Two-Step Feature Selection for Identifying Developmental Differences in Resting fMRI Intrinsic Connectivity Networks
Source abstract
Abstract
Functional connectivity derived from functional magnetic resonance imaging (fMRI) is used as an effective way to assess brain architecture. There has been a growing interest in its application to the study of intrinsic connectivity networks (ICNs) during different brain development stages. fMRI data are of high dimension but small sample size, and it is crucial to perform dimension reduction before pattern analysis of ICNs. Feature selection is thus used to reduce redundancy, lower the complexity of learning, and enhance the interpretability. To study the varying patterns of ICNs in different brain development stages, we propose a two-step feature selection method. First, an improved support vector machine based recursive feature elimination method is utilized to study the differences of connectivity during development. To further reduce the highly correlated features, a combination of F-score and correlation score is applied. This method was then applied to analysis of the Philadelphia Neurodevelopmental Cohort (PNC) data. The two-step feature selection was randomly performed 20 times, and those features that showed up consistently in the experiments were chosen as the essential ICN differences between different brain ages. Our results indicate that ICN differences exist in brain development, and they are related to task control, cognition, information processing, attention, and other brain functions. In particular, compared with children, young adults exhibit increasing functional connectivity in the sensory/somatomotor network, cingulo-opercular task control network, visual network, and some other subnetworks. In addition, the connectivity in young adults decreases between the default mode network and other subnetworks such as the fronto-parietal task control network. The results are coincident with the fact that the connectivity within the brain alters from segregation to integration as an individual grows.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Functional Brain Connectivity Studies · Advanced Neuroimaging Techniques and Applications · Neural dynamics and brain function
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Mathematics and Statistics, Xi’an Jiaotong University, Xi’an 710049, China
Tri-institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS), Georgia State University, Georgia Institute of Technology, and Emory University, Atlanta, GA 30303, USA
Department of Biomedical Engineering, Tulane University, New Orleans, LA 70112, USA
Funding
National Natural Science Foundation of China
References (59)
Show source-provided references
1. Application of graph theory to assess static and dynamic brain connectivity: Approaches for building brain graphs10.1109/JPROC.2018.2825200 ↗
2. Lawrence, S.J.D., Formisano, E., Muckli, L., and De Lange, F.P. (2017). Laminar fMRI: Applications for cognitive neuroscience. Neuroimage.
3. Quantitative positron emission tomography in brain research10.1016/j.brainres.2017.06.022 ↗
4. Functional connectivity in the motor cortex of resting human brain using echo-planar MRI10.1002/mrm.1910340409 ↗
5. Changes in structural and functional connectivity among resting-state networks across the human lifespan10.1016/j.neuroimage.2014.07.067 ↗
6. State-space model with deep learning for functional dynamics estimation in resting-state fMRI10.1016/j.neuroimage.2016.01.005 ↗
7. Functional connectome fingerprinting: Identifying individuals using patterns of brain connectivity10.1038/nn.4135 ↗
8. Reduced higher-dimensional resting state fMRI dynamism in clinical high-risk individuals for schizophrenia identified by meta-state analysis10.1016/j.schres.2018.06.007 ↗
9. The chronnectome: Time-varying connectivity networks as the next frontier in fMRI data discovery10.1016/j.neuron.2014.10.015 ↗
10. The connectomics of brain disorders10.1038/nrn3901 ↗
11. Methods and considerations for dynamic analysis of functional MR imaging data10.1016/j.nic.2017.06.009 ↗
12. The dynamic functional connectome: State-of-the-art and perspectives10.1016/j.neuroimage.2016.12.061 ↗
13. Can sliding-window correlations reveal dynamic functional connectivity in resting-state fMRI?10.1016/j.neuroimage.2015.11.055 ↗
14. Evaluation of sliding window correlation performance for characterizing dynamic functional connectivity and brain states10.1016/j.neuroimage.2016.02.074 ↗
15. Dynamic functional connectivity impairments in early schizophrenia and clinical high-risk for psychosis10.1016/j.neuroimage.2017.10.022 ↗
16. Tracking whole-brain connectivity dynamics in the resting state10.1093/cercor/bhs352 ↗
17. Identifying sparse connectivity patterns in the brain using resting-state fMRI10.1016/j.neuroimage.2014.09.058 ↗
18. The geometry of correlation fields with an application to functional connectivity of the brain10.1214/aoap/1029962864 ↗
19. Brain connectivity networks in schizophrenia underlying resting state functional magnetic resonance imaging10.2174/156802612805289890 ↗
20. Deep ensemble learning of sparse regression models for brain disease diagnosis10.1016/j.media.2017.01.008 ↗
