using artificial‐neural‐network trained with high‐fidelity experimental data

Fan¹,

Pan

Huang³

et al. 2020

Magnetic Resonance in Med

Self Cite

View full text Add to dashboard Cite

We aim to leverage the power of deep-learning with high-fidelity training data to improve the reliability and processing speed of hemodynamic mapping with MR fingerprinting (MRF) arterial spin labeling (ASL). Methods: A total of 15 healthy subjects were studied on a 3T MRI. Each subject underwent 10 runs of a multi-band multi-slice MRF-ASL sequence for a total scan time of approximately 40 min. MRF-ASL images were averaged across runs to yield a set of high-fidelity data. Training of a fully connected artificial neural network (ANN) was then performed using these data. The results from ANN were compared to those of dictionary matching (DM), ANN trained with single-run experimental data and with simulation data. Initial clinical performance of the technique was also demonstrated in a Moyamoya patient. Results: The use of ANN reduced the processing time of MRF-ASL data to 3.6 s, compared to DM of 3 h 12 min. Parametric values obtained with ANN and DM were strongly correlated (R 2 between 0.84 and 0.96). Results obtained from high-fidelity ANN were substantially more reliable compared to those from DM or single-run ANN. Voxel-wise coefficient of variation (CoV) of high-fidelity ANN, DM, and single-run ANN was 0.15 ± 0.08, 0.41 ± 0.20, 0.30 ± 0.16, respectively, for cerebral blood flow and 0.11 ± 0.06, 0.20 ± 0.19, 0.15 ± 0.10, respectively, for bolus arrival time. In vivo data trained ANN also outperformed ANN trained with simulation data. The superior performance afforded by ANN allowed more conspicuous depiction of hemodynamic abnormalities in Moyamoya patient. Conclusion: Deep-learning-based parametric reconstruction improves the reliability of MRF-ASL hemodynamic maps and reduces processing time. K E Y W O R D S arterial spin labeling, artificial neural network, bolus arrival time, cerebral blood flow, MR fingerprinting (MRF), perfusion

show abstract

Section: Comparison With Literaturementioning

confidence: 72%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Multi‐band MR fingerprinting (MRF) ASL imaging using artificial‐neural‐network trained with high‐fidelity experimental data

Fan¹,

Pan

Huang³

et al. 2020

Magnetic Resonance in Med

Self Cite

View full text Add to dashboard Cite

show abstract

“…In our method, due to the absence of significant artifacts, there is a strong similarity between Bloch simulations and the acquired data, as was also the case in EPI-based arterial-spin labeling MRF (Zhang et al, 2020). As such, we found a dictionary generated using Bloch simulations with just added Gusaaian noise sufficient for neural-network training, implying that we can generate potentially unlimited training data from a wide parameter space.…”

Section: Parameter Estimate By Deep Learningmentioning

confidence: 69%

Streamlined Magnetic Resonance Fingerprinting: Fast Whole-brain Coverage with Deep-learning Based Parameter Estimation

