A model-based MR parameter mapping network robust to substantial variations in acquisition settings

Deep learning methods show great potential for the efficient and precise estimation of quantitative parameter maps from multiple magnetic resonance (MR) images. Current deep learning-based MR parameter mapping (MPM) methods are mostly trained and tested using data with specific acquisition settings. However, scan protocols usually vary with centers, scanners, and studies in practice. Thus, deep learning methods applicable to MPM with varying acquisition settings are highly required but still rarely investigated. In this work, we develop a model-based deep network termed MMPM-Net for robust MPM with varying acquisition settings. A deep learning-based denoiser is introduced to construct the regularization term in the nonlinear inversion problem of MPM. The alternating direction method of multipliers is used to solve the optimization problem and then unrolled to construct MMPM-Net. The variation in acquisition parameters can be addressed by the data fidelity component in MMPM-Net. Extensive experiments are performed on R2 mapping and R1 mapping datasets with substantial variations in acquisition settings, and the results demonstrate that the proposed MMPM-Net method outperforms other state-of-the-art MR parameter mapping methods both qualitatively and quantitatively.

Constrained alternating minimization for parameter mapping (CAMP)

OBJECTIVE

To improve image quality in highly accelerated parameter mapping by incorporating a linear constraint that relates consecutive images.

APPROACH

In multi-echo T1 or T2 mapping, scan time is often shortened by acquiring undersampled but complementary measures of k-space at each TE or TI. However, residual undersampling artifacts from the individual images can then degrade the quality of the final parameter maps. In this work, a new reconstruction method, dubbed Constrained Alternating Minimization for Parameter mapping (CAMP), is introduced. This method simultaneously extracts T2 or T1* maps in addition to an image for each TE or TI from accelerated datasets, leveraging the constraints of the decay to improve the reconstructed image quality. The model enforces exponential decay through a linear constraint, resulting in a biconvex objective function that lends itself to alternating minimization. The method was tested in four in vivo volunteer experiments and validated in phantom studies and healthy subjects, using T2 and T1 mapping, with accelerations of up to 12.

MAIN RESULTS

CAMP is demonstrated for accelerated radial and Cartesian acquisitions in T2 and T1 mapping. The method is even applied to generate an entire T2 weighted image series from a single TSE dataset, despite the blockwise k-space sampling at each echo time. Experimental undersampled phantom and in vivo results processed with CAMP exhibit reduced artifacts without introducing bias.

SIGNIFICANCE

For a wide array of applications, CAMP linearizes the model cost function without sacrificing model accuracy so that the well-conditioned and highly efficient reconstruction algorithm improves the image quality of accelerated parameter maps.

Endogenous assessment of myocardial injury with single-shot model-based non-rigid motion-corrected T1 rho mapping

BACKGROUND

Cardiovascular magnetic resonance T1ρ mapping may detect myocardial injuries without exogenous contrast agent. However, multiple co-registered acquisitions are required, and the lack of robust motion correction limits its clinical translation. We introduce a single breath-hold myocardial T1ρ mapping method that includes model-based non-rigid motion correction.

METHODS

A single-shot electrocardiogram (ECG)-triggered balanced steady state free precession (bSSFP) 2D adiabatic T1ρ mapping sequence that collects five T1ρ-weighted (T1ρw) images with different spin lock times within a single breath-hold is proposed. To address the problem of residual respiratory motion, a unified optimization framework consisting of a joint T1ρ fitting and model-based non-rigid motion correction algorithm, insensitive to contrast change, was implemented inline for fast (~ 30 s) and direct visualization of T1ρ maps. The proposed reconstruction was optimized on an ex vivo human heart placed on a motion-controlled platform. The technique was then tested in 8 healthy subjects and validated in 30 patients with suspected myocardial injury on a 1.5T CMR scanner. The Dice similarity coefficient (DSC) and maximum perpendicular distance (MPD) were used to quantify motion and evaluate motion correction. The quality of T1ρ maps was scored. In patients, T1ρ mapping was compared to cine imaging, T2 mapping and conventional post-contrast 2D late gadolinium enhancement (LGE). T1ρ values were assessed in remote and injured areas, using LGE as reference.

