Multimedia Tools and Applications

, Volume 77, Issue 3, pp 3963–3989 | Cite as

fMRI based computer aided diagnosis of schizophrenia using fuzzy kernel feature extraction and hybrid feature selection



Functional magnetic resonance imaging (fMRI) is a useful technique for capturing deformities in brain activity patterns of several disorders. Schizophrenia is one such serious psychiatric disorder that, in absence of any standard diagnostic tests, is detected from behavioural symptoms observed externally. Thus, fMRI can be used for building an effective decision model for computer aided diagnosis of schizophrenia. However, fMRI data has huge dimension compared with the number of subjects; therefore it is essential to reduce the data dimension to avoid poor generalisation performance of the decision model. In the present work, we propose a three-phase dimension reduction that comprises of segmentation of voxels of 3-D spatial maps (independent component score-maps or β-maps) into anatomical brain regions; feature extraction from each region using a novel fuzzy kernel principal component analysis; and a novel hybrid (filter-cum-wrapper) feature selection for determining a reduced subset of discriminative features. These features are used as input to support vector machine classifier for learning a decision model. The method is carried out within leave-one-out cross-validation. Classification accuracy, sensitivity, and specificity are utilised to estimate the performance on two different balanced datasets D1 and D2 (respectively acquired on 1.5 T and 3 T scanners). Both the datasets contain fMRI data of age-matched healthy subjects and schizophrenia patients for auditory oddball task, obtained from FBIRN multisite dataset. The proposed method attains best classification accuracy of 95.6% and 96.0% for D1 and D2 respectively. The proposed method shows enhanced performance over the state-of-the-art methods. Further, the discriminative brain regions identified are in accordance with the findings in related literature and may be used as potential biomarkers.


Computer aided diagnosis fMRI Fuzzy kernel principal component analysis Hybrid forward feature selection Support vector machine Schizophrenia 



Data used for this study were downloaded from the publicly available Function BIRN Data Repository (, supported by grants to the Function BIRN (U24-RR021992). Testbed funded by the National Centre for Research Resources at the National Institutes of Health, U.S.A. First author thanks University Grants Commission (INDIA) and second author thanks Department of Science and Technology (INDIA) for research fellowship. The authors are grateful to the reviewers for their valuable comments which helped in improving the overall quality of the manuscript.


