Fast and accurate reconstruction of human lung gas MRI with deep learning
Fast and accurate reconstruction of human lung gas MRI with deep learning
复制标题
利用深度学习快速准确地重建人体肺气 MRI
DOI：
10.1002/mrm.27889
复制
发表时间：
2019-07-19
影响因子：
3.3
通讯作者：
Zhou, Xin
中科院分区：
文献类型：
--
作者：
Duan, Caohui;Deng, He;Zhou, Xin
目的 使用深度学习从高度欠采样的 k 空间快速准确地重建人体肺部气体 MRI。方法该方案由粗到细的网络（C-net 和 F-net）组成。来自以加速因子 4 进行回顾性欠采样 k 空间的零填充图像被用作 C-net 的输入，然后输出中间结果，该中间结果被馈送到 F-net 中。训练时，C-net中采用L2损失函数，F-net中采用L2损失与质子先验知识相结合的函数。来自 72 名志愿者的 871 张超极化 Xe-129 肺通气图像被随机排列为训练数据（90%）和测试数据（10%）。使用配对 2 尾学生 t 检验和相关分析进行通风缺陷百分比比较。此外，在 5 名健康受试者和 5 名无症状吸烟者中证实了预期获得性。结果每张尺寸为96 x 84的图像可以在31 ms内重建（平均绝对误差为4.35%，结构相似度为0.7558）。与传统压缩感知MRI相比，平均绝对误差降低了17.92%，但结构相似度提高了6.33%。对于通气缺陷百分比，通过所提出的算法完全采样和重建图像之间没有显着差异（P = 0.932），但具有显着相关性（r = 0.975；P < 0.001）。前瞻性欠采样结果验证了与完全采样图像的良好一致性，通气缺陷百分比没有显着差异，但信噪比值明显更高。结论 该算法优于经典的欠采样方法，为未来使用深度学习实时准确地重建气体 MRI 铺平了道路。
Purpose To fast and accurately reconstruct human lung gas MRI from highly undersampled k-space using deep learning. Methods The scheme was comprised of coarse-to-fine nets (C-net and F-net). Zero-filling images from retrospectively undersampled k-space at an acceleration factor of 4 were used as input for C-net, and then output intermediate results which were fed into F-net. During training, a L2 loss function was adopted in C-net, while a function that united L2 loss with proton prior knowledge was used in F-net. The 871 hyperpolarized Xe-129 pulmonary ventilation images from 72 volunteers were randomly arranged as training (90%) and testing (10%) data. Ventilation defect percentage comparisons were implemented using a paired 2-tailed Student's t-test and correlation analysis. Furthermore, prospective acquisitions were demonstrated in 5 healthy subjects and 5 asymptomatic smokers. Results Each image with size of 96 x 84 could be reconstructed within 31 ms (mean absolute error was 4.35% and structural similarity was 0.7558). Compared with conventional compressed sensing MRI, the mean absolute error decreased by 17.92%, but the structural similarity increased by 6.33%. For ventilation defect percentage, there were no significant differences between the fully sampled and reconstructed images through the proposed algorithm (P = 0.932), but had significant correlations (r = 0.975; P < 0.001). The prospectively undersampled results validated a good agreement with fully sampled images, with no significant differences in ventilation defect percentage but significantly higher signal-to-noise ratio values. Conclusion The proposed algorithm outperformed classical undersampling methods, paving the way for future use of deep learning in real-time and accurate reconstruction of gas MRI.