Khajehim

Christen

Tam

et al. 2020

Preprint

View full text Add to dashboard Cite

Magnetic resonance fingerprinting (MRF) is a novel quantitative MRI (qMRI) framework that provides simultaneous estimates of multiple relaxation parameters as well as metrics of field inhomogeneity in a single acquisition. However, current bottlenecks exist in the forms of (1) scan time; (2) need for custom image reconstruction; (3) large dictionary sizes; (4) long dictionary-matching time. The aim of this study is to introduce a novel streamlined magnetic-resonance fingerprinting (sMRF) framework that is based on a single-shot echo-planar imaging (EPI) sequence to simultaneously estimate tissue T1, T2, and T2* with integrated B1+ correction. Encouraged by recent work on EPI-based MRF, we developed a method that combines spin-echo EPI with gradient-echo EPI to achieve T2 in addition to T1 and T2* quantification. To this design, we add simultaneous multi-slice (SMS) acceleration to enable full-brain coverage in a few minutes. Moreover, in the parameter-estimation step, we use deep learning to train a deep neural network (DNN) to accelerate the estimation process by orders of magnitude. Notably, due to the high image quality of the EPI scans, the training process can rely simply on Bloch-simulated data. The DNN also removes the need for storing large dictionaries. Phantom scans along with in-vivo multi-slice scans from seven healthy volunteers were acquired with resolutions of 1.1×1.1×3 mm3 and 1.7×1.7×3 mm3, and the results were validated against ground truth measurements. Excellent correspondence was found between our T1, T2, and T2* estimates and results obtained from standard approaches. In the phantom scan, a strong linear relationship (R=1-1.04, R2>0.96) was found for all parameter estimates, with a particularly high agreement for T2 estimation (R2>0.99). Similar findings are reported for the in-vivo human data for all of our parameter estimates. Incorporation of DNN results in a reduction of parameter estimation time on the order of 1000 x and a reduction in storage requirements on the order of 2500 x while achieving highly similar results as conventional dictionary matching (%differences of 7.4±0.4%, 3.6±0.3% and 6.0±0.4% error in T1, T2, and T2* estimation). Thus, sMRF has the potential to be the method of choice for future MRF studies by providing ease of implementation, fast whole-brain coverage, and ultra-fast T1/T2/T2* estimation.

show abstract

“…Recent progress in MRF‐ASL might also benefit from this work, particularly (and interestingly) those using deep learning approaches. The proposed numerical approximation with matrix formalism can potentially be combined with deep learning to further improve quantification of flow 49‐51 …”

Section: Discussionmentioning

confidence: 99%

Numerical approximation to the general kinetic model for ASL quantification

Lee

Javed

Jao

et al. 2020

Magnetic Resonance in Med

View full text Add to dashboard Cite

Purpose To develop a numerical approximation to the general kinetic model for arterial spin labeling (ASL) quantification that will enable greater flexibility in ASL acquisition methods. Theory The Bloch‐McConnell equations are extended to include the effects of single‐compartment inflow and outflow on both the transverse and longitudinal magnetization. These can be solved using an extension of Jaynes’ matrix formalism with piecewise constant approximation of incoming labeled arterial flow and a clearance operator for outgoing venous flow. Methods The proposed numerical approximation is compared with the general kinetic model using simulations of pulsed labeling and pseudo‐continuous labeling and a broad range of transit time and bolus duration for tissue blood flow of 0.6 mL/g/min. Accuracy of the approximation is studied as a function of the timestep using Monte‐Carlo simulations. Three additional scenarios are demonstrated: (1) steady‐pulsed ASL, (2) MR fingerprinting ASL, and (3) balanced SSFP and spoiled gradient‐echo sequences. Results The proposed approximation was found to be arbitrarily accurate for pulsed labeling and pseudo‐continuous labeling. The pulsed labeling/pseudo‐continuous labeling approximation error compared with the general kinetic model was less than 0.002% (<0.002%) and less than 0.05% (<0.05%) for timesteps of 3 ms and 35 ms, respectively. The proposed approximation matched well with customized signal expressions of steady‐pulsed ASL and MR fingerprinting ASL. The simulations of simultaneous modeling of flow, T2, and magnetization transfer showed an increase in steady‐state balanced SSFP and spoiled gradient signals. Conclusion We demonstrate a numerical approximation of the “Bloch–McConnell flow” equations that enables arbitrarily accurate modeling of pulsed ASL and pseudo‐continuous labeling signals comparable to the general kinetic model. This enables increased flexibility in the experiment design for quantitative ASL.

show abstract

Deep learning–based MR fingerprinting ASL ReconStruction (DeepMARS)

Cited by 25 publications

References 32 publications

Multi‐band MR fingerprinting (MRF) ASL imaging using artificial‐neural‐network trained with high‐fidelity experimental data

Multi‐band MR fingerprinting (MRF) ASL imaging using artificial‐neural‐network trained with high‐fidelity experimental data

Streamlined Magnetic Resonance Fingerprinting: Fast Whole-brain Coverage with Deep-learning Based Parameter Estimation

Numerical approximation to the general kinetic model for ASL quantification

Contact Info

Product

Resources

About