  1. 1.
    Ashburner J, Friston KJ (1999) Nonlinear spatial normalization using basis functions. Hum Brain Mapp 7(4):254–266Google Scholar
  2. 2.
    Bell AJ, Sejnowski TJ (1995) An information-maximization approach to blind separation and blind deconvolution. Neural Comput 7(6):1129–1159CrossRefGoogle Scholar
  3. 3.
    Bellman R, Corporation R (1957) Dynamic programming. Princeton University Press, New Jersey, USAGoogle Scholar
  4. 4.
    Calhoun VD, Adali T, Pearlson GD (2001) A method for making group inferences from functional MRI data using independent component analysis. Hum Brain Mapp 14(3):140–151Google Scholar
  5. 5.
    Calhoun VD, Adali T, Kiehl KA, Astur R, Pekar JJ, Pearlson GD (2006) A method for multitask fMRI data fusion applied to schizophrenia. Hum Brain Mapp 27(7):598–610Google Scholar
  6. 6.
    Camps-Valls G, Martín-Guerrero JD, Rojo-Álvarez JL, Soria-Olivas E (2004) Fuzzy sigmoid kernel for support vector classifiers. Neurocomputing 62:501–506CrossRefGoogle Scholar
  7. 7.
    Carter CS, MacDonald AW III, Ross LL, Stenger VA (2001) Anterior cingulate cortex activity and impaired self-monitoring of performance in patients with schizophrenia: an event-related fMRI study. Am J Psychiatr 158:1423–1428Google Scholar
  8. 8.
    Castro E, Martinez-Ramon M, Pearlson GD, 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
  9. 9.
    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
  10. 10.
    Chang C-C, Lin C-J (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2(3):27:1–27:27CrossRefGoogle Scholar
  11. 11.
    Chen Y, Ma J, Feng Q, Luo L, Shi P, Chen W (2008) Nonlocal prior Bayesian tomographic reconstruction. J Math Imaging Vision 30(2):133–146CrossRefGoogle Scholar
  12. 12.
    Chen Y, Shi L, Feng Q, Yang J, Shu H, Luo L, Coatrieux JL, Chen W (2014) Artifact suppressed dictionary learning for low-dose CT image processing. IEEE Trans Med Imaging 33(12):2271–2292CrossRefGoogle Scholar
  13. 13.
    Demirci O, Clark VP, Calhoun VD (2008) A projection pursuit algorithm to classify individuals using fMRI data: application to schizophrenia. NeuroImage 39(4):1774–1782CrossRefGoogle Scholar
  14. 14.
    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 Hum Neurosci 6:1–12Google Scholar
  15. 15.
    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-MICCAIGoogle Scholar
  16. 16.
    Friston KJ (2000) Nonlinear responses in fMRI: the balloon model, Volterra kernels, and other hemodynamics. NeuroImage 12(4):466–477CrossRefGoogle Scholar
  17. 17.
    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):189–210Google Scholar
  18. 18.
    Guyon I, ElisseeffA (2003) An introduction to variable and feature selection. J Mach Learn Res 3:1157–1182Google Scholar
  19. 19.
    Guyon I, Weston J, Stephen B, Vladimir V (2002) Gene selection for cancer classification using support vector machines. Mach Learn 46(1–3):389–422Google Scholar
  20. 20.
    Juneja A, Rana B, Agrawal RK (2014) A novel approach for computer aided diagnosis of schizophrenia using auditory oddball functional MRI. In: Ninth Indian Conference on Computer Vision Graphics and Image ProcessingGoogle Scholar
  21. 21.
    Juneja A, Rana B, Agrawal RK (2016) A combination of singular value decomposition and multivariate feature selection method for diagnosis of schizophrenia using fMRI. Biomedical Signal Processing and Control 27:122–133Google Scholar
  22. 22.
    Kim D, Burge J, Lane T, Pearlson GD, Kiehl KA, Calhoun VD (2008) Hybrid ICA–Bayesian network approach reveals distinct effective connectivity differences in schizophrenia. NeuroImage 42(4):1560–1568CrossRefGoogle Scholar
  23. 23.
    Kim DI, Manoach DS, Mathalon DH, Turner JA, Mannell M, Brown GG, Ford JM, Gollub RL, White T, Wible C et al (2009a) Dysregulation of working memory and default-mode networks in schizophrenia using independent component analysis, an fBIRN and MCIC study. Hum Brain Mapp 30(11):3795–3811Google Scholar
  24. 24.
    Kim DI, Mathalon DH, Ford JM, Mannell M, Turner JA, Brown GG, Belger A et al (2009b) Auditory oddball deficits in schizophrenia: an independent component analysis of the fMRI multisite function BIRN study. Schizophr Bull 35(1):67–81Google Scholar
  25. 25.
    Kittler J (1986) Feature selection and extraction. Handbook of pattern recognition and image processing, p 59–83Google Scholar
  26. 26.
    Li YO, Adali T, Calhoun VD (2007) Estimating the number of independent components for functional magnetic resonance imaging data. Hum Brain Mapp 28(11):1251–1266Google Scholar
  27. 27.
