An adaptive fuzzy K-nearest neighbor approach for MR brain tumor image classification using parameter free bat optimization algorithm

  • Taranjit KaurEmail author
  • Barjinder Singh Saini
  • Savita Gupta


This paper presents an automatic diagnosis system for the tumor grade classification through magnetic resonance imaging (MRI). The diagnosis system involves a region of interest (ROI) delineation using intensity and edge magnitude based multilevel thresholding algorithm. Then the intensity and the texture attributes are extracted from the segregated ROI. Subsequently, a combined approach known as Fisher+ Parameter-Free BAT (PFreeBAT) optimization is employed to derive the optimal feature subset. Finally, a novel learning approach dubbed as PFree BAT enhanced fuzzy K-nearest neighbor (FKNN) is proposed by combining FKNN with PFree BAT for the classification of MR images into two categories: High and Low-Grade. In PFree BAT enhanced FKNN, the model parameters, i.e., