Free-breathing myocardial T1 mapping using inversion-recovery radial FLASH and motion-resolved model-based reconstruction

Abstract

Purpose: To develop a free-breathing myocardial $T_1$ mapping technique using inversion-recovery (IR) radial fast low-angle shot (FLASH) and calibrationless motion-resolved model-based reconstruction.

Methods: Free-running (free-breathing, retrospective cardiac gating) IR radial FLASH is used for data acquisition at 3T. First, to reduce the waiting time between inversions, an analytical formula is derived that takes the incomplete $T_1$ recovery into account for an accurate $T_1$ calculation. Second, the respiratory motion signal is estimated from the k-space center of the contrast varying acquisition using an adapted singular spectrum analysis (SSA-FARY) technique. Third, a motion-resolved model-based reconstruction is used to estimate both parameter and coil sensitivity maps directly from the sorted k-space data. Thus, spatiotemporal total variation, in addition to the spatial sparsity constraints, can be directly applied to the parameter maps. Validations are performed on an experimental phantom, 11 human subjects, and a young landrace pig with myocardial infarction.

Results: In comparison to an IR spin-echo reference, phantom results confirm good $T_1$ accuracy, when reducing the waiting time from 5 s to 1 s using the new correction. The motion-resolved model-based reconstruction further improves $T_1$ precision compared to the spatial regularization-only reconstruction. Aside from showing that a reliable respiratory motion signal can be estimated using modified SSA-FARY, in vivo studies demonstrate that dynamic myocardial $T_1$ maps can be obtained within 2 min with good precision and repeatability.

Conclusion: Motion-resolved myocardial $T_1$ mapping during free-breathing with good accuracy, precision and repeatability can be achieved by combining inversion-recovery radial FLASH, self-gating and a calibrationless motion-resolved model-based reconstruction.

Keywords: free-breathing myocardial T1 mapping; motion-resolved model-based reconstruction; radial FLASH; self-gating; spatiotemporal total variation.

Figure 1.

A. Schematic diagram of the free-running inversion-recovery radial FLASH sequence. Note TD is the delay time between inversions and this period encodes pure T₁ information in the data. B. Flowchart of the main steps in the adapted SSA-FARY technique for the respiratory motion signal estimation from the k-space center.

Figure 2.

Quantitative phantom T₁ maps with various delay times from 5 s to 1 s (step size 1 s) using (top) the conventional Look-Locker correction and (middle) the proposed formula. (Bottom) Quantitative T₁ values (mean and standard deviation) within ROIs of the 6 phantom tubes in comparison to an IR spin-echo reference. The corresponding Bland-Altman plots are shown in the Supporting Information Figure S1 (A).

Figure 3.

(Top) Phantom T₁ maps reconstructed with different regularization using the motion-resolved model-based reconstruction in comparison to an IR spin-echo reference. (Bottom) Quantitative T₁ values (mean and standard deviation) within ROIs of the 6 phantom tubes. The value in the bracket (top) indicates the regularization parameter α_min used for each reconstruction. The corresponding Bland-Altman plots are presented in the Supporting Information Figure S1 (B).

Figure 4.

Snippet of the complex plot with color-coded phase of the DC samples used for auto-calibration before (A) and after (B) data correction with the extended orthogonal projection. Notably less disturbing oscillations are observed in B. The above snippet corresponds to one complete inversion recovery (3 s).

Figure 5.

A. Comparison of the estimated respiratory signal with that obtained from the respiratory belt for 12 inversions for a healthy subject. The background image represents the temporal evolution of a vertical line profile (white line in B) extracted from a real-time image reconstruction [46] of the data acquired with free-running IR radial FLASH. The dark regions represent the time delay between inversions. The white arrow indicates a time point where the respiration belt failed to provide a signal. B. The corresponding steady-state images reconstructed by the non-uniform fast Fourier transform after binning the data (combing all cardiac phases) into 6 respiratory motion states. The dashed green line serves as a baseline for the end-respiration motion state. (C) and (D) show similar results for the pig experiment but with the respiratory belt signal absent.

Figure 6.

(Top) Myocardial T₁ maps (end-expiration and end-diastolic) with different types of regularization using the proposed motion-resolved model-based reconstruction. (Bottom) Horizontal profiles (dashed black line in the top) through all cardiac phases. The black arrows indicate subtle wall motion that is preserved best with the spatio-temporal TV regularization. Note that the regularization parameter α_min for each regularization type was tuned individually to achieve a fair comparison.

Figure 7.

A. (Top) Myocardial T₁ maps (end-expiration and end-diastolic) estimated with motion-resolved model-based reconstruction with different choices of the minimum regularization parameter α_min. (Bottom) Horizontal profiles (dashed black line in the top) through all cardiac phases. B. Quantitative T₁ values (mean and standard deviation) within a ROI in the septal region.

Figure 8.

Diastolic and systolic myocardial T₁ maps (end-expiration) and line profiles through the cardiac phase of the motion-resolved model-based reconstruction acquired during free breathing in comparison to MOLLI acquired in a breathhold for two representative subjects.

Figure 9.

A. Bullseye plots of six mid-ventricular myocardial segments, showing (top) the mean diastolic T₁ values and (bottom) the measurement repeatability errors for all eleven subjects and all scans for (left) the motion-resolved model-based reconstruction (free-breathing) and (right) the MOLLI method (breathhold), respectively. B. Bland–Altman plots comparing the mean diastolic T₁ values of (top) all the six mid-ventricular segments (mean difference: −12 ms, SD: 52 ms) and (bottom) the septal segments (segments 8 and 9 according to AHA, mean difference: 12 ms, SD: 44 ms) for the proposed method and MOLLI for all subjects and scans.

Figure 10.

Synthesized T₁-weighted images at two representative inversion times (bright blood and dark blood) for the end-diastolic and end-systolic cardiac phases for the same subjects shown in Figure 8.