MR fingerprinting Deep RecOnstruction NEtwork (DRONE).
MR fingerprinting Deep RecOnstruction NEtwork (DRONE).
复制标题
DOI：
10.1002/mrm.27198
复制
发表时间：
2018-09
影响因子：
3.3
通讯作者：
Rosen MS
中科院分区：
文献类型：
--
作者：
Cohen O;Zhu B;Rosen MS
演示一种使用深度学习方法重建多维MR指纹（MRF）数据的新型快速方法。使用TensorFlow框架定义神经网络（NN），并在使用扩展相位图形式主义计算的模拟MRF数据上进行训练。将无噪声和有噪声数据的NN重建精度与传统的MRF模板匹配进行比较，作为训练数据大小的函数，并在1.5T和3 T扫描仪上测量的模拟数值脑体模数据和ISMRM/NIST体模数据中进行量化，其中优化的MRF EPI和MRF FISP序列具有螺旋读出。该方法的实用性在健康受试者体内1.5 T下得到证实。网络训练需要10至74分钟，一旦训练完成，MRF EPI的数据重建需要约10 ms，MRF FISP序列的数据重建需要约76 ms。使用NN重建模拟的无噪声大脑数据，T1和T2的均方根误差（RMSE）分别为2.6 ms和1.9 ms。对于信噪比大于25 dB的T1和T2，存在噪声时的重建误差小于10%。通过NN估计的T1和T2与ISMRM/NIST体模的参考值之间的体模测量结果具有良好的一致性（MRF EPI T1/T2的R2=0.99/0.99，MRF FISP T1/T2的R2 = 0.94/0.98）。用NN重建MRF数据是准确的，比传统的MRF字典匹配快300-5000倍，并且对噪声和欠采样更鲁棒。
Demonstrate a novel fast method for reconstruction of multi-dimensional MR Fingerprinting (MRF) data using Deep Learning methods. A neural network (NN) is defined using the TensorFlow framework and trained on simulated MRF data computed with the Extended Phase Graph formalism. The NN reconstruction accuracy for noiseless and noisy data is compared to conventional MRF template matching as a function of training data size, and quantified in simulated numerical brain phantom data and ISMRM/NIST phantom data measured on 1.5T and 3T scanners with an optimized MRF EPI and MRF FISP sequences with spiral readout. The utility of the method is demonstrated in a healthy subject in vivo at 1.5 T. Network training required 10 to 74 minutes and once trained, data reconstruction required approximately 10 ms for the MRF EPI and 76 ms for the MRF FISP sequence. Reconstruction of simulated, noiseless brain data using the NN resulted in a root-mean-square error (RMSE) of 2.6 ms for T1 and 1.9 ms for T2. The reconstruction error in the presence of noise was less than 10% for both T1 and T2 for signal-to-noise greater than 25 dB. Phantom measurements yielded good agreement (R2=0.99/0.99 for MRF EPI T1/T2 and 0.94/0.98 for MRF FISP T1/T2) between the T1 and T2 estimated by the NN and reference values from the ISMRM/NIST phantom. Reconstruction of MRF data with a NN is accurate, 300–5000 fold faster and more robust to noise and undersampling than conventional MRF dictionary matching.
登录
查看更多内容
影响因子：
3.3
作者：
Pierre EY;Ma D;Chen Y;Badve C;Griswold MA
通讯作者：
Griswold MA
影响因子：
3.3
作者：
Deoni, SCL;Peters, TM;Rutt, BK
通讯作者：
Rutt, BK
影响因子：
3.3
作者：
Griswold, MA;Jakob, PM;Haase, A
通讯作者：
Haase, A
影响因子：
3.3
作者：
Cauley SF;Setsompop K;Ma D;Jiang Y;Ye H;Adalsteinsson E;Griswold MA;Wald LL
通讯作者：
Wald LL
影响因子：
7.8
作者：
HORNIK, K;STINCHCOMBE, M;WHITE, H
通讯作者：
WHITE, H