Share：
Share this content in WeChat
X
[Chinese][PDF]6787
• Original Article •
Research on the recognition of brain functional connections in flight students based on multivariate pattern analysis
YE Lu  LIU Mengxuan  YAN Dongfeng  CHEN Xi  MA Shan 

Cite this article as: YE L, LIU M X, YAN D F, et al. Research on the recognition of brain functional connections in flight students based on multivariate pattern analysis[J]. Chin J Magn Reson Imaging, 2024, 15(2): 108-114. DOI:10.12015/issn.1674-8034.2024.02.016.


[Abstract] Objective Based on multivariate pattern analysis (MVPA), effectively identify the brain functional connections between flight cadets and healthy individuals.Materials and Methods Functional magnetic resonance data were collected from 40 licensed flight major students and 39 ground major students. The functional connectivity matrix was obtained through network functional connectivity analysis as a feature, and the feature dimensionality was reduced using the least absolute shrinkage and selection operator (LASSO) algorithm and independent sample t-test method, respectively. Support vector machines (SVM) with different kernel functions were used for training and prediction, and the performance of the model was evaluated using the left one cross validation method. Finally, the functional connections between corresponding brain regions were located based on the weight information in the trained SVM model.Results The linear kernel SVM model using LASSO feature screening had an accuracy of 81.82%, sensitivity of 82.05%, specificity of 81.58%, and area under the curve (AUC) of 0.88. The kernel function had little effect on the accuracy of the model. In the model, the right paracentral lobule, bilateral posterior central gyrus, bilateral inferior parietal angular gyrus, right fusiform gyrus, left orbital frontal gyrus, left superior parietal gyrus, and right orbital inferior frontal gyrus had higher weights. The weights in the model were concentrated in the somatomotor network (SMN) and default mode network (DMN), accounting for 25.62% and 25.27% of all weights, respectively.Conclusions SVM combined with LASSO algorithm for feature filtering can effectively recognize the brain of flight students, and has better interpretability and smaller overfitting. The weight information of the model reflects that flight students are mainly different from ordinary people in terms of motor and perceptual abilities.
[Keywords] flight cadets；magnetic resonance imaging；functional connectivity；minimum absolute contraction selection operator；support vector machine

YE Lu*   LIU Mengxuan   YAN Dongfeng   CHEN Xi   MA Shan  

Flight Technology College, Civil Aviation Flight University of China, Guanghan 618307, China

Corresponding author: YE L, E-mail: yelucafuc@163.com

Conflicts of interest   None.

Received  2023-09-20
Accepted  2024-01-21
DOI: 10.12015/issn.1674-8034.2024.02.016
Cite this article as: YE L, LIU M X, YAN D F, et al. Research on the recognition of brain functional connections in flight students based on multivariate pattern analysis[J]. Chin J Magn Reson Imaging, 2024, 15(2): 108-114. DOI:10.12015/issn.1674-8034.2024.02.016.

