A deep learning approach for fast muscle water T2 mapping with subject specific fat T2 calibration from multi-spin-echo acquisitions.
A deep learning approach for fast muscle water T2 mapping with subject specific fat T2 calibration from multi-spin-echo acquisitions.
复制标题
一种用于快速肌肉水 T2 映射的深度学习方法，通过多自旋回波采集进行受试者特定脂肪 T2 校准。
DOI：
10.1038/s41598-024-58812-2
复制
发表时间：
2024
影响因子：
4.6
通讯作者：
Mazzoli,Valentina
中科院分区：
文献类型：
--
作者：
Barbieri,Marco;Hooijmans,MelissaT;Moulin,Kevin;Cork,TylerE;Ennis,DanielB;Gold,GarryE;Kogan,Feliks;Mazzoli,Valentina
这项工作提出了一种深度学习方法，用于快速准确的肌肉水T2，并使用多自旋回波采集进行特定于受试者的脂肪T2校准。该方法通过利用完全连接的神经网络以最小的计算资源进行快速处理，解决了传统双分量扩展相位图拟合方法（非线性最小二乘和基于字典）的计算限制。我们使用两个不同的MRI供应商通过体内实验验证了该方法。结果显示，我们的深度学习方法与参考方法高度一致，Lin的一致性相关系数范围为0.89至0.97。此外，深度学习方法实现了显着的计算时间改进，处理数据的速度分别比非线性最小二乘法和字典方法快116倍和33倍。总之，所提出的方法表现出显着的时间和资源效率比传统方法的改进，同时保持类似的准确性。这种方法使水T2数据的处理更快，更容易为用户，并将促进利用定量水T2地图的肌肉在临床和研究中的使用。
This work presents a deep learning approach for rapid and accurate muscle water T2with subject-specific fat T2calibration using multi-spin-echo acquisitions. This method addresses the computational limitations of conventional bi-component Extended Phase Graph fitting methods (nonlinear-least-squares and dictionary-based) by leveraging fully connected neural networks for fast processing with minimal computational resources. We validated the approach through in vivo experiments using two different MRI vendors. The results showed strong agreement of our deep learning approach with reference methods, summarized by Lin’s concordance correlation coefficients ranging from 0.89 to 0.97. Further, the deep learning method achieved a significant computational time improvement, processing data 116 and 33 times faster than the nonlinear least squares and dictionary methods, respectively. In conclusion, the proposed approach demonstrated significant time and resource efficiency improvements over conventional methods while maintaining similar accuracy. This methodology makes the processing of water T2data faster and easier for the user and will facilitate the utilization of the use of a quantitative water T2map of muscle in clinical and research studies.