Multimedia Tools and Applications

, Volume 77, Issue 20, pp 26991–27015 | Cite as

Bi-objective approach for computer-aided diagnosis of schizophrenia patients using fMRI data

  • Indranath ChatterjeeEmail author
  • Manoj Agarwal
  • Bharti Rana
  • Navin Lakhyani
  • Naveen Kumar


Computer-aided diagnosis (CAD) of schizophrenia based on the analysis of brain images, captured using functional Magnetic Resonance Imaging (fMRI) technique, is an active area of research. The main problem lies in the identification of brain regions that contribute to differentiating between a healthy subject and a schizophrenia affected subject. The problem becomes complex due to the high dimensionality of the fMRI data on the one hand and the availability of data for only a small number of subjects on the other hand. In this paper, we propose a three-stage evolutionary based framework for feature selection. It comprises application of general linear model, followed by statistical hypothesis testing, and finally application of Non-dominated Sorting Genetic Algorithm (NSGA-II) to arrive at a small set of about fifty features. Experiments show that the feature set generated by the proposed approach yields accuracy as high as 99.5% in classifying fMRI dataset of healthy and schizophrenia subjects, and can identify the relevant brain regions that are affected in schizophrenia.


Functional magnetic resonance imaging (fMRI) Schizophrenia Computer-aided diagnosis (CAD) Feature selection NSGA-II Bi-objective evolutionary algorithm 



We are thankful to Prof. R. K. Agrawal, School of Computer & Systems Sciences, Jawaharlal Nehru University, Delhi, India for his insightful comments. Indranath Chatterjee is thankful to the Council of Scientific & Industrial Research (CSIR), India for his research fellowship with grant number 09/045(1323)/2014-EMR-I. Naveen Kumar is thankful to University of Delhi for the research grant RC/2015/9677. Data used here for this study were downloaded from the Function BIRN Data Repository (, i.e., Biomedical Informatics Research Network under the following support: for function data, U24-RR021992, Function BIRN and U24 GM104203, Bio-Informatics Research Network Coordinating Center (BIRN-CC). These data were obtained from the Function BIRN Data Repository, Project Accession Number 2007-BDR-6UHZ1.

Compliance with Ethical Standards

Conflict of interests

The authors declare that they have no conflict of interest.


