Unsupervised Deep Learning for Susceptibility Distortion Correction in Connectome Imaging.
Unsupervised Deep Learning for Susceptibility Distortion Correction in Connectome Imaging.
复制标题
DOI：
10.1007/978-3-030-59728-3_30
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Shi Y
中科院分区：
文献类型：
--
作者：
Qiao Y;Shi Y
为了减少HCP-Pipeline预处理的高分辨率弥散MRI（dMRI）数据中的残余失真，我们提出了一种基于无监督深度学习的方法来校正残余磁化率引起的失真。在我们的方法中，使用从dMRI数据计算的纤维取向分布（FOD）图像，而不是使用来自两相编码（PE）的B 0图像，其提供更可靠的对比度信息。我们的深度学习框架名为DistoRtion Correction Net（DrC-Net），它使用U-Net从FOD图像中捕获潜在特征，并沿相位编码方向沿着估计变形场。借助Transformer网络，我们可以将变形特征传播到FOD图像，并将变形图像和真实未失真图像之间的损失反向传播。拟议的DrC-Net在从人类连接组项目（HCP）数据集中的100名受试者中随机选择的60名受试者上进行训练。我们在其余40个受试者上评估了DrC-Net，结果显示与训练数据集相比，其性能相似。我们的评估方法使用分数各向异性（FA）的均方差（MSD）和两个PE之间的最小角度差。我们将DrC-Net与HCP-Pipeline中使用的topup方法进行了比较，结果表明，这两种评估方法在纠正磁化率引起的失真方面都有显着改进。
To reduce the residual distortion in high resolution diffusion MRI (dMRI) data preprocessed by the HCP-Pipeline, we propose an unsupervised deep learning based method to correct the residual susceptibility induced distortion. Instead of using B0 images from two phase encoding (PE), fiber orientation distribution (FOD) images computed from dMRI data, which provide more reliable contrast information, are used in our method. Our deep learning framework named DistoRtion Correction Net (DrC-Net) uses an U-Net to capture the latent features from FOD images and estimates a deformation field along the phase encoding direction. With the help of a transformer network, we can propagate the deformation feature to the FOD images and back propagate the losses between the deformed images and true undistorted images. The proposed DrC-Net is trained on 60 subjects randomly selected from 100 subjects in the Human Connectome Project (HCP) dataset. We evaluated the DrC-Net on the rest 40 subjects and the results show a similar performance compared to the training dataset. Our evaluation method used mean squared difference (MSD) of fractional anisotropy (FA) and minimum angular difference between two PEs. We compared the DrC-Net to topup method used in the HCP-Pipeline, and the results show a significant improvement to correct the susceptibility induced distortions in both evaluation methods.