Department of Electronic and Computer Engineering, Sungkyunkwan University, South Korea; Center for Neuroscience Imaging Research (CNIR), Institute for Basic Science, South Korea; NEUROPHET Inc., South Korea.
McConnell Brain Imaging Centre, Montreal Neurological Institute and Hospital, McGill University, Montreal, Canada.
Comput Biol Med. 2019 Dec;115:103528. doi: 10.1016/j.compbiomed.2019.103528. Epub 2019 Oct 31.
Medical image synthesis can simulate a target modality of interest based on existing modalities and has the potential to save scanning time while contributing to efficient data collection. This study proposed a three-dimensional (3D) deep learning architecture based on a fully convolutional network (FCN) to synthesize diffusion-tensor imaging (DTI) from resting-state functional magnetic resonance imaging (fMRI).
fMRI signals derived from white matter (WM) exist and can be used for assessing WM alterations. We constructed an initial functional correlation tensor image using the correlation patterns of adjacent fMRI voxels as one input to the FCN. We considered T1-weighted images as an additional input to provide an algorithm with the structural information needed to synthesize DTI. Our architecture was trained and tested using a large-scale open database dataset (training n = 648; testing n = 293).
The average correlation value between synthesized and actual diffusion tensors for 38 WM regions was 0.808, which significantly improves upon an existing study (r = 0.480). We also validated our approach using two open databases. Our proposed method showed a higher correlation with the actual diffusion tensor than the conventional machine-learning method for many WM regions.
Our method synthesized DTI images from fMRI images using a 3D FCN architecture. We hope to expand our method of synthesizing various other imaging modalities from a single image source.
医学图像合成可以根据现有模态模拟目标模态，具有节省扫描时间的潜力，同时有助于高效的数据采集。本研究提出了一种基于全卷积网络（FCN）的三维（3D）深度学习架构，用于从静息态功能磁共振成像（fMRI）合成扩散张量成像（DTI）。
源自于白质（WM）的 fMRI 信号可以用于评估 WM 改变。我们使用相邻 fMRI 体素的相关模式构建初始功能相关张量图像，作为 FCN 的一个输入。我们将 T1 加权图像作为附加输入，为算法提供合成 DTI 所需的结构信息。我们的架构使用大型开放数据库数据集进行训练和测试（训练 n=648；测试 n=293）。
38 个 WM 区域的合成和实际扩散张量之间的平均相关值为 0.808，显著优于现有研究（r=0.480）。我们还使用两个开放数据库验证了我们的方法。与许多 WM 区域的传统机器学习方法相比，我们的方法在许多 WM 区域与实际扩散张量的相关性更高。
我们使用 3D FCN 架构从 fMRI 图像合成 DTI 图像。我们希望扩展我们从单个图像源合成各种其他成像模式的方法。
