Hierarchical Brain Networks Decomposition via Prior Knowledge Guided Deep Belief Network

Tianji Pang, Dajiang Zhu, Tianming Liu, Junwei Han, Shijie ZhaoMICCAI 2022 · OpenReview

Abstract

Modeling and characterizing functional brain networks from task-based functional magnetic resonance imaging (fMRI) data has been a popular topic in neuroimaging community. Recently, deep belief network (DBN) has shown great advantages in modeling the hierarchical and complex task functional brain networks (FBNs). However, due to the unsupervised nature, traditional DBN algorithms may be limited in fully utilizing the prior knowledge from the task design. In addition, the FBNs extracted from different DBN layers do not have correspondences, which makes the hierarchical analysis of FBNs a challenging problem. In this paper, we propose a novel prior knowledge guided DBN (PKG-DBN) to overcome the above limitations when conducting hierarchical task FBNs analysis. Specifically, we enforce part of the time courses learnt from DBN to be task-related (in either positive or negative way) and the rest to be linear combinations of task-related components. By incorporating such constraints in the learning process, our method can simultaneously leverage the advantages of data-driven approaches and the prior knowledge of task design. Our experiment results on HCP task fMRI data showed that the proposed PKG-DBN can not only successfully identify meaningful hierarchical task FBNs with correspondence comparing to traditional DBN models, but also converge significantly faster than traditional DBN models.
BibTeX
@inproceedings{pang2022hierarchical,
  author = {Tianji Pang and Dajiang Zhu and Tianming Liu and Junwei Han and Shijie Zhao},
  title = {{Hierarchical Brain Networks Decomposition via Prior Knowledge Guided Deep Belief Network}},
  booktitle = {International Conference on Medical Image Computing and Computer-Assisted Intervention},
  year = {2022},
  url = {https://openreview.net/forum?id=TeXaz0IEof},
}

Loading related content...

Figure