Wang Yingying, Feng Yu, Zeng Weiming
Lab of Digital Image and Intelligent Computation, College of Information Engineering, Shanghai Maritime University, Shanghai 201306, China.
Brain Sci. 2025 Jan 5;15(1):46. doi: 10.3390/brainsci15010046.
In neuroscience research about functional magnetic resonance imaging (fMRI), accurate inter-subject image registration is the basis for effective statistical analysis. Traditional fMRI registration methods are usually based on high-resolution structural MRI with clear anatomical structure features. However, this registration method based on structural information cannot achieve accurate functional consistency between subjects since the functional regions do not necessarily correspond to anatomical structures. In recent years, fMRI registration methods based on functional information have emerged, which usually ignore the importance of structural MRI information.
In this study, we proposed a non-rigid cycle consistent bidirectional network with Transformer for unsupervised deformable functional MRI registration. The work achieves fMRI registration through structural MRI registration, and functional information is introduced to improve registration performance. Specifically, we employ a bidirectional registration network that implements forward and reverse registration between image pairs and apply Transformer in the registration network to establish remote spatial mapping between image voxels. Functional and structural information are integrated by introducing the local functional connectivity pattern, the local functional connectivity features of the whole brain are extracted as functional information. The proposed registration method was experimented on real fMRI datasets, and qualitative and quantitative evaluations of the quality of the registration method were implemented on the test dataset using relevant evaluation metrics. We implemented group ICA analysis in brain functional networks after registration. Functional consistency was evaluated on the resulting t-maps.
Compared with non-learning-based methods (Affine, Syn) and learning-based methods (Transmorph-tiny, Cyclemorph, VoxelMorph x2), our method improves the peak t-value of t-maps on DMN, VN, CEN, and SMN to 18.7, 16.5, 16.6, and 17.3 and the mean number of suprathreshold voxels ( < 0.05, t > 5.01) on the four networks to 2596.25, and there is an average improvement in peak t-value of 23.79%, 12.74%, 12.27%, 7.32%, and 5.43%.
The experimental results show that the registration method of this study improves the structural and functional consistency between fMRI with superior registration performance.
在功能磁共振成像（fMRI）的神经科学研究中，准确的受试者间图像配准是有效统计分析的基础。传统的fMRI配准方法通常基于具有清晰解剖结构特征的高分辨率结构MRI。然而，这种基于结构信息的配准方法无法实现受试者之间准确的功能一致性，因为功能区域不一定与解剖结构相对应。近年来，基于功能信息的fMRI配准方法应运而生，但这些方法通常忽略了结构MRI信息的重要性。
在本研究中，我们提出了一种基于Transformer的无监督可变形功能磁共振成像配准的非刚性循环一致双向网络。该工作通过结构MRI配准实现fMRI配准，并引入功能信息以提高配准性能。具体而言，我们采用双向配准网络，在图像对之间实现正向和反向配准，并在配准网络中应用Transformer来建立图像体素之间的远程空间映射。通过引入局部功能连接模式来整合功能和结构信息，提取全脑的局部功能连接特征作为功能信息。所提出的配准方法在真实的fMRI数据集上进行了实验，并使用相关评估指标在测试数据集上对配准方法的质量进行了定性和定量评估。我们在配准后的脑功能网络中实施了组独立成分分析（ICA）。在得到的t图上评估功能一致性。
与基于非学习的方法（仿射变换、Syn）和基于学习的方法（Transmorph-tiny、Cyclemorph、VoxelMorph x2）相比，我们的方法将默认模式网络（DMN）、视觉网络（VN）、中央执行网络（CEN）和体感运动网络（SMN）上t图的峰值t值分别提高到18.7、16.5、16.6和17.3，将四个网络上超阈值体素（<0.05，t>5.01）的平均数量提高到2596.25，峰值t值平均提高了23.79%、12.74%、12.27%、7.32%和5.43%。
实验结果表明，本研究的配准方法提高了fMRI之间的结构和功能一致性，具有优异的配准性能。
