基于物理的重建与 k 空间（SPARK）神经网络的特定扫描伪影减少技术协同作用，加速 MRI。
Scan-specific artifact reduction in k-space (SPARK) neural networks synergize with physics-based reconstruction to accelerate MRI.
机构信息
Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA.
Computer and Communication Sciences, École Polytechnique Fédérale de Lausanne, Lausanne, Switzerland.
出版信息
Magn Reson Med. 2022 Feb;87(2):764-780. doi: 10.1002/mrm.29036. Epub 2021 Oct 2.
PURPOSE
To develop a scan-specific model that estimates and corrects k-space errors made when reconstructing accelerated MRI data.
METHODS
Scan-specific artifact reduction in k-space (SPARK) trains a convolutional-neural-network to estimate and correct k-space errors made by an input reconstruction technique by back-propagating from the mean-squared-error loss between an auto-calibration signal (ACS) and the input technique's reconstructed ACS. First, SPARK is applied to generalized autocalibrating partially parallel acquisitions (GRAPPA) and demonstrates improved robustness over other scan-specific models, such as robust artificial-neural-networks for k-space interpolation (RAKI) and residual-RAKI. Subsequent experiments demonstrate that SPARK synergizes with residual-RAKI to improve reconstruction performance. SPARK also improves reconstruction quality when applied to advanced acquisition and reconstruction techniques like 2D virtual coil (VC-) GRAPPA, 2D LORAKS, 3D GRAPPA without an integrated ACS region, and 2D/3D wave-encoded imaging.
RESULTS
SPARK yields SSIM improvement and 1.5 - 2× root mean squared error (RMSE) reduction when applied to GRAPPA and improves robustness to ACS size for various acceleration rates in comparison to other scan-specific techniques. When applied to advanced reconstruction techniques such as residual-RAKI, 2D VC-GRAPPA and LORAKS, SPARK achieves up to 20% RMSE improvement. SPARK with 3D GRAPPA also improves RMSE performance by ~2×, SSIM performance, and perceived image quality without a fully sampled ACS region. Finally, SPARK synergizes with non-Cartesian, 2D and 3D wave-encoding imaging by reducing RMSE between 20% and 25% and providing qualitative improvements.
CONCLUSION
SPARK synergizes with physics-based acquisition and reconstruction techniques to improve accelerated MRI by training scan-specific models to estimate and correct reconstruction errors in k-space.
目的
开发一种特定于扫描的模型，用于估计和校正重建加速 MRI 数据时的 k 空间误差。
方法
k 空间特定于扫描的伪影校正（SPARK）通过从自动校准信号（ACS）和输入技术重建的 ACS 之间的均方误差损失反向传播，训练卷积神经网络来估计和校正输入重建技术产生的 k 空间误差。首先，将 SPARK 应用于广义自动校准部分并行采集（GRAPPA），并展示了相对于其他特定于扫描的模型（如 k 空间插值的稳健人工神经网络（RAKI）和残差-RAKI）的更高鲁棒性。后续实验表明，SPARK 与残差-RAKI 协同作用可提高重建性能。当应用于先进的采集和重建技术，如二维虚拟线圈（VC-）GRAPPA、二维 LORAKS、无集成 ACS 区域的三维 GRAPPA 和二维/三维波编码成像时，SPARK 也可以提高重建质量。
结果
SPARK 应用于 GRAPPA 时可提高 SSIM 并降低 1.5-2 倍均方根误差（RMSE），并与其他特定于扫描的技术相比，提高了对各种加速率的 ACS 大小的鲁棒性。当应用于高级重建技术，如残差-RAKI、二维 VC-GRAPPA 和 LORAKS 时，SPARK 可实现高达 20%的 RMSE 改善。具有三维 GRAPPA 的 SPARK 还可以改善 RMSE 性能约 2 倍、SSIM 性能和感知图像质量，而无需完全采样的 ACS 区域。最后，SPARK 通过在 20%至 25%之间降低 RMSE 并提供定性改善，与非笛卡尔、二维和三维波编码成像协同作用。
结论
SPARK 通过训练特定于扫描的模型来估计和校正 k 空间中的重建误差，与基于物理的采集和重建技术协同作用，从而改善加速 MRI。
Zotero 插件