[1]
Civil Aviation Administration of China. Statistical bulletin on the development of the civil aviation industry in 2022[R/OL]. (2022-05-10) [2023-08-20]. http://www.caac.gov.cn/XXGK/XXGK/TJSJ/202305/t20230510_218565.html.2023.
[2]
CONSTANTINIDIS C, KLINGBERG T. The neuroscience of working memory capacity and training[J]. Nat Rev Neurosci, 2016, 17(7): 438-449. DOI: 10.1038/nrn.2016.43.
[3]
SILVERS JA, GUASSI MOREIRA JF. Capacity and tendency: A neuroscientific framework for the study of emotion regulation[J/OL]. Neurosci Lett, 2019, 693: 35-39 [2023-08-20]. https://www.sciencedirect.com/science/article/abs/pii/S0304394017307516. DOI: 10.1016/j.neulet.2017.09.017.
[4]
CHEN X, WANG Z A, JIANG H, et al. Flight training changes the brain functional pattern in cadets[J/OL]. Front Neurosci, 2023, 17: 1120628 [2023-08-20]. https://www.frontiersin.org/articles/10.3389/fnins.2023.1120628. DOI: 10.3389/fnins.2023.1120628.
[5]
CHEN X, XU K J, YANG Y, et al. Altered default mode network dynamics in civil aviation pilots[J/OL]. Front Neurosci, 2019, 13: 1406 [2023-08-20]. https://www.frontiersin.org/articles/10.3389/fnins.2019.01406. DOI: 10.3389/fnins.2019.01406.
[6]
XU K J, LIU R, CHEN X P, et al. Research on brain functions related to visual information processing and body coordination function of pilots based on the low-frequency amplitude method[J/OL]. Front Hum Neurosci, 2023, 17: 796526 [2023-08-20]. https://www.frontiersin.org/articles/10.3389/fnhum.2023.796526. DOI: 10.3389/fnhum.2023.796526.
[7]
CHEN X, WANG Q C, LUO C, et al. Increased functional dynamics in civil aviation pilots: evidence from a neuroimaging study[J/OL]. PLoS One, 2020, 15(6): e0234790 [2023-08-20]. https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0234790. DOI: 10.1371/journal.pone.0234790.
[8]
JIANG H, XU K J, CHEN X, et al. The neural underpinnings of emotional conflict control in pilots[J]. Aerosp Med Hum Perform, 2020, 91(10): 798-805. DOI: 10.3357/AMHP.5618.2020.
[9]
YANG Z, FANG F, WENG X C. Recent developments in multivariate pattern analysis for functional MRI[J]. Neurosci Bull, 2012, 28(4): 399-408. DOI: 10.1007/s12264-012-1253-3.
[10]
HALLER S, LOVBLAD K O, GIANNAKOPOULOS P, et al. Multivariate pattern recognition for diagnosis and prognosis in clinical neuroimaging: state of the art, current challenges and future trends[J]. Brain Topogr, 2014, 27(3): 329-337. DOI: 10.1007/s10548-014-0360-z.
[11]
TZOURIO-MAZOYER N, LANDEAU B, PAPATHANASSIOU D, et al. Automated anatomical labeling of activations in SPM using a macroscopic anatomical parcellation of the MNI MRI single-subject brain[J]. NeuroImage, 2002, 15(1): 273-289. DOI: 10.1006/nimg.2001.0978.
[12]
SUN Y K, ZHAO L, LAN Z H, et al. Differentiating boys with ADHD from those with typical development based on whole-brain functional connections using a machine learning approach[J/OL]. Neuropsychiatr Dis Treat, 2020, 16: 691-702 [2023-08-20]. https://www.dovepress.com/differentiating-boys-with-adhd-from-those-with-typical-development-bas-peer-reviewed-fulltext-article-NDT. DOI: 10.2147/NDT.S239013.
[13]
YAN B Y, XU X P, LIU M W, et al. Quantitative identification of major depression based on resting-state dynamic functional connectivity: a machine learning approach[J/OL]. Front Neurosci, 2020, 14: 191 [2023-08-20]. https://www.frontiersin.org/articles/10.3389/fnins.2020.00191. DOI: 10.3389/fnins.2020.00191.
[14]
BHADRA S, KUMAR C J. An insight into diagnosis of depression using machine learning techniques: a systematic review[J]. Curr Med Res Opin, 2022, 38(5): 749-771. DOI: 10.1080/03007995.2022.2038487.
[15]
STEARDO L, CARBONE E A, FILIPPIS R D, et al. Application of support vector machine on fMRI data as biomarkers in schizophrenia diagnosis: a systematic review[J/OL]. Front Psychiatry, 2020, 11: 588 [2023-08-20]. https://www.frontiersin.org/articles/10.3389/fpsyt.2020.00588. DOI: 10.3389/fpsyt.2020.00588.
[16]
LV Q, ZELJIC K, ZHAO S L, et al. Dissecting psychiatric heterogeneity and comorbidity with core region-based machine learning[J]. Neurosci Bull, 2023, 39(8): 1309-1326. DOI: 10.1007/s12264-023-01057-2.
[17]
ZHANG S, HU S E, SINHA R, et al. Cocaine dependence and thalamic functional connectivity: a multivariate pattern analysis[J/OL]. Neuroimage Clin, 2016, 12: 348-358 [2023-08-20]. https://pubmed.ncbi.nlm.nih.gov/27556009/. DOI: 10.1016/j.nicl.2016.08.006.
[18]
THOMAS YEO B T, KRIENEN F M, SEPULCRE J, et al. The organization of the human cerebral cortex estimated by intrinsic functional connectivity[J]. J Neurophysiol, 2011, 106(3): 1125-1165. DOI: 10.1152/jn.00338.2011.
[19]
TANVEER M, RICHHARIYA B, KHAN R U, et al. Machine learning techniques for the diagnosis of Alzheimer's disease: a review[J/OL]. ACM Trans Multimed Comput Commun Appl, 16(1s): 30 [2023-08-20]. https://dl.acm.org/doi/10.1145/3344998. DOI: 10.1145/3344998.
[20]
