NeuroMark: an adaptive independent component analysis framework for estimating reproducible and comparable fMRI biomarkers among brain disorders

Published on Oct 16, 2019in medRxiv
路 DOI :10.1101/19008631
Yuhui Du15
Estimated H-index: 15
(Shanxi University),
Zening Fu8
Estimated H-index: 8
(Georgia Institute of Technology)
+ 11 AuthorsVince D. Calhoun93
Estimated H-index: 93
(Georgia Institute of Technology)
Increasing data-sharing initiatives have provided unprecedented opportunities to study brain disorders. Standardized approaches for capturing reproducible and comparable biomarkers are greatly needed in big-data analysis. Here, we propose a framework (called NeuroMark) that leverages a priori-driven independent component analysis (ICA) to extract functional brain network features from fMRI data. NeuroMark estimates features adaptable to each individual and comparable across subjects by taking advantage of the replicated brain network templates extracted from 1828 healthy controls. Four studies including 2454 subjects were conducted, spanning six brain disorders (schizophrenia, autism spectrum disorder, depression, bipolar disorder, mild cognitive impairment and Alzheimer9s disease) to evaluate the proposed framework from different perspectives (replication, cross-study comparison, subtle difference identification, and multi-disorder classification). Our results demonstrate the great potential of NeuroMark to identify reproducible and comparable brain network markers, its feasibility to link results across different datasets/studies/disorders, and its sensitivity in identifying biomarkers for patients with challenging mental illnesses.
  • References (0)
  • Citations (1)
馃摉 Papers frequently viewed together
138 Citations
7 Citations
5 Citations
78% of Scinapse members use related papers. After signing in, all features are FREE.
Cited By1
#1Debbrata Kumar Saha (Georgia Institute of Technology)
#2Vince D. CalhounH-Index: 93
Last. Sergey M. Plis (Georgia Institute of Technology)H-Index: 2
view all 6 authors...
Visualization of high dimensional large-scale datasets via an embedding into a 2D map is a powerful exploration tool for assessing latent structure in the data and detecting outliers. It plays a vital role in neuroimaging field because sometimes it is the only way to perform quality control of large dataset. There are many methods developed to perform this task but most of them rely on the assumption that all samples are locally available for the computation. Specifically, one needs access to al...