Accelerated cardiac T1 mapping with recurrent networks and cyclic, model-based loss.

BACKGROUND: Using the spin-lattice relaxation time (T1) as a biomarker, the myocardium can be quantitatively characterized using cardiac T1 mapping. The modified Look-Locker inversion (MOLLI) recovery sequences have become the standard clinical method for cardiac T1 mapping. However, the MOLLI sequences require an 11-heartbeat breath-hold that can be difficult for subjects, particularly during exercise or pharmacologically induced stress. Although shorter cardiac T1 mapping sequences have been proposed, these methods suffer from reduced precision. As such, there is an unmet need for accelerated cardiac T1 mapping. PURPOSE: To accelerate cardiac T1 mapping MOLLI sequences by using neural networks to estimate T1 maps using a reduced number of T1-weighted images and their corresponding inversion times. MATERIALS AND METHODS: In this retrospective study, 911 pre-contrast T1 mapping datasets from 202 subjects (128 males, 56 ± 15 years; 74 females, 54 ± 17 years) and 574 T1 mapping post-contrast datasets from 193 subjects (122 males, 57 ± 15 years; 71 females, 54 ± 17 years) were acquired using the MOLLI-5(3)3 sequence and the MOLLI-4(1)3(1)2 sequence, respectively. All acquisition protocols used similar scan parameters: T R = 2.2 ms $TR\; = \;2.2\;{\rm{ms}}$ , T E = 1.12 ms $TE\; = \;1.12\;{\rm{ms}}$ , and F A = 35 ∘ $FA\; = \;35^\circ $ , gadoteridol (ProHance, Bracco Diagnostics) dose ∼ 0.075 mmol / kg $\sim 0.075\;\;{\rm{mmol/kg}}$ . A bidirectional multilayered long short-term memory (LSTM) network with fully connected output and cyclic model-based loss was used to estimate T1 maps from the first three T1-weighted images and their corresponding inversion times for pre- and post-contrast T1 mapping. The performance of the proposed architecture was compared to the three-parameter T1 recovery model using the same reduction of the number of T1-weighted images and inversion times. Reference T1 maps were generated from the scanner using the full MOLLI sequences and the three-parameter T1 recovery model. Correlation and Bland-Altman plots were used to evaluate network performance in which each point represents averaged regions of interest in the myocardium corresponding to the standard American Heart Association 16-segment model. The precision of the network was examined using consecutively repeated scans. Stress and rest pre-contrast MOLLI studies as well as various disease test cases, including amyloidosis, hypertrophic cardiomyopathy, and sarcoidosis were also examined. Paired t-tests were used to determine statistical significance with p < 0.05 $p < 0.05$ . RESULTS: Our proposed network demonstrated similar T1 estimations to the standard MOLLI sequences (pre-contrast: 1260 ± 94 ms $1260 \pm 94\;{\rm{ms}}$ vs. 1254 ± 91 ms $1254 \pm 91\;{\rm{ms}}$ with p = 0.13 $p\; = \;0.13$ ; post-contrast: 484 ± 92 ms $484 \pm 92\;{\rm{ms}}$ vs. 493 ± 91 ms $493 \pm 91\;{\rm{ms}}$ with p = 0.07 $p\; = \;0.07$ ). The precision of standard MOLLI sequences was well preserved with the proposed network architecture ( 24 ± 28 ms $24 \pm 28\;\;{\rm{ms}}$ vs. 18 ± 13 ms $18 \pm 13\;{\rm{ms}}$ ). Network-generated T1 reactivities are similar to stress and rest pre-contrast MOLLI studies ( 5.1 ± 4.0 % $5.1 \pm 4.0\;\% $ vs. 4.9 ± 4.4 % $4.9 \pm 4.4\;\% $ with p = 0.84 $p\; = \;0.84$ ). Amyloidosis T1 maps generated using the proposed network are also similar to the reference T1 maps (pre-contrast: 1243 ± 140 ms $1243 \pm 140\;\;{\rm{ms}}$ vs. 1231 ± 137 ms $1231 \pm 137\;{\rm{ms}}$ with p = 0.60 $p\; = \;0.60$ ; post-contrast: 348 ± 26 ms $348 \pm 26\;{\rm{ms}}$ vs. 346 ± 27 ms $346 \pm 27\;{\rm{ms}}$ with p = 0.89 $p\; = \;0.89$ ). CONCLUSIONS: A bidirectional multilayered LSTM network with fully connected output and cyclic model-based loss was used to generate high-quality pre- and post-contrast T1 maps using the first three T1-weighted images and their corresponding inversion times. This work demonstrates that combining deep learning with cardiac T1 mapping can potentially accelerate standard MOLLI sequences from 11 to 3 heartbeats.

Deep learning for radial SMS myocardial perfusion reconstruction using the 3D residual booster U-net.

PURPOSE: To develop an end-to-end deep learning solution for quickly reconstructing radial simultaneous multi-slice (SMS) myocardial perfusion datasets with comparable quality to the pixel tracking spatiotemporal constrained reconstruction (PT-STCR) method. METHODS: Dynamic contrast enhanced (DCE) radial SMS myocardial perfusion data were obtained from 20 subjects who were scanned at rest and/or stress with or without ECG gating using a saturation recovery radial CAIPI turboFLASH sequence. Input to the networks consisted of complex coil combined images reconstructed using the inverse Fourier transform of undersampled radial SMS k-space data. Ground truth images were reconstructed using the PT-STCR pipeline. The performance of the residual booster 3D U-Net was tested by comparing it to state-of-the-art network architectures including MoDL, CRNN-MRI, and other U-Net variants. RESULTS: Results demonstrate significant improvements in speed requiring approximately 8 seconds to reconstruct one radial SMS dataset which is approximately 200 times faster than the PT-STCR method. Images reconstructed with the residual booster 3D U-Net retain quality of ground truth PT-STCR images (0.963 SSIM/40.238 PSNR/0.147 NRMSE). The residual booster 3D U-Net has superior performance compared to existing network architectures in terms of image quality, temporal dynamics, and reconstruction time. CONCLUSION: Residual and booster learning combined with the 3D U-Net architecture was shown to be an effective network for reconstructing high-quality images from undersampled radial SMS datasets while bypassing the reconstruction time of the PT-STCR method.