On most informative regions for binary classification of schizophrenia based on resting state fMRI data done by selection of functionally homogeneous regions method

Cover Page

Cite item

Full Text

Open Access Open Access
Restricted Access Access granted
Restricted Access Subscription Access

Abstract

In this work we solve the problem of automatic binary classification of subjects with a diagnosis of schizophrenia and control groups on a data set obtained on a Siemens 3T tomograph. The data set included 36 subjects undergoing treatment at Psychiatric Hospital no. 1 Named after N.A. Alexeev of the Department of Health of Moscow (GBUZ PKB No. 1 DZM) and 36 subjects from the control group. Machine learning methods were used to solve this problem. As a result, an accuracy of 76% was achieved, which corresponds to the results obtained in other scientific studies. The highest accuracy was obtained for the local homogeneity parameter (regional homogeneity – ReHo), already known in the literature. At the same time, the set of features developed by the authors based on the method for identifying functionally homogeneous regions (FHR) gave a classification accuracy of 74%. But at the same time, the set of FHR features provides higher classification accuracy when using a small number of brain regions. For example, already in 8 regions, the FHR set provided an almost maximum classification accuracy of 72.5% (versus 65% for the ReHo set), which suggests that it is the selected 8 regions that give the highest level of separation.

Full Text

Restricted Access

About the authors

A. D. Zhemchuzhnikov

Kurchatov Institute

Email: Poyda_AA@nrcki.ru
Russian Federation, Moscow

S. I. Kartashov

Kurchatov Institute

Email: Poyda_AA@nrcki.ru
Russian Federation, Moscow

S. O. Kozlov

Kurchatov Institute

Email: Poyda_AA@nrcki.ru
Russian Federation, Moscow

V. A. Orlov

Kurchatov Institute

Email: Poyda_AA@nrcki.ru
Russian Federation, Moscow

A. A. Poyda

Kurchatov Institute

Author for correspondence.
Email: Poyda_AA@nrcki.ru
Russian Federation, Moscow

N. V. Zakharova

Samara State Medical University; V.M. Bekhterev National Research Medical Center for Psychiatry and Neurology

Email: Poyda_AA@nrcki.ru
Russian Federation, Samara; Saint Petersburg

L. V. Bravve

Psychiatric Hospital No. 1 named after N.A. Alexeev of the Department of Health of Moscow

Email: Poyda_AA@nrcki.ru
Russian Federation, Moscow

G. Sh. Mamedova

Psychiatric Hospital No. 1 named after N.A. Alexeev of the Department of Health of Moscow

Email: Poyda_AA@nrcki.ru
Russian Federation, Moscow

M. A. Kaydan

Psychiatric Hospital No. 1 named after N.A. Alexeev of the Department of Health of Moscow