RESULTS

Despite breath holds, respiratory motion throughout T1ρw images was much larger in patients than in healthy subjects (5.1 ± 2.7 mm vs. 0.5 ± 0.4 mm, P < 0.01). In patients, the model-based non-rigid motion correction improved the alignment of T1ρw images, with higher DSC (87.7 ± 5.3% vs. 82.2 ± 7.5%, P < 0.01), and lower MPD (3.5 ± 1.9 mm vs. 5.1 ± 2.7 mm, P < 0.01). This resulted in significantly improved quality of the T1ρ maps (3.6 ± 0.6 vs. 2.1 ± 0.9, P < 0.01). Using this approach, T1ρ mapping could be used to identify LGE in patients with 93% sensitivity and 89% specificity. T1ρ values in injured (LGE positive) areas were significantly higher than in the remote myocardium (68.4 ± 7.9 ms vs. 48.8 ± 6.5 ms, P < 0.01).

CONCLUSIONS

The proposed motion-corrected T1ρ mapping framework enables a quantitative characterization of myocardial injuries with relatively low sensitivity to respiratory motion. This technique may be a robust and contrast-free adjunct to LGE for gaining new insight into myocardial structural disorders.

A deep learning approach for magnetic resonance fingerprinting: Scaling capabilities and good training practices investigated by simulations

MR fingerprinting (MRF) is an innovative approach to quantitative MRI. A typical disadvantage of dictionary-based MRF is the explosive growth of the dictionary as a function of the number of reconstructed parameters, an instance of the curse of dimensionality, which determines an explosion of resource requirements. In this work, we describe a deep learning approach for MRF parameter map reconstruction using a fully connected architecture. Employing simulations, we have investigated how the performance of the Neural Networks (NN) approach scales with the number of parameters to be retrieved, compared to the standard dictionary approach. We have also studied optimal training procedures by comparing different strategies for noise addition and parameter space sampling, to achieve better accuracy and robustness to noise. Four MRF sequences were considered: IR-FISP, bSSFP, IR-FISP-B₁, and IR-bSSFP-B₁. A comparison between NN and the dictionary approaches in reconstructing parameter maps as a function of the number of parameters to be retrieved was performed using a numerical brain phantom. Results demonstrated that training with random sampling and different levels of noise variance yielded the best performance. NN performance was at least as good as the dictionary-based approach in reconstructing parameter maps using Gaussian noise as a source of artifacts: the difference in performance increased with the number of estimated parameters because the dictionary method suffers from the coarse resolution of the parameter space sampling. The NN proved to be more efficient in memory usage and computational burden, and has great potential for solving large-scale MRF problems.

Deep model-based magnetic resonance parameter mapping network (DOPAMINE) for fast T1 mapping using variable flip angle method

Quantitative tissue characteristics, which provide valuable diagnostic information, can be represented by magnetic resonance (MR) parameter maps using magnetic resonance imaging (MRI); however, a long scan time is necessary to acquire them, which prevents the application of quantitative MR parameter mapping to real clinical protocols. For fast MR parameter mapping, we propose a deep model-based MR parameter mapping network called DOPAMINE that combines a deep learning network with a model-based method to reconstruct MR parameter maps from undersampled multi-channel k-space data. DOPAMINE consists of two networks: 1) an MR parameter mapping network that uses a deep convolutional neural network (CNN) that estimates initial parameter maps from undersampled k-space data (CNN-based mapping), and 2) a reconstruction network that removes aliasing artifacts in the parameter maps with a deep CNN (CNN-based reconstruction) and an interleaved data consistency layer by an embedded MR model-based optimization procedure. We demonstrated the performance of DOPAMINE in brain T₁ map reconstruction with a variable flip angle (VFA) model. To evaluate the performance of DOPAMINE, we compared it with conventional parallel imaging, low-rank based reconstruction, model-based reconstruction, and state-of-the-art deep-learning-based mapping methods for three different reduction factors (R = 3, 5, and 7) and two different sampling patterns (1D Cartesian and 2D Poisson-disk). Quantitative metrics indicated that DOPAMINE outperformed other methods in reconstructing T₁ maps for all sampling patterns and reduction factors. DOPAMINE exhibited quantitatively and qualitatively superior performance to that of conventional methods in reconstructing MR parameter maps from undersampled multi-channel k-space data. The proposed method can thus reduce the scan time of quantitative MR parameter mapping that uses a VFA model.