publications | Jiaxin \(Cindy\) Tu

2025

Deep-learning based Embedding of Functional Connectivity Profiles for Precision Functional Mapping

Jiaxin C. Tu, Jung-Hoon Kim, Patrick H. Luckett, and 5 more authors

Jan 2025

Pages: 2025.01.29.635570 Section: New Results

Abs

Spatial correlation of functional connectivity profiles across matching anatomical locations in individuals is often calculated to delineate individual differences in functional networks. Likewise, spatial correlation is assessed across average functional connectivity profiles of groups to evaluate the maturity of functional networks during development. Despite its widespread use, spatial correlation is limited to comparing two samples at a time. In this study, we employed a variational autoencoder to embed functional connectivity profiles from various anatomical locations, individuals, and group averages for simultaneous comparison. We demonstrate that our variational autoencoder, with pre-trained weights, can project new functional connectivity profiles from the vertex space to a latent space with as few as two dimensions, yet still retain meaningful global and local structures in the data. Functional connectivity profiles from various functional networks occupy distinct compartments of the latent space. Moreover, the variability of functional connectivity profiles from the same anatomical location is readily captured in the latent space. We believe that this approach could be useful for visualization and exploratory analyses in precision functional mapping.
A Subset of Cortical Areas Exhibit Adult-like Functional Network Patterns in Early Childhood

Jiaxin Cindy Tu, Yu Wang, Xintian Wang, and 7 more authors

Developmental Cognitive Neuroscience, Jan 2025

Publisher: Elsevier

2024

Functional parcellation of the neonatal cortical surface

Michael J Myers, Alyssa K Labonte, Evan M Gordon, and 16 more authors

Cerebral Cortex, Feb 2024

Abs

The cerebral cortex is organized into distinct but interconnected cortical areas, which can be defined by abrupt differences in patterns of resting state functional connectivity (FC) across the cortical surface. Such parcellations of the cortex have been derived in adults and older infants, but there is no widely used surface parcellation available for the neonatal brain. Here, we first demonstrate that existing parcellations, including surface-based parcels derived from older samples as well as volume-based neonatal parcels, are a poor fit for neonatal surface data. We next derive a set of 283 cortical surface parcels from a sample of n = 261 neonates. These parcels have highly homogenous FC patterns and are validated using three external neonatal datasets. The Infomap algorithm is used to assign functional network identities to each parcel, and derived networks are consistent with prior work in neonates. The proposed parcellation may represent neonatal cortical areas and provides a powerful tool for neonatal neuroimaging studies.
Network-level enrichment provides a framework for biological interpretation of machine learning results

Jiaqi Li, Ari Segel, Xinyang Feng, and 8 more authors

Network Neuroscience, Jul 2024

Abs

Machine learning algorithms are increasingly being utilized to identify brain connectivity biomarkers linked to behavioral and clinical outcomes. However, research often prioritizes prediction accuracy at the expense of biological interpretability, and inconsistent implementation of ML methods may hinder model accuracy. To address this, our paper introduces a network-level enrichment approach, which integrates brain system organization in the context of connectome-wide statistical analysis to reveal network-level links between brain connectivity and behavior. To demonstrate the efficacy of this approach, we used linear support vector regression (LSVR) models to examine the relationship between resting-state functional connectivity networks and chronological age. We compared network-level associations based on raw LSVR weights to those produced from the forward and inverse models. Results indicated that not accounting for shared family variance inflated prediction performance, the k-best feature selection via Pearson correlation reduced accuracy and reliability, and raw LSVR model weights produced network-level associations that deviated from the significant brain systems identified by forward and inverse models. Our findings offer crucial insights for applying machine learning to neuroimaging data, emphasizing the value of network enrichment for biological interpretation.
Increasing hub disruption parallels dementia severity in autosomal dominant Alzheimer disease

Jiaxin Cindy Tu, Peter R Millar, Jeremy F Strain, and 8 more authors

Network Neuroscience, Jul 2024

Publisher: MIT Press 255 Main Street, 9th Floor, Cambridge, Massachusetts 02142, USA …

2023

Brain network decoupling with increased serum neurofilament and reduced cognitive function in Alzheimer’s disease

