Zhi Da, Shahshahani Ladan, Nettekoven Caroline, Pinho Ana Luísa, Bzdok Danilo, Diedrichsen Jörn
Western Institute for Neuroscience, Western University, London, Ontario, Canada.
Department of Computer Science, Western University, London, Ontario, Canada.
Imaging Neurosci (Camb). 2025 Jan 2;3. doi: 10.1162/imag_a_00408. eCollection 2025.
Different task-based and resting-state imaging datasets provide complementary information about the organization of the human brain. Brain parcellations based on single datasets will, therefore, be biased toward the particular type of information present in each dataset. To overcome this limitation, we propose here a hierarchical Bayesian framework that can learn a probabilistic brain parcellation across numerous task-based and resting-state datasets, exploiting their combined strengths. The framework is partitioned into a spatial arrangement model that defines the probability of each voxel belonging to a specific parcel (the probabilistic group atlas), and a set of dataset-specific emission models that define the probability of the observed data given the parcel of the voxel. Using the human cerebellum as an example, we show that the framework optimally combines information from different datasets to achieve a new population-based atlas that outperforms atlases based on single datasets. Furthermore, we demonstrate that using only 10 min of individual data, the framework is able to generate individual brain parcellations that outperform group atlases.
不同的基于任务和静息状态的成像数据集提供了关于人类大脑组织的互补信息。因此，基于单个数据集的脑图谱划分会偏向于每个数据集中所呈现的特定类型的信息。为了克服这一局限性，我们在此提出一种分层贝叶斯框架，该框架可以利用多个基于任务和静息状态的数据集的综合优势，跨数据集学习概率性脑图谱划分。该框架分为一个空间排列模型和一组特定于数据集的发射模型，前者定义每个体素属于特定脑区的概率（概率性群体图谱），后者定义给定体素所属脑区时观测数据的概率。以人类小脑为例，我们表明该框架能最佳地整合来自不同数据集的信息，以获得一个新的基于群体的图谱，其性能优于基于单个数据集的图谱。此外，我们证明仅使用10分钟的个体数据，该框架就能生成优于群体图谱的个体脑图谱划分。
