Xiaojuan Guo

Xiaojuan Guo

Auto-generated profile, based on publicly available information

Xiaojuan Guo

School of Information Engineering, Ordos Institute of Technology, Ordos, Inner Mongolia, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 April 2019 in IEEE Access
Verified
Journal Article
Open access
YGYufei Gao
Yufei Gao
YZYameng Zhang
Yameng Zhang
HWHailing Wang
Hailing Wang
XGXiaojuan Guo
Xiaojuan Guo
JZjiacai Zhang
jiacai Zhang
Recently, advances in noninvasive detection techniques have shown that it is possible to decode visual information from measurable brain activities. However, these studies typically focused on the mapping between neural activities and visual information, such as the image or video stimulus, on the individual level. Here, the common decoding models across individuals that classifying behavior tasks from brain signals were investigated. We proposed a cross-subject decoding approach using deep transfer learning (DTL) to decipher the behavior tasks from functional magnetic resonance imaging (fMRI) recording during subjects performing different tasks. We connected parts of the state-of-the-art networks pre-trained on the ImageNet dataset to our defined adaption layers to classify the behavior tasks from fMRI data. Our experiments on the Human Connectome Project (HCP) dataset showed that the proposed method achieved a higher decoding accuracy across subjects than the previous studies. We also conducted an experiment on five subsets of HCP data, which further demonstrated that our DTL approach is more effective on small dataset than the traditional methods.

17 April 2026
Verified
Conference Paper
Open access
XZXiaoyu Zhao
Xiaoyu Zhao
HBHongying Bai
Hongying Bai
YLYanping Li
Yanping Li
Elucidating lifespan trajectories of the relationship between brain structure and function is essential for understanding neurobiological aging. While prior work has largely emphasized correspondence between structural and functional connectivity, less is known about how macroscopic structural properties relate to whole brain functional activity across adulthood. Here, we applied constant block partial least squares correlation (PLSC) to quantify multivariate covariance between the mean gray matter volume of the default mode network derived from structural magnetic resonance imaging and voxel wise resting state functional activity derived from functional magnetic resonance imaging (fMRI). Analyses were performed in 280 healthy individuals aged 16 to 85 years from the NKI Rockland sample. We identified twelve statistically significant latent variables whose spatial patterns recapitulated canonical intrinsic networks, including default mode, auditory, dorsal attention, and sensorimotor systems. Importantly, individual brain scores indexing expression of these structure function covariance patterns exhibited a significant linear decline with advancing age, indicating a progressive attenuation of coordinated structure function coupling across adulthood. Collectively, these results provide a data driven characterization of macroscale structure function covariance over the adult lifespan and support a gradual uncoupling process that may constitute a key neural substrate of age related cognitive change.