TIBSHIRANI R. Regression shrinkage and selection via the lasso: a retrospective[J]. J R Stat Soc Ser B Stat Methodol, 2011, 73(3): 273-282. DOI: 10.1111/j.1467-9868.2011.00771.x.
[21]
WANG Y Y, LU Y Z, DENG Y Q, et al. Predicting domain-specific actions in expert table tennis players activates the semantic brain network[J/OL]. NeuroImage, 2019, 200: 482-489 [2023-08-20]. https://pubmed.ncbi.nlm.nih.gov/31284027/. DOI: 10.1016/j.neuroimage.2019.06.035.
[22]
KIM J H, PARK J W, TAE W S, et al. Cerebral cortex changes in basketball players[J/OL]. J Korean Med Sci, 2022, 37(11): e86 [2023-08-20]. https://jkms.org/DOIx.php?id=10.3346/jkms.2022.37.e86. DOI: 10.3346/jkms.2022.37.e86.
[23]
BAKER C M, BURKS J D, BRIGGS R G, et al. A connectomic atlas of the human Cerebrum-chapter 3: the motor, premotor, and sensory cortices[J/OL]. Oper Neurosurg, 2018, 15(suppl_1): S75-S121 [2023-08-20]. https://journals.lww.com/onsonline/abstract/2018/12001/a_connectomic_atlas_of_the_human_cerebrum_chapter.3.aspx. DOI: 10.1093/ons/opy256.
[24]
BRUCHHAGE M M K, AMAD A, DRAPER S B, et al. Drum training induces long-term plasticity in the cerebellum and connected cortical thickness[J/OL]. Sci Rep, 2020, 10(1): 10116 [2023-08-20]. https://www.nature.com/articles/s41598-020-65877-2. DOI: 10.1038/s41598-020-65877-2.
[25]
FORNIA L, ROSSI M, RABUFFETTI M, et al. Motor impairment evoked by direct electrical stimulation of human parietal cortex during object manipulation[J/OL]. Neuroimage, 2022, 248: 118839 [2023-08-20]. https://linkinghub.elsevier.com/retrieve/pii/S1053811921011101. DOI: 10.1016/j.neuroimage.2021.118839.
[26]
GALE D J, FLANAGAN J R, GALLIVAN J P. Human somatosensory cortex is modulated during motor planning[J]. J Neurosci, 2021, 41(27): 5909-5922. DOI: 10.1523/JNEUROSCI.0342-21.2021.
[27]
CORAY R C, ZIMMERMANN J, HAUGG A, et al. The functional connectome of 3, 4-methyldioxymethamphetamine-related declarative memory impairments[J]. Hum Brain Mapp, 2023, 44(15): 5079-5094. DOI: 10.1002/hbm.26438.
[28]
LIU Q Q, LI W B, SONG Y W, et al. Correlation between focal lesion sites and language deficits in the acute phase of post-stroke aphasia[J]. Folia Neuropathol, 2022, 60(1): 60-68. DOI: 10.5114/fn.2022.114343.
[29]
GIAMPICCOLO D, DUFFAU H. Controversy over the temporal cortical terminations of the left arcuate fasciculus: a reappraisal[J]. Brain, 2022, 145(4): 1242-1256. DOI: 10.1093/brain/awac057.
[30]
MORET-TATAY C, BAIXAULI FORTEA I, GRAU SEVILLA M D. Challenges and insights for the visual system: are face and word recognition two sides of the same coin?[J/OL]. J Neurolinguistics, 2020, 56: 100941 [2023-08-20]. https://www.sciencedirect.com/science/article/abs/pii/S0911604420301019. DOI: 10.1016/j.jneuroling.2020.100941.
[31]
LIU J H, SPAGNA A, BARTOLOMEO P. Hemispheric asymmetries in visual mental imagery[J]. Brain Struct Funct, 2022, 227(2): 697-708. DOI: 10.1007/s00429-021-02277-w.
[32]
CAO D, LIU Q H, ZHANG J Q, et al. State-specific modulation of mood using intracranial electrical stimulation of the orbitofrontal cortex[J]. Brain Stimul, 2023, 16(4): 1112-1122. DOI: 10.1016/j.brs.2023.07.049.
[33]
FASANO M C, CABRAL J, STEVNER A, et al. The early adolescent brain on music: analysis of functional dynamics reveals engagement of orbitofrontal cortex reward system[J]. Hum Brain Mapp, 2023, 44(2): 429-446. DOI: 10.1002/hbm.26060.
[34]
WONG W W, CABRAL J, RANE R, et al. Effects of visual attention modulation on dynamic functional connectivity during own-face viewing in body dysmorphic disorder[J]. Neuropsychopharmacology, 2021, 46(11): 2030-2038. DOI: 10.1038/s41386-021-01039-w.
[35]
DUGRÉ J R, POTVIN S. Impaired attentional and socio-affective networks in subjects with antisocial behaviors: a meta-analysis of resting-state functional connectivity studies[J]. Psychol Med, 2021, 51(8): 1249-1259. DOI: 10.1017/S0033291721001525.
[36]
PASSARELLI L, GAMBERINI M, FATTORI P. The superior parietal lobule of Primates: a sensory-motor hub for interaction with the environment[J]. J Integr Neurosci, 2021, 20(1): 157-171. DOI: 10.31083/j.jin.2021.01.334.
[37]
GRAY O, FRY L, MONTALDI D. Information content best characterises the hemispheric selectivity of the inferior parietal lobe: a meta-analysis[J/OL]. Sci Rep, 2020, 10(1): 15112 [2023-08-20]. https://www.nature.com/articles/s41598-020-72228-8. DOI: 10.1038/s41598-020-72228-8.
[38]
SUN J Z, HE L, CHEN Q L, et al. The bright side and dark side of daydreaming predict creativity together through brain functional connectivity[J]. Hum Brain Mapp, 2022, 43(3): 902-914. DOI: 10.1002/hbm.25693.

PREV Predicting the occurrence of knee osteoarthritis based on MRI meniscus 3D convolutional neural network model
NEXT Processing of Chinese linguistic and prosodic signals in dichotic listening conditions: A fMRI study
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn