Zhu Qiao Yun, Bai HanHua, Wu Yi, Zhou Yu Jia, Feng Qianjin
School of Biomedical Engineering, Southern Medical University, Guangzhou, 510515, People's Republic of China.
Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, Guangzhou, People's Republic of China.
Phys Med Biol. 2021 Nov 15;66(22). doi: 10.1088/1361-6560/ac34b1.
Neuroscience researches based on functional magnetic resonance imaging (fMRI) rely on accurate inter-subject image registration of functional regions. The intersubject alignment of fMRI can improve the statistical power of group analyses. Recent studies have shown the deep learning-based registration methods can be used for registration. In our work, we proposed a 30-Identity-Mapping Cascaded network (30-IMCNet) for rs-fMRI registration. It is a cascaded network that can warp the moving image progressively and finally align to the fixed image. A Combination unit with an identity-mapping path is added to the inputs of each IMCNet to guide the network training. We implemented 30-IMCNet on an rs-fMRI dataset (1000 Functional Connectomes Project dataset) and a task-related fMRI dataset (Eyes Open Eyes Closed fMRI dataset). To evaluate our method, a group-level analysis was implemented in the testing dataset. For rs-fMRI, the criterions such as peak-value of group-level t-maps, cluster-level evaluation, and intersubject functional network correlation were used to evaluate the quality of the registrations. For task-related fMRI, peak-value in ALFF paired-t map and peak-value in ReHo paired-t maps were used. Compared with traditional algorithm FSL, SPM, and deep learning algorithm Kim, Zhaoour method has improvements of 48.90%, 30.73%, 36.38%, and 16.73% in the peakvalue of t-maps. Our proposed method can achieve superior functional registration performance and thus gain a significant improvement in functional consistency.
基于功能磁共振成像（fMRI）的神经科学研究依赖于功能区域准确的受试者间图像配准。fMRI的受试者间对齐可以提高组分析的统计功效。最近的研究表明，基于深度学习的配准方法可用于配准。在我们的工作中，我们提出了一种用于静息态功能磁共振成像（rs-fMRI）配准的30-恒等映射级联网络（30-IMCNet）。它是一个级联网络，可以逐步扭曲运动图像并最终与固定图像对齐。在每个IMCNet的输入中添加了一个具有恒等映射路径的组合单元，以指导网络训练。我们在一个rs-fMRI数据集（1000个功能连接组项目数据集）和一个任务相关的fMRI数据集（睁眼闭眼fMRI数据集）上实现了30-IMCNet。为了评估我们的方法，在测试数据集中进行了组水平分析。对于rs-fMRI，使用组水平t图的峰值、簇水平评估和受试者间功能网络相关性等标准来评估配准质量。对于任务相关的fMRI，使用局部一致性（ALFF）配对t图中的峰值和局部同质性（ReHo）配对t图中的峰值。与传统算法FSL、SPM以及深度学习算法Kim、Zhao相比，我们的方法在t图峰值上分别有48.90%、30.73%、36.38%和16.73%的提升。我们提出的方法可以实现卓越的功能配准性能，从而在功能一致性方面取得显著提升。