21. Discriminating Bipolar Disorder from Major Depression using Whole-Brain Functional Connectivity: A Feature Selection Analysis with SVM-FoBa Algorithm10.1007/s11265-016-1159-9 ↗
22. Qiao, C., Lu, L., Yang, L., and Kennedy, P.J. (2019). Identifying Brain Abnormalities with Schizophrenia Based on a Hybrid Feature Selection Technology. Appl. Sci., 9.10.3390/app9102148 ↗
23. Chandrashekar, G., and Sahin, F. (2014). A Survey on Feature Selection Methods, Pergamon Press, Inc.10.1016/j.compeleceng.2013.11.024 ↗
24. Classification and Prediction of Brain Disorders Using Functional Connectivity: Promising but Challenging10.3389/fnins.2018.00525 ↗
25. Kuncheva, L.I. (2014). Ensemble Feature Selection. Combining Pattern Classifiers: Methods and Algorithms, John Wiley & Sons. [2nd ed.].10.1002/9781118914564 ↗
26. Estimation of dynamic sparse connectivity patterns from resting state fMRI10.1109/TMI.2017.2786553 ↗
27. Fused estimation of sparse connectivity patterns from rest fMRI: Application to comparison of children and adult brains10.1109/TMI.2017.2721640 ↗
28. The development of hub architecture in the human functional brain network10.1093/cercor/bhs227 ↗
29. Functional network organization of the human brain10.1016/j.neuron.2011.09.006 ↗
30. A parcellation scheme for human left lateral parietal cortex10.1016/j.neuron.2010.05.025 ↗
31. Defining functional areas in individual human brains using resting functional connectivity MRI10.1016/j.neuroimage.2008.01.066 ↗
32. Accurate in silico identification of species-specific acetylation sites by integrating protein sequence-derived and functional features10.1038/srep05765 ↗
33. A comprehensive study of whole-brain functional connectivity in children and young adults10.1093/cercor/bhq104 ↗
34. Tracking the brains functional coupling dynamics over development10.1523/JNEUROSCI.4638-14.2015 ↗
35. Connectomics and epilepsy10.1097/WCO.0b013e32835ee5b8 ↗
36. Default-mode brain dysfunction in mental disorders: A systematic review10.1016/j.neubiorev.2008.09.002 ↗
37. Connectivity gradients between the default mode and attention control networks10.1089/brain.2011.0007 ↗
38. The teen brain: Insights from neuroimaging10.1016/j.jadohealth.2008.01.007 ↗
39. Gene selection for cancer classification using support vector machines10.1023/A:1012487302797 ↗
40. MSVM-RFE: Extensions of SVM-RFE for multiclass gene selection on DNA microarray data10.1093/bioinformatics/btm036 ↗
41. Feature selection and analysis on correlated gas sensor data with recursive feature 536 elimination10.1016/j.snb.2015.02.025 ↗
42. SVMRFE based approach for prediction of most discriminatory gene target for type II diabetes10.1016/j.gdata.2017.02.008 ↗
43. An Introduction to Variable and Feature Selection
44. Dao, F.Y., Lv, H., Wang, F., Feng, C.Q., Ding, H., Chen, W., and Lin, H. (2018). Identify origin of replication in Saccharomyces cerevisiae using two-step feature selection technique. Bioinformatics.10.1093/bioinformatics/bty943 ↗
45. The philadelphia neurodevelopmental cohort: A publicly available resource for the study of normal and abnormal brain development in youth10.1016/j.neuroimage.2015.03.056 ↗
46. Chiang, S., Vankov, E.R., Yeh, H.J., Guindani, M., Vannucci, M., Haneef, Z., and Stern, J. (2018). Temporal and spectral characteristics of dynamic functional connectivity between resting-state networks reveal information beyond static connectivity. PLoS ONE, 13.10.1371/journal.pone.0190220 ↗
47. Dynamic functional connectivity of neurocognitive networks in children10.1002/hbm.23346 ↗
48. Dynamic functional connectivity analysis reveals transient states of dysconnectivity in schizophrenia10.1016/j.nicl.2014.07.003 ↗
49. Decoding subject-driven cognitive states with whole-brain connectivity patterns10.1093/cercor/bhr099 ↗
50. Correspondence of the brain’s functional architecture during activation and rest10.1073/pnas.0905267106 ↗
51. Network modelling methods for fMRI10.1016/j.neuroimage.2010.08.063 ↗
52. Mingrui, X., Jinhui, W., and Yong, H. (2013). BrainNet viewer: A network visualization tool for human brain connectomics. PLoS ONE, 8.10.1371/journal.pone.0068910 ↗
53. Functional brain networks and cognitive deficits in Parkinson’s disease10.1002/hbm.22499 ↗
54. Disrupted functional brain connectome in individuals at risk for Alzheimer’s disease10.1016/j.biopsych.2012.03.026 ↗
55. Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy10.1109/TPAMI.2005.159 ↗
56. Menze, B.H., Kelm, M.B., Masuch, R., Himmelreich, U., Bachert, P., Petrich, W., and Hamprecht, F.A. (2009). A comparison of random forest and its Gini importance with standard chemometric methods for the feature selection and classification of spectral data. BMC Bioinform., 10.10.1186/1471-2105-10-213 ↗
57. Sensory-motor brain network connectivity for speech comprehension10.1002/hbm.20888 ↗
58. Fronto-parietal and cingulo-opercular network interity and cognition in health and schizophrenia10.1016/j.neuropsychologia.2015.05.006 ↗
59. A review of fronto-striatal and fronto-cortical brain abnormalities in children and adults with Attention Deficit Hyperactivity Disorder (ADHD) and new evidence for dysfunction in adults with ADHD during motivation and attention10.1016/j.cortex.2011.04.007 ↗