Individual Functional Topography Severed as Fingerprint in Alzheimer's disease
Poster No:
1407
Submission Type:
Abstract Submission
Authors:
Pindong Chen1,2, Rongshen Zhou1, Kun Zhao1, Timothy Rittman3, Yong Liu1
Institutions:
1Beijing University of Posts and Telecommunications, Beijing, China, 2Brainnetome Center & National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China, 3University of Cambridge, Cambridge, United Kingdom
First Author:
Pindong Chen
Beijing University of Posts and Telecommunications|Brainnetome Center & National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
Beijing, China|Beijing, China
Beijing University of Posts and Telecommunications|Brainnetome Center & National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
Beijing, China|Beijing, China
Co-Author(s):
Introduction:
Alzheimer's disease (AD) is a neurodegeneration disease associated with widespread disruptions in functional networks (Dai & He, 2014; Liu et al., 2014). The brain's functional systems are organized into topographic distributed functional networks that support human cognitive functions (Yeo et al., 2011). Increasing studies show that this functional topography is substantially different between individuals, with relevance to cognition and disease (Glasser et al., 2016; Gordon et al., 2017; Kong et al., 2019; Laumann et al., 2015; Wang et al., 2015), suggesting the importance of functional networks for disease mechanism understanding (Dai & He, 2014; Eyler et al., 2019; Liu et al., 2014). Modeling the hierarchical structure of the brain into distinct functional systems offers insights into the mechanisms underlying brain organization and cognitive process. However, this approach often overlooks the heterogeneity in individual functional topography, restricting precise investigation on functional topographic organization. Therefore, we investigated the inter-subject variability of functional topography to assess underlying functional organization changes in AD.
Methods:
Structural MRI and resting-state fMRI scans were acquired from an in-house database for discovery experiments, including 257 normal controls (NCs), 257 participants with mild cognitive impairment (MCI) and 295 patients with AD. 263 NCs and 84 ADs from Alzheimer's Disease Neuroimaging Initiative (ADNI) formed a validation cohort. The images of sMRI and fMRI were preprocessed using fmriprep (Esteban et al., 2019).
We generated individualized functional networks by using the iteration-based methods developed by Wang (Fig. 1A) (Wang et al., 2015). Specifically, we began with 18 functional networks derived from Yeo networks and an additional hand sensorimotor network (Yeo et al., 2011). We assigned each vertex to a functional network according to Pearson correlation, temporal Signal-to-Noise Ratio (tSNR) and pre-defined variability. This process was performed 10 times to achieve convergence. Individual variability was calculated through the entropy across subjects in each vertex. Second, the homogeneity within a functional network is calculated as the Pearson correlation between the mean time series and each vertex. Third, we investigated the individual identification rate (IDR) of functional topography by using two visits for each participants from longitudinal data in ADNI, aiming to validate whether it could serve as a fingerprint to recognise subjects. Finally, support vector regression was used to classify the AD patients based on functional topography to validate the disease relevance of the individualized functional networks. Those prediction tasks were performed in a randomly repeated five-fold cross-validation with 1000 repetitions.
We generated individualized functional networks by using the iteration-based methods developed by Wang (Fig. 1A) (Wang et al., 2015). Specifically, we began with 18 functional networks derived from Yeo networks and an additional hand sensorimotor network (Yeo et al., 2011). We assigned each vertex to a functional network according to Pearson correlation, temporal Signal-to-Noise Ratio (tSNR) and pre-defined variability. This process was performed 10 times to achieve convergence. Individual variability was calculated through the entropy across subjects in each vertex. Second, the homogeneity within a functional network is calculated as the Pearson correlation between the mean time series and each vertex. Third, we investigated the individual identification rate (IDR) of functional topography by using two visits for each participants from longitudinal data in ADNI, aiming to validate whether it could serve as a fingerprint to recognise subjects. Finally, support vector regression was used to classify the AD patients based on functional topography to validate the disease relevance of the individualized functional networks. Those prediction tasks were performed in a randomly repeated five-fold cross-validation with 1000 repetitions.
·Fig1
Results:
NC, MCI and AD groups had very similar group-average functional networks, while large heterogeneity was seen in individual-level functional network topography (Fig. 1B-C). AD had greater inter-individual variability in functional networks across subjects (Fig.1D). Furthermore, the individualized method improved homogeneity within functional networks (Fig. 2A). The functional topography showed significant performance in individual identification in both NC and AD (Fig 2B). Then, machine learning results showed that individualized functional networks demonstrate significant diagnostic performance (P < 0.05, except for network 10) (Fig. 2C). Interesting, the performance of AD classification is significantly associated with the change of functional topography variability in AD (Fig 2D).
·Fig2
Conclusions:
In conclusion, patients with AD had higher inter-individual variability in functional networks, and that variability carry both individual and disease information, showing potential use for future precision medicine.
Disorders of the Nervous System:
Neurodegenerative/ Late Life (eg. Parkinson’s, Alzheimer’s) 2
Modeling and Analysis Methods:
Classification and Predictive Modeling
fMRI Connectivity and Network Modeling 1
Neuroanatomy, Physiology, Metabolism and Neurotransmission:
Cortical Anatomy and Brain Mapping
Novel Imaging Acquisition Methods:
BOLD fMRI
Keywords:
Cognition
Degenerative Disease
FUNCTIONAL MRI
Machine Learning
MRI
1|2Indicates the priority used for review
Abstract Information
By submitting your proposal, you grant permission for the Organization for Human Brain Mapping (OHBM) to distribute your work in any format, including video, audio print and electronic text through OHBM OnDemand, social media channels, the OHBM website, or other electronic publications and media.
The Open Science Special Interest Group (OSSIG) is introducing a reproducibility challenge for OHBM 2025. This new initiative aims to enhance the reproducibility of scientific results and foster collaborations between labs. Teams will consist of a “source” party and a “reproducing” party, and will be evaluated on the success of their replication, the openness of the source work, and additional deliverables. Click here for more information. Propose your OHBM abstract(s) as source work for future OHBM meetings by selecting one of the following options:
Please indicate below if your study was a "resting state" or "task-activation” study.
Healthy subjects only or patients (note that patient studies may also involve healthy subjects):
Was this research conducted in the United States?
Were any human subjects research approved by the relevant Institutional Review Board or ethics panel? NOTE: Any human subjects studies without IRB approval will be automatically rejected.
Were any animal research approved by the relevant IACUC or other animal research panel? NOTE: Any animal studies without IACUC approval will be automatically rejected.
Please indicate which methods were used in your research:
For human MRI, what field strength scanner do you use?
Provide references using APA citation style.
Esteban, O., Markiewicz, C. J., Blair, R. W., Moodie, C. A., Isik, A. I., Erramuzpe, A., . . . Gorgolewski, K. J. (2019). fMRIPrep: a robust preprocessing pipeline for functional MRI. Nat Methods, 16(1), 111-116. doi:10.1038/s41592-018-0235-4
Eyler, L. T., Elman, J. A., Hatton, S. N., Gough, S., Mischel, A. K., Hagler, D. J., . . . Kremen, W. S. (2019). Resting State Abnormalities of the Default Mode Network in Mild Cognitive Impairment: A Systematic Review and Meta-Analysis. J Alzheimers Dis, 70(1), 107-120. doi:10.3233/JAD-180847
Glasser, M. F., Coalson, T. S., Robinson, E. C., Hacker, C. D., Harwell, J., Yacoub, E., . . . Van Essen, D. C. (2016). A multi-modal parcellation of human cerebral cortex. Nature, 536(7615), 171-178. doi:10.1038/nature18933
Gordon, E. M., Laumann, T. O., Gilmore, A. W., Newbold, D. J., Greene, D. J., Berg, J. J., . . . Dosenbach, N. U. F. (2017). Precision Functional Mapping of Individual Human Brains. Neuron, 95(4), 791-807 e797. doi:10.1016/j.neuron.2017.07.011
Kong, R., Li, J., Orban, C., Sabuncu, M. R., Liu, H., Schaefer, A., . . . Yeo, B. T. T. (2019). Spatial Topography of Individual-Specific Cortical Networks Predicts Human Cognition, Personality, and Emotion. Cereb Cortex, 29(6), 2533-2551. doi:10.1093/cercor/bhy123
Laumann, T. O., Gordon, E. M., Adeyemo, B., Snyder, A. Z., Joo, S. J., Chen, M. Y., . . . Petersen, S. E. (2015). Functional System and Areal Organization of a Highly Sampled Individual Human Brain. Neuron, 87(3), 657-670. doi:10.1016/j.neuron.2015.06.037
Liu, Y., Yu, C., Zhang, X., Liu, J., Duan, Y., Alexander-Bloch, A. F., . . . Bullmore, E. (2014). Impaired long distance functional connectivity and weighted network architecture in Alzheimer's disease. Cereb Cortex, 24(6), 1422-1435. doi:10.1093/cercor/bhs410
Wang, D., Buckner, R. L., Fox, M. D., Holt, D. J., Holmes, A. J., Stoecklein, S., . . . Liu, H. (2015). Parcellating cortical functional networks in individuals. Nat Neurosci, 18(12), 1853-1860. doi:10.1038/nn.4164
Yeo, B. T., Krienen, F. M., Sepulcre, J., Sabuncu, M. R., Lashkari, D., Hollinshead, M., . . . Buckner, R. L. (2011). The organization of the human cerebral cortex estimated by intrinsic functional connectivity. J Neurophysiol, 106(3), 1125-1165. doi:10.1152/jn.00338.2011