.png){kind=icon}
返回
An untrained deep learning method for reconstructing dynamic MR images from accelerated model-based data
.png){kind=icon}
OA
AI
DOI：10.1002/mrm.29547.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Purpose To implement physics-based regularization as a stopping condition in tuning an untrained deep neural network for reconstructing MR images from accelerated data. Methods The ConvDecoder (CD) neural network was trained with a physics-based regularization term incorporating the spoiled gradient echo equation that describes variable-flip angle data. Fully-sampled variable-flip angle k-space data were retrospectively accelerated by factors of R = {8, 12, 18, 36} and reconstructed with CD, CD with the proposed regularization (CD + r), locally low-rank (LR) reconstruction, and compressed sensing with L1-wavelet regularization (L1). Final images from CD + r training were evaluated at the argmin of the regularization loss; whereas the CD, LR, and L1 reconstructions were chosen optimally based on ground truth data. The performance measures used were the normalized RMS error, the concordance correlation coefficient, and the structural similarity index. Results The CD + r reconstructions, chosen using the stopping condition, yielded structural similarity indexs that were similar to the CD (p = 0.47) and LR structural similarity indexs (p = 0.95) across R and that were significantly higher than the L1 structural similarity indexs (p = 0.04). The concordance correlation coefficient values for the CD + r T-1 maps across all R and subjects were greater than those corresponding to the L1 (p = 0.15) and LR (p = 0.13) T-1 maps, respectively. For R >= 12 (<= 4.2 min scan time), L1 and LR T-1 maps exhibit a loss of spatially refined details compared to CD + r. Conclusion The use of an untrained neural network together with a physics-based regularization loss shows promise as a measure for determining the optimal stopping point in training without relying on fully-sampled ground truth data.
Keyword:
image reconstruction
inverse problem
physics-guided deep learning
quantitative MRI
期刊
IF:
3
论文数:
1.2W
被引数:
3.1W
机构
引用论文
分享收藏The effects of developer age on diagnostic accuracy: a study using assessment of endodontic file length开发者年龄对诊断准确性的影响：一项使用根管锉长度评估的研究
PREAI
分享收藏Pressure-temperature trajectory of the Sanbagawa metamorphism deduced from garnet zoning根据石榴石成分环带推断的须越变质作用的压力-温度轨迹.png)
Lithos
LithosIF0
PREAI
分享收藏分享收藏
查看更多内容