Department of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea.
Magn Reson Med. 2019 Jul;82(1):476-484. doi: 10.1002/mrm.27697. Epub 2019 Feb 20.
To accurately separate water and fat signals for bipolar multi-echo gradient-recalled echo sequence using a convolutional neural network (CNN).
A CNN architecture was designed and trained using the relationship between multi-echo images from the bipolar multi-echo gradient-recalled echo sequence and artifact-free water-fat-separated images. The artifact-free water-fat-separated images for training the CNN were obtained from multiple signals with different TEs by using iterative decomposition of water and fat with echo asymmetry and the least-squares estimation method, in which multiple signals at different TEs were acquired using a single-echo gradient-recalled echo sequence. We also proposed a data augmentation method using a synthetic field inhomogeneity to generate multi-echo signals, including various bipolar multi-echo gradient-recalled echo artifacts so that the CNN could prevent overfitting and increase the separation accuracy. We trained the CNN using in vivo knee images and tested it using in vivo knee, head, and ankle images.
In vivo imaging results showed that the proposed CNN could separate water-fat images accurately. Although the proposed CNN was trained using only in vivo knee images, the proposed CNN could also separate water-fat images of different imaging regions. The proposed data augmentation method could prevent overfitting even with a limited number of training data sets and make the method robust to magnetic field inhomogeneities.
The proposed CNN could obtain water-fat-separated images from the multi-echo images acquired from the bipolar multi-echo gradient-recalled echo sequence, which included artifacts from the bipolar gradients.
使用卷积神经网络（CNN）准确分离双极多回波梯度回波序列中的水和脂肪信号。
设计并训练了一个 CNN 架构，该架构使用双极多回波梯度回波序列的多回波图像与无伪影的水脂分离图像之间的关系。用于训练 CNN 的无伪影水脂分离图像是通过使用具有回波不对称性的水和脂肪的迭代分解以及最小二乘估计方法，从具有不同 TE 的多个信号获得的，其中，使用单回波梯度回波序列获取了具有不同 TE 的多个信号。我们还提出了一种使用合成场不均匀性生成多回波信号的的数据增强方法，包括各种双极多回波梯度回波伪影，以便 CNN 可以防止过拟合并提高分离精度。我们使用体内膝关节图像对 CNN 进行了训练，并使用体内膝关节、头部和踝关节图像对其进行了测试。
体内成像结果表明，所提出的 CNN 可以准确地分离水脂图像。尽管所提出的 CNN 仅使用体内膝关节图像进行训练，但该 CNN 还可以分离不同成像区域的水脂图像。所提出的数据增强方法即使在训练数据集数量有限的情况下也可以防止过拟合，并使该方法对磁场不均匀性具有鲁棒性。
所提出的 CNN 可以从双极多回波梯度回波序列采集的多回波图像中获得水脂分离图像，其中包括双极梯度的伪影。