    Maldjian JA, Laurienti PJ, Kraft RA, Burdette JH (2003) An automated method for neuroanatomic and cytoarchitectonic atlas-based interrogation of fMRI data sets. NeuroImage 19(3):1233–1239CrossRefGoogle Scholar
  28. 28.
    Mundra PA, Rajapakse JC (2010) SVM-RFE with MRMR filter for gene selection. IEEE Trans NanoBiosci 9(1):31–37CrossRefGoogle Scholar
  29. 29.
    Mwangi B, Tian TS, Soares JC (2014) A review of feature reduction techniques in neuroimaging. Neuroinformatics 12:229–244CrossRefGoogle Scholar
  30. 30.
    Ogawa S, Lee TM, Kay AR, Tank DW (1990) Brain magnetic resonance imaging with contrast dependent on blood oxygenation. In Proceedings of the National Academy of SciencesGoogle Scholar
  31. 31.
    Orrùa G, Pettersson-Yeo W, Marquandb AF, Sartori G, Mechelli A (2012) Using support vector machine to identify imaging biomarkers of neurological and psychiatric disease: a critical review. Neurosci Biobehav Rev 36:1140–1152Google Scholar
  32. 32.
    Qu X, Hou Y, Lam F, Guo D, Zhong J, Chen Z (2014) Magnetic resonance image reconstruction from undersampled measurements using a patch-based nonlocal operator. Med Image Anal 18(6):843–856Google Scholar
  33. 33.
    Qu X, Mayzel M, Cai JF, Chen Z, Orekhov V (2015) Accelerated NMR spectroscopy with low-rank reconstruction. Angew Chem Int Ed 54(3):852–854CrossRefGoogle Scholar
  34. 34.
    Saggar M, Shelly EW, Lepage J-F, Hoeft F, Reiss AL (2014) Revealing the neural networks associated with processing of natural social interaction and the related effects of actor-orientation and face-visibility. NeuroImage 84:648–656CrossRefGoogle Scholar
  35. 35.
    Schölkopf B, Smola A, Müller KR (1997) Kernel principal component analysis. In: Artificial Neural Networks—ICANN'97Google Scholar
  36. 36.
    Soria E, Martin J, Camps G, Serrano AJ, Calpe J, Chova L (2003) A low complexity fuzzy activation function for artificial neural networks. IEEE Trans Neural Netw 14(6):1576–1579CrossRefGoogle Scholar
  37. 37.
    Tzourio-Mazoyer N, Landeau B, Papathanassiou D, Crivello F, Etard O, Delcroix N, Mazoyer B, Joliot M (2002) Automated anatomical labeling of activations in SPM using a macroscopic anatomical parcellation of the MNI MRI single-subject brain. NeuroImage 15(1):273–289CrossRefGoogle Scholar
  38. 38.
    Ungar L, Nester PG, Niznikiewicz MA, Wible CG, Kubicki M (2010) Color Stroop and negative priming in schizophrenia: an fMRI study. Psychiatry Res Neuroimaging 181(1):24–29Google Scholar
  39. 39.
    Vapnik V (1995) The nature of statistical learning theory. Springer-Verlag, New YorkCrossRefMATHGoogle Scholar
  40. 40.
    Wang S, Chen M, Li Y, Shao Y, Zhang Y, Du S, Wu J (2016) Morphological analysis of dendrites and spines by hybridization of ridge detection with twin support vector machine. PeerJ 4:e2207CrossRefGoogle Scholar
  41. 41.
    Watanuki T, Matsuo K, Egashira K, Nakashima M, Harada K, Nakano M, Matsubara T, Takahashi K, Watanabe Y (2016) Precentral and inferior prefrontal hypoactivation during facial emotion recognition in patients with schizophrenia: a functional near-infrared spectroscopy study. Schizophr Res 170(1):109–114Google Scholar
  42. 42.
    Wellcome-Trust-Centre-for-Neuroimaging (2009) SPM8 - Statistical Parametric Mapping. University College London, 12 April 2009. [Online]. Available:
  43. 43.
    Xie ZX, Hu QH, Yu DR (2006) Improved feature selection algorithm based on SVM and correlation. In: Advances in Neural Networks-ISNN 2006, Berlin HeidelbergGoogle Scholar
  44. 44.
    Yoon JH, Nguyen DV, McVay LM, Deramo P, Minzenberg MJ, Niendham T, Ragland JD, Solomon M, Carter CS (2012) Automated classification of fMRI during cognitive control identifies more severely disorganized subjects with schizophrenia. Schizophr Res 135(1):28–33Google Scholar
  45. 45.
    Zhang Y, Dong Z, Wang S, Ji G, Yang J (2015a) Preclinical diagnosis of magnetic resonance (MR) brain images via discrete wavelet packet transform with Tsallis entropy and generalized eigenvalue proximal support vector machine (GEPSVM). Entropy 17(4):1795–1813CrossRefGoogle Scholar
  46. 46.
    Zhang Y, Wang S, Phillips P, Dong Z, Ji G, Yang J (2015b) Detection of Alzheimer's disease and mild cognitive impairment based on structural volumetric MR images using 3D-DWT and WTA-KSVM trained by PSOTVAC. Biomedical Signal Processing and Control 21:58–73Google Scholar

Copyright information

© Springer Science+Business Media New York 2017

Authors and Affiliations

  1. 1.School of Computer & Systems SciencesJawaharlal Nehru UniversityNew DelhiIndia

Personalised recommendations