  1. 1.
    Åberg MB, Löken L, Wessberg J (2008) An evolutionary approach to multivariate feature selection for fmri pattern analysis. In: BIOSIGNALS, vol 2, pp 302–307Google Scholar
  2. 2.
    Agarwal M, Kumar N, Vig L (2014) Non-additive multi-objective robot coalition formation. Expert Syst Appl 41(8):3736–3747CrossRefGoogle Scholar
  3. 3.
    Aliakbaryhosseinabadi S, Kamavuako EN, Jiang N, Farina D, Mrachacz-Kersting N (2017) Influence of dual-tasking with different levels of attention diversion on characteristics of the movement-related cortical potential. Brain Res 1674:10–19CrossRefGoogle Scholar
  4. 4.
    Arribas JI, Calhoun VD, Adali T (2010) Automatic bayesian classification of healthy controls, bipolar disorder, and schizophrenia using intrinsic connectivity maps from fmri data. IEEE Trans Biomed Eng 57(12):2850–2860CrossRefGoogle Scholar
  5. 5.
    Bellman RE (1961) Adaptive Control Processes: A Guided Tour. Princeton University Press, PrincetonzbMATHCrossRefGoogle Scholar
  6. 6.
    Bhattacharyya A (1946) On a measure of divergence between two multinomial populations. Sankhyā: Indian J Statist, 401–406Google Scholar
  7. 7.
    Boser BE, Guyon IM, Vapnik VN (1992) A training algorithm for optimal margin classifiers. In: Proceedings of the fifth annual workshop on Computational learning theory. ACM, pp 144–152Google Scholar
  8. 8.
    Caprihan A, Pearlson GD, Calhoun VD (2008) Application of principal component analysis to distinguish patients with schizophrenia from healthy controls based on fractional anisotropy measurements. Neuroimage 42(2):675–682CrossRefGoogle Scholar
  9. 9.
    Castro E, Martínez-Ramón M, Pearlson G, Sui J, Calhoun VD (2011) Characterization of groups using composite kernels and multi-source fmri analysis data: application to schizophrenia. Neuroimage 58(2):526–536CrossRefGoogle Scholar
  10. 10.
    Castro E, Gómez-Verdejo V, Martínez-Ramón M, Kiehl KA, Calhoun VD (2014) A multiple kernel learning approach to perform classification of groups from complex-valued fmri data analysis: application to schizophrenia. NeuroImage 87:1–17CrossRefGoogle Scholar
  11. 11.
    Chang CC, Lin CJ (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2:27:1–27:27. Software available at CrossRefGoogle Scholar
  12. 12.
    Chen J, Xu Y, Zhang J, Liu Z, Xu C, Zhang K, Shen Y, Xu Q (2013) A combined study of genetic association and brain imaging on the daoa gene in schizophrenia. Amer J Med Gen Part B: Neuropsych Gen 162(2):191–200CrossRefGoogle Scholar
  13. 13.
    Chyzhyk D, Savio A, Graña M (2015) Computer aided diagnosis of schizophrenia on resting state fmri data by ensembles of elm. Neural Netw 68:23–33CrossRefGoogle Scholar
  14. 14.
    Deb K, Pratap A, Agarwal S, Meyarivan T (2002) A fast and elitist multiobjective genetic algorithm: Nsga-ii. IEEE Trans Evolut Comput 6(2):182–197CrossRefGoogle Scholar
  15. 15.
    Demirci O, Clark VP, Magnotta VA, Andreasen NC, Lauriello J, Kiehl KA, Pearlson GD, Calhoun VD (2008) A review of challenges in the use of fmri for disease classification/characterization and a projection pursuit application from a multi-site fmri schizophrenia study. Brain Imag Behav 2(3):207–226CrossRefGoogle Scholar
  16. 16.
    Du W, Calhoun VD, Li H, Ma S, Eichele T, Kiehl KA, Pearlson GD, Adali T (2012) High classification accuracy for schizophrenia with rest and task fmri data. Front Human Neurosci 6:145CrossRefGoogle Scholar
  17. 17.
    Ford J, Shen L, Makedon F, Flashman LA, Saykin AJ (2002) A combined structural-functional classification of schizophrenia using hippocampal volume plus fmri activation. In: Engineering in medicine and biology, 2002. 24th Annual conference and the annual fall meeting of the biomedical engineering society EMBS/BMES conference, 2002. Proceedings of the second joint, vol 1. IEEE, pp 48-49Google Scholar
  18. 18.
    Ford J, Farid H, Makedon F, Flashman LA, McAllister TW, Megalooikonomou V, Saykin AJ (2003) Patient classification of fmri activation maps. In: Medical image computing and computer-assisted intervention-MICCAI 2003. Springer, pp 58–65Google Scholar
  19. 19.