Muriah D Wheelock, Jeremy F Strain, Patricia Mansfield, and 164 more authors

Brain, Jan 2023

Abs

Abstract Neurofilament light chain, a putative measure of neuronal damage, is measurable in blood and CSF and is predictive of cognitive function in individuals with Alzheimer’s disease. There has been limited prior work linking neurofilament light and functional connectivity, and no prior work has investigated neurofilament light associations with functional connectivity in autosomal dominant Alzheimer’s disease. Here, we assessed relationships between blood neurofilament light, cognition, and functional connectivity in a cross-sectional sample of 106 autosomal dominant Alzheimer’s disease mutation carriers and 76 non-carriers. We employed an innovative network-level enrichment analysis approach to assess connectome-wide associations with neurofilament light. Neurofilament light was positively correlated with deterioration of functional connectivity within the default mode network and negatively correlated with connectivity between default mode network and executive control networks, including the cingulo-opercular, salience, and dorsal attention networks. Further, reduced connectivity within the default mode network and between the default mode network and executive control networks was associated with reduced cognitive function. Hierarchical regression analysis revealed that neurofilament levels and functional connectivity within the default mode network and between the default mode network and the dorsal attention network explained significant variance in cognitive composite scores when controlling for age, sex, and education. A mediation analysis demonstrated that functional connectivity within the default mode network and between the default mode network and dorsal attention network partially mediated the relationship between blood neurofilament light levels and cognitive function. Our novel results indicate that blood estimates of neurofilament levels correspond to direct measurements of brain dysfunction, shedding new light on the underlying biological processes of Alzheimer’s disease. Further, we demonstrate how variation within key brain systems can partially mediate the negative effects of heightened total serum neurofilament levels, suggesting potential regions for targeted interventions. Finally, our results lend further evidence that low-cost and minimally invasive blood measurements of neurofilament may be a useful marker of brain functional connectivity and cognitive decline in Alzheimer’s disease.
Developing and benchmarking functional parcellations in infant neuroimaging datasets

Jiaxin Cindy Tu, Michael Myers, Chad Sylvester, and 17 more authors

In , Jun 2023
Development of functional systems in 0–2-year-olds

Jiaxin Cindy Tu, Michael Myers, Chad Sylvester, and 8 more authors

In Flux: The society for developmental cognitive neuroscience, Jun 2023
Effects of functional network model definition on biomarker outcome prediction

Xinyang Feng, Jiaqi Li, Ari Segel, and 8 more authors

In Organization for human brain mapping, Jun 2023

2021

Multicentric tracking of multiple agents by anterior cingulate cortex during pursuit and evasion

Seng Bum Michael Yoo, Jiaxin Cindy Tu, and Benjamin Yost Hayden

Nature Communications, Mar 2021

Number: 1 Publisher: Nature Publishing Group

Abs

Successful pursuit and evasion require rapid and precise coordination of navigation with adaptive motor control. We hypothesize that the dorsal anterior cingulate cortex (dACC), which communicates bidirectionally with both the hippocampal complex and premotor/motor areas, would serve a mapping role in this process. We recorded responses of dACC ensembles in two macaques performing a joystick-controlled continuous pursuit/evasion task. We find that dACC carries two sets of signals, (1) world-centric variables that together form a representation of the position and velocity of all relevant agents (self, prey, and predator) in the virtual world, and (2) avatar-centric variables, i.e. self-prey distance and angle. Both sets of variables are multiplexed within an overlapping set of neurons. Our results suggest that dACC may contribute to pursuit and evasion by computing and continuously updating a multicentric representation of the unfolding task state, and support the hypothesis that it plays a high-level abstract role in the control of behavior.

2020

The neural basis of predictive pursuit

Seng Bum Michael Yoo, Jiaxin Cindy Tu, Steven T. Piantadosi, and 1 more author

Nature Neuroscience, Feb 2020
Rules warp feature encoding in decision-making circuits

R Becket Ebitz, Jiaxin Cindy Tu, and Benjamin Y Hayden

PLoS biology, Feb 2020

Publisher: Public Library of Science

2019

Ventromedial prefrontal cortex tracks multiple environmental variables during search

Priyanka S Mehta, Jiaxin Cindy Tu, Giuliana A LoConte, and 2 more authors

Journal of Neuroscience, Feb 2019

Publisher: Soc Neuroscience

2018

Neural representation of allocentric and egocentric positions in a dynamic foraging task

Jiaxin Tu, Seng Bum Yoo, and Ben Yost Hayden

In Society for neuroscience poster, Feb 2018

2017

Understanding Drosophila navigation using visual and olfactory cues

Jiaxin Tu, and Trevor J. Wardill

Feb 2017