Email: Poyda_AA@nrcki.ru
Russian Federation, Moscow

References

  1. Zakharova N.V., Mamedova G., Bravve L.V., Kaydan A., Kartashov S., Orlov V.A., Ushakov V. Differential diagnosis of delusional symptoms in schizophrenia: Brain tractography data. Cognitive Systems Research. 2023. 77. 217–225. https://doi.org/ 10.1016/j.cogsys.2022.10.008
  2. Antonucci L.A., Pergola G., Pigoni A., Dwyer D., Kambeitz-Ilankovic L., Penzel N., Romano R., Gelao B., Torretta S., Rampino A., Trojano M., Caforio G., Falkai P., Blasi G., Koutsouleris N., Bertolino A. A Pattern of Cognitive Deficits Stratified for Genetic and Environmental Risk Reliably Classifies Patients With Schizophrenia From Healthy Control Subjects. Biol. Psychiatry. 2020. 87, 8. 697–707.
  3. Arlot S., Celisse A. A survey of cross-validation procedures for model selection. Statistics Surveys, 2010, P: 40-79.
  4. Bassett D.S., Sporns O. Network neuroscience. Nature Neuroscience. 2017, 20(3), 353–364.
  5. Biswal B., Zerrin Yetkin F., Haughton V.M., Hyde J.S. Functional connectivity in the motor cortex of resting human brain using echo-planar mri. Magnetic Resonance in Medicine. 1995. 34 (4): 537–541.
  6. Calhoun V.D., Liu J., Adalı T. A review of group ICA for fMRI data and ICA for joint inference of imaging, genetic, and ERP data. NeuroImage. 2009. 45(1), S163–S172, https://doi.org/10.1016/j.neuroimage.2008.10.057
  7. Cao B., Cho R.Y., Chen D., Xiu M., Wang L., Soares J.C., Zhang X.Y. Treatment response prediction and individualized identification of first-episode drug-naïve schizophrenia using brain functional connectivity. Mol. Psychiatry. 2020. 25(4): 906–913.
  8. Chang Y.-W., Tsai S.J., Wu Y.-F., Yang A.C. Development of an Al-Based Web Diagnostic System for Phenotyping Psychiatric Disorders. Front. Psychiatry. 2020. 11. 542394.
  9. Corponi F., Zorkina Y., Stahl D., Murru A., Vieta E., Serretti A., Morozova А., Reznik A., Kostyuk G.P., Chekhonin V. Disfunción de los lóbulos frontales en grupos clínicos de esquizofrenia aguda. Revista de Psiquiatría y Salud Mental, 2021, https://doi.org/ 10.1016/j.rpsm.2021.12.002
  10. Cui Y., Li C., Liu B., Sui J., Song M., Chen J., Chen Y., Guo H., Li P., Lu L., Lv L., Ning Y., Wan P., Wang H., Wang H., Wu H., Yan H., Yan J., Yang Y., Zhang H., Zhang D., Jiang T. Consistent brain structural abnormalities and multisite individualised classification of schizophrenia using deep neural networks. Br J Psychiatry. 2022. 221 (6): 732–739. https://doi.org/10.1192/bjp.2022.22
  11. Freund Y., Schapire R.E. A Short Introduction to Boosting. 1999.
  12. Fusar-Poli P., Radua J., McGuire P., Borgwardt S. Neuroanatomical maps of psychosis onset: voxel-wise meta-analysis of antipsychotic-naive VBM studies. Schizophr Bull. 2012 Nov; 38 (6): 1297–307. Epub 2011 Nov 10. PMID: 22080494; PMCID: PMC3494061. https://doi.org/10.1093/schbul/sbr134
  13. Gilbert A.R., Rosenberg D.R., Harenski K., Spencer S., Sweeney J.A., Keshavan M.S. Thalamic volumes in patients with first-episode schizophrenia. Am J Psychiatry. 2001 Apr; 158 (4): 618-24. PMID: 11282698. https://doi.org/10.1176/appi.ajp.158.4.618
  14. Gutiérrez-Gómez L., Vohryzek J., Chiêm B., Baumann P.S., Conus P., Cuenod K.D., Hagmann P., Delvenne J.C. Stable biomarker identification for predicting schizophrenia in the human connectome. Neuroimage Clin. 2020. Vol. 27. P. 102316.
  15. Hu K., Wang M., Liu Y., Yan H., Song M., Chen J., Chen Y., Wang H., Guo H., Wan P., Lv L., Yang Y., Li P., Lu L., Yan J., Wang H., Zhang H., Zhang D., Wu H., Ning Y., Jiang T., Liu B. Multisite schizophrenia classification by integrating structural magnetic resonance imaging data with polygenic risk score. Neuroimage Clin. 2021. 32. 102860.
  16. Jo Jun-Mo. Effectiveness of Normalization Pre-Processing of Big Data to the Machine Learning Performance. The Journal of the Korea institute of electronic communication sciences. 2019. 14. 547–552. https://doi.org/ 10.13067/JKIECS.2019.14.3.547
  17. Kalmady S.V., Greiner R., Agrawal R., Shivakumar V., Narayanaswamy J.C., Brown M.R.G., Greenshaw A.J., Dursun S.M., Venkatasubramanian G. Towards artificial intelligence in mental health by improving schizophrenia prediction with multiple brain parcellation ensemble-learning. NPJ Schizophr. 2019. 5 (1): 2.
  18. Kartashov S., Vartanov A., Захарова Н., Arkhipov A., Strelets V., Maslennikova A., Ushakov V. Tractographic studies in the human brain at the norm and the paranoid schizophrenia. Procedia Computer Science. 2021. 190. 434–438. https://doi.org/ 10.1016/j.procs.2021.06.051
  19. Kambeitz-Ilankovic L., Meisenzahl E.M., Cabral C., von Saldern S., Kambeitz J., Falkai P., Möller H.J., Reiser M., Koutsouleris N. Prediction of outcome in the psychosis prodrome using neuroanatomical pattern classification. Schizophr. Res. 2016. 173 (3): 159–165.
  20. Kottaram A., Johnston L.A., Tian Y., Ganella E.P., Laskaris L., Cocchi L., McGorry P., Pantelis C., Kotagiri R., Cropley V., Zalesky A. Predicting individual improvement in schizophrenia symptom severity at 1-year follow-up: Comparison of connectomic, structural, and clinical predictors. Hum. Brain Mapp. 2020. 41 (12): 3342–3357.
  21. Kozlov S., Poyda A., Orlov V., Malakhov D., Ushakov V., Sharaev M. Selection of functionally homogeneous brain regions based on correlation-clustering analysis. Procedia Comput. Sci. Elsevier BV, 2020. 169. 519–526.
  22. Kozlov S., Poyda A., Orlov V., Sharaev M., Ushakov V. Selection of functionally homogeneous human brain regions for functional connectomes building based on fMRI data. Advances in Cognitive Research, Artificial Intelligence and Neuroinformatics. Cham: Springer International Publishing. 2021. 709–719.
  23. Larkman D.J., Hajnal J.V., Herlihy A.H., Coutts G.A., Young I.R., Ehnholm G. Use of multicoil arrays for separation of signal from multiple slices simultaneously excited. J. Magn. Reson. Imaging. 2001. 13 (2): 313–317.
  24. Lauer M., Senitz D., Beckmann H. Increased volume of the nucleus accumbens in schizophrenia. J Neural Transm (Vienna). 2001;108 (6):645–60. PMID: 11478417. https://doi.org/10.1007/s007020170042
  25. Luo X., Mao Q., Shi J., Wang X., Li C.R. Putamen Gray Matter Volumes in Neuropsychiatric and Neurodegenerative Disorders. World J Psychiatry Ment Health Res. 2019. Vol. 3(1): 1020. Messaritaki E., Foley S., Barawi K., Ettinger U., Jones D. Increased sensorimotor structural connectivity in high schizotypy. bioRxiv, 2022. https://doi.org/10.1101/2022.05.12.491533
  26. Morozova A., Zorkina Y., Abramova O., Pavlova O., Pavlov K., Soloveva K., Volkova M., Alekseeva P., Andryshchenko A., Kostyuk G., Gurina O., Chekhonin V. Neurobiological Highlights of Cognitive Impairment in Psychiatric Disorders. Int J Mol Sci. 2022 Jan 22;23(3):1217. PMID: 35163141; PMCID: PMC8835608. https://doi.org/10.3390/ijms23031217.
  27. Nieto-Castanon A., Whitfield-Gabrieli S. CONN functional connectivity toolbox: RRID SCR_009550, release 22. Hilbert Press. 2022. https://doi.org/10.56441/hilbertpress.2246.5840
  28. Pedregosa F., Varoquaux Gael, Gramfort A., Michel V., Thirion B., Grisel O., Blondel M., Prettenhofer P., Weiss R., Dubourg V., Vanderplas J., Passos A., Cournapeau D, Brucher M., Perrot M. Duchesnay E., Louppe G. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 2011. 12(Oct), 2825–2830.
  29. Pudjihartono N., Fadason T., Kempa-Liehr A.W., O’Sullivan J.M. A Review of Feature Selection Methods for Machine Learning-Based Disease Risk Prediction. Front. Bioinform. 2022.2:927312. https://doi.org/10.3389/fbinf.2022.927312
  30. Rosazza C., Minati L. Resting-state brain networks: Literature review and clinical applications. Neurological Sciences. 2011; 32(5),773–785.
  31. Sharaff A., Gupta H. Extra-Tree Classifier with Metaheuristics Approach for Email Classification. 2019. https://doi.org/ 10.1007/978-981-13-6861-5_17.
  32. Tibshirani R., Friedman J. The Elements of Statistical Learning: Data Mining, Inference, and Prediction. 2001. 546.
  33. Todd N., Josephs O., Zeidman P., Flandin G., Moeller S. Weiskopf N. Functional Sensitivity of 2D Simultaneous Multi-Slice Echo-Planar Imaging: Effects of Acceleration on g-factor and Physiological Noise. Front. Neurosci. 2017. 11: 158. https://doi.org/10.3389/fnins.2017.00158
  34. Tohid H., Faizan M., Faizan U. Alterations of the occipital lobe in schizophrenia. Neurosciences (Riyadh). 2015 Jul; 20 (3): 213–24. PMID: 26166588; PMCID: PMC4710336. https://doi.org/10.17712/nsj.2015.3.20140757
  35. Wolf A. The Machine Learning Simplified: A Gentle Introduction to Supervised Learning. Leanpub, 2022.
  36. Xu K., Liu Y., Zhan Y., Ren J., Jiang T. BRANT: A Versatile and Extendable Resting-State fMRI Toolkit. Front Neuroinform. 2018. 12: 52. https://doi.org/10.3389/fninf.2018.00052
  37. Zang Y., Jiang T., Lu Y., He Y., Tian L. Regional homogeneity approach to fMRI data analysis. Neuroimage. 2004. 22 (1): 394–400. PMID: 15110032
  38. Zou Q.H., Zhu C.Z., Yang Y., Zuo X.N., Long X.Y., Cao Q.J., Wang Y.F., Zang Y.F. An improved approach to detection of amplitude of low-frequency fluctuation (ALFF) for resting-state fMRI: fractional ALFF. J Neurosci Me thods. 2008 Jul 15; 172 (1): 137–41. Epub 2008 Apr 22. PMID: 18501969; PMCID: PMC3902859. https://doi.org/10.1016/j.jneumeth.2008.04.012

Supplementary files

Supplementary Files
Action
1. JATS XML
Download
2. Fig. 1. A scheme of fMRI data analysis for classification

Download (148KB)
Indexing metadata
3. Fig. 2. An example of a homogeneity zone (two-dimensional slice) for voxel A. Black circles indicate voxels, numbers below them indicate the level of correlation with voxel A, dotted lines between voxels correspond to spatial connectivity between voxels with high correlation, and a line indicates the boundary of the homogeneity zone

Download (100KB)
Indexing metadata
4. Fig. 3. Dependence of classification accuracy on the selected number of features. Horizontally – the number of features (logarithmic scale), vertically – maximum accuracy among all classifiers

Download (89KB)
Indexing metadata

Copyright (c) 2024 Russian Academy of Sciences