    Fortin FA, Grenier S, Parizeau M (2013) Generalizing the improved run-time complexity algorithm for non-dominated sorting. In: Proceedings of the 15th annual conference on Genetic and evolutionary computation. ACM, pp 615–622Google Scholar
  20. 20.
    Frances A et al. (1994) Diagnostic and statistical manual of mental disorders. DSM-IV. American Psychiatric AssociationGoogle Scholar
  21. 21.
    Friston KJ, Holmes AP, Worsley KJ, Poline JP, Frith CD, Frackowiak RS (1994) Statistical parametric maps in functional imaging: a general linear approach. Hum Brain Mapp 2(4):189–210CrossRefGoogle Scholar
  22. 22.
    Garrity AG, Pearlson GD, McKiernan K, Lloyd D, Kiehl KA, Calhoun VD (2007) Aberrant “default mode” functional connectivity in schizophrenia. Amer J Psych 164(3):450–457CrossRefGoogle Scholar
  23. 23.
    Gur RE, Gur RC (2010) Functional magnetic resonance imaging in schizophrenia. Dial Clin Neurosci 12(3):333Google Scholar
  24. 24.
    Honea RA, Meyer-Lindenberg A, Hobbs KB, Pezawas L, Mattay VS, Egan MF, Verchinski B, Passingham RE, Weinberger DR, Callicott JH (2008) Is gray matter volume an intermediate phenotype for schizophrenia? A voxel-based morphometry study of patients with schizophrenia and their healthy siblings. Biolog Psych 63(5):465–474CrossRefGoogle Scholar
  25. 25.
    Iragui VJ, Kutas M, Mitchiner MR, Hillyard SA (1993) Effects of aging on event-related brain potentials and reaction times in an auditory oddball task. Psychophysiology 30(1):10–22CrossRefGoogle Scholar
  26. 26.
    Juneja A, Rana B, Agrawal RK (2014) A novel approach for computer aided diagnosis of schizophrenia using auditory oddball functional mri. In: Proceedings of the 2014 Indian conference on computer vision graphics and image processing, ICVGIP ’14, pp 37:1–37:6Google Scholar
  27. 27.
    Juneja A, Rana B, Agrawal R (2016) A combination of singular value decomposition and multivariate feature selection method for diagnosis of schizophrenia using fmri. Biomed Signal Process Control 27:122–133CrossRefGoogle Scholar
  28. 28.
    Juneja A, Rana B, Agrawal R (2017) fmri based computer aided diagnosis of schizophrenia using fuzzy kernel feature extraction and hybrid feature selection. Multimed Tools Appl, 1–27Google Scholar
  29. 29.
    Kiehl KA, Liddle PF (2001) An event-related functional magnetic resonance imaging study of an auditory oddball task in schizophrenia. Schizophren Res 48 (2):159–171CrossRefGoogle Scholar
  30. 30.
    Kim DI, Mathalon D, Ford J, Mannell M, Turner J, Brown G, Belger A, Gollub R, Lauriello J, Wible C et al (2009) Auditory oddball deficits in schizophrenia: an independent component analysis of the fmri multisite function birn study. Schizophren Bull 35(1):67–81CrossRefGoogle Scholar
  31. 31.
    Kim J, Calhoun VD, Shim E, Lee JH (2016) Deep neural network with weight sparsity control and pre-training extracts hierarchical features and enhances classification performance: Evidence from whole-brain resting-state functional connectivity patterns of schizophrenia. Neuroimage 124:127–146CrossRefGoogle Scholar
  32. 32.
    Koolschijn PCM, van Haren NE, Pol HEH, Kahn RS (2008) Hypothalamus volume in twin pairs discordant for schizophrenia. Eur Neuropsychopharmacol 18 (4):312–315CrossRefGoogle Scholar
  33. 33.
    Kriegeskorte N, Simmons WK, Bellgowan PS, Baker CI (2009) Circular analysis in systems neuroscience: the dangers of double dipping. Nat Neurosci 12 (5):535–540CrossRefGoogle Scholar
  34. 34.
    Lancaster JL, Woldorff MG, Parsons LM, Liotti M, Freitas CS, Rainey L, Kochunov PV, Nickerson D, Mikiten SA, Fox PT (2000) Automated talairach atlas labels for functional brain mapping. Hum Brain Mapp 10(3):120–131CrossRefGoogle Scholar
  35. 35.
    Lancaster JL, Laird AR, Eickhoff SB, Martinez MJ, Fox PM, Fox PT (2012) Automated regional behavioral analysis for human brain images. Front Neuroinform 6:23CrossRefGoogle Scholar
  36. 36.
    Linden DE, Prvulovic D, Formisano E, Völlinger M, Zanella FE, Goebel R, Dierks T (1999) The functional neuroanatomy of target detection: an fmri study of visual and auditory oddball tasks. Cereb Cortex 9(8):815–823CrossRefGoogle Scholar
