SuperMAP: Deep ultrafast MR relaxometry with joint spatiotemporal undersampling

PURPOSE

To develop an ultrafast and robust MR parameter mapping network using deep learning.

THEORY AND METHODS

We design a deep learning framework called SuperMAP that directly converts a series of undersampled (both in k-space and parameter-space) parameter-weighted images into several quantitative maps, bypassing the conventional exponential fitting procedure. We also present a novel technique to simultaneously reconstruct T1rho and T2 relaxation maps within a single scan. Full data were acquired and retrospectively undersampled for training and testing using traditional and state-of-the-art techniques for comparison. Prospective data were also collected to evaluate the trained network. The performance of all methods is evaluated using the parameter qualification errors and other metrics in the segmented regions of interest.

RESULTS

SuperMAP achieved accurate T1rho and T2 mapping with high acceleration factors (R = 24 and R = 32). It exploited both spatial and temporal information and yielded low error (normalized mean square error of 2.7% at R = 24 and 2.8% at R = 32) and high resemblance (structural similarity of 97% at R = 24 and 96% at R = 32) to the gold standard. The network trained with retrospectively undersampled data also works well for the prospective data (with a slightly lower acceleration factor). SuperMAP is also superior to conventional methods.

CONCLUSION

Our results demonstrate the feasibility of generating superfast MR parameter maps through very few undersampled parameter-weighted images. SuperMAP can simultaneously generate T1rho and T2 relaxation maps in a short scan time.

23 Na MRI in ischemic stroke: Acquisition time reduction using postprocessing with convolutional neural networks

Quantitative ²³ Na magnetic resonance imaging (MRI) provides tissue sodium concentration (TSC), which is connected to cell viability and vitality. Long acquisition times are one of the most challenging aspects for its clinical establishment. K-space undersampling is an approach for acquisition time reduction, but generates noise and artifacts. The use of convolutional neural networks (CNNs) is increasing in medical imaging and they are a useful tool for MRI postprocessing. The aim of this study is ²³ Na MRI acquisition time reduction by k-space undersampling. CNNs were applied to reduce the resulting noise and artifacts. A retrospective analysis from a prospective study was conducted including image datasets from 46 patients (aged 72 ± 13 years; 25 women, 21 men) with ischemic stroke; the ²³ Na MRI acquisition time was 10 min. The reconstructions were performed with full dataset (FI) and with a simulated dataset an image that was acquired in 2.5 min (RI). Eight different CNNs with either U-Net-based or ResNet-based architectures were implemented with RI as input and FI as label, using batch normalization and the number of filters as varying parameters. Training was performed with 9500 samples and testing included 400 samples. CNN outputs were evaluated based on signal-to-noise ratio (SNR) and structural similarity (SSIM). After quantification, TSC error was calculated. The image quality was subjectively rated by three neuroradiologists. Statistical significance was evaluated by Student's t-test. The average SNR was 21.72 ± 2.75 (FI) and 10.16 ± 0.96 (RI). U-Nets increased the SNR of RI to 43.99 and therefore performed better than ResNet. SSIM of RI to FI was improved by three CNNs to 0.91 ± 0.03. CNNs reduced TSC error by up to 15%. The subjective rating of CNN-generated images showed significantly better results than the subjective image rating of RI. The acquisition time of ²³ Na MRI can be reduced by 75% due to postprocessing with a CNN on highly undersampled data.

Performance of a fast and high-resolution multi-echo spin-echo sequence for prostate T2 mapping across multiple systems

PURPOSE

To evaluate the performance of a multi-echo spin-echo sequence with k-t undersampling scheme (k-t T₂ ) in prostate cancer.

METHODS

Phantom experiments were performed at five systems to estimate the bias, short-term repeatability, and reproducibility across all systems expressed with the within-subject coefficient of variation (wCV). Monthly measurements were performed on two systems for long-term repeatability estimation. To evaluate clinical repeatability, two T₂ maps (voxel size 0.8 × 0.8 × 3 mm³ ; 5 min) were acquired at separate visits on one system for 13 prostate cancer patients. Repeatability was assessed per patient in relation to spatial resolution. T₂ values were compared for tumor, peripheral zone, and transition zone.

RESULTS

Phantom measurements showed a small bias (median = -0.9 ms) and good short-term repeatability (median wCV = 0.5%). Long-term repeatability was 0.9 and 1.1% and reproducibility between systems was 1.7%. The median bias observed in patients was -1.1 ms. At voxel level, the median wCV was 15%, dropping to 4% for structures of 0.5 cm³ . The median tumor T₂ values (79 ms) were significantly lower (P < 0.001) than in the peripheral zone (149 ms), but overlapped with the transition zone (91 ms).

CONCLUSIONS

Reproducible T₂ mapping of the prostate is feasible with good spatial resolution in a clinically reasonable scan time, allowing reliable measurement of T₂ in structures as small as 0.5 cm³ . Magn Reson Med 79:1586-1594, 2018. © 2017 International Society for Magnetic Resonance in Medicine.