  37. 37.
    Ma X, Chou CA, Sayama H, Chaovalitwongse WA (2016) Brain response pattern identification of fmri data using a particle swarm optimization-based approach. Brain Inform, 1–12Google Scholar
  38. 38.
    Mitchell TM, Hutchinson R, Niculescu RS, Pereira F, Wang X, Just M, Newman S (2004) Learning to decode cognitive states from brain images. Mach Learn 57(1-2):145–175zbMATHCrossRefGoogle Scholar
  39. 39.
    Niiniskorpi T, Åberg MB, Wessberg J (2009) Particle swarm feature selection for fmri pattern classification. In: BIOSIGNALS, pp 279–284Google Scholar
  40. 40.
    O’Brien JL, Lister JJ, Fausto BA, Clifton GK, Edwards JD (2017) Cognitive training enhances auditory attention efficiency in older adults. Front Aging Neurosci 9:322CrossRefGoogle Scholar
  41. 41.
    Ogawa S, Lee TM, Kay AR, Tank DW (1990) Brain magnetic resonance imaging with contrast dependent on blood oxygenation. Proc Natl Acad Sci 87(24):9868–9872CrossRefGoogle Scholar
  42. 42.
    Riaz A, Asad M, Al-Arif SMR, Alonso E, Dima D, Corr P, Slabaugh G (2017) Fcnet: a convolutional neural network for calculating functional connectivity from functional mri. In: International workshop on connectomics in neuroimaging. Springer, pp 70–78Google Scholar
  43. 43.
    Savio A, Graña M (2015) Local activity features for computer aided diagnosis of schizophrenia on resting-state fmri. Neurocomputing 164:154–161CrossRefGoogle Scholar
  44. 44.
    Shahamat H, Pouyan AA (2015) Feature selection using genetic algorithm for classification of schizophrenia using fmri data. J AI Data Min 3(1):30–37Google Scholar
  45. 45.
    Shi F, Liu Y, Jiang T, Zhou Y, Zhu W, Jiang J, Liu H, Liu Z (2007) Regional homogeneity and anatomical parcellation for fmri image classification: application to schizophrenia and normal controls. In: International conference on medical image computing and computer-assisted intervention. Springer, pp 136–143Google Scholar
  46. 46.
    Smart O, Burrell L (2015) Genetic programming and frequent itemset mining to identify feature selection patterns of ieeg and fmri epilepsy data. Eng Appl Artif Intell 39:198–214CrossRefGoogle Scholar
  47. 47.
    Ülker CC, Aytekin T (2013) Improving the performance of active voxel selection in the analysis of fmri data using genetic algorithms. In: Proceedings of the 6th Balkan conference in informatics. ACM, pp 129–136Google Scholar
  48. 48.
    Ungar L, Nestor PG, Niznikiewicz MA, Wible CG, Kubicki M (2010) Color stroop and negative priming in schizophrenia: an fmri study. Psychiatry Res Neuroimaging 181(1):24–29CrossRefGoogle Scholar
  49. 49.
    Viviani R, Grön G, Spitzer M (2005) Functional principal component analysis of fmri data. Hum Brain Mapp 24(2):109–129CrossRefGoogle Scholar
  50. 50.
    Welch BL (1947) The generalization of student’s’ problem when several different population variances are involved. Biometrika 34(1/2):28–35MathSciNetzbMATHCrossRefGoogle Scholar
  51. 51.
    Williams M, Galvin K, O’Sullivan B, MacDonald C, Ching E, Turkheimer F, Howes O, Pearce R, Hirsch S, Maier M (2014) Neuropathological changes in the substantia nigra in schizophrenia but not depression. Eur Arch Psychiatry Clin Neurosci 264(4):285–296CrossRefGoogle Scholar
  52. 52.
    Wu L, Shen C, van den Hengel A (2017) Deep linear discriminant analysis on fisher networks: a hybrid architecture for person re-identification. Pattern Recogn 65:238–250CrossRefGoogle Scholar
  53. 53.
    Yoon JH, Minzenberg MJ, Raouf S, D’Esposito M, Carter CS (2013) Impaired prefrontal-basal ganglia functional connectivity and substantia nigra hyperactivity in schizophrenia. Biol Psych 74(2):122–129CrossRefGoogle Scholar
  54. 54.
    Zang Y, Jiang T, Lu Y, He Y, Tian L (2004) Regional homogeneity approach to fmri data analysis. Neuroimage 22(1):394–400CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Computer ScienceUniversity of DelhiDelhiIndia
  2. 2.Department of Computer Science, Hans Raj CollegeUniversity of DelhiDelhiIndia
  3. 3.Department of MRISaral DiagnosticsNew DelhiIndia

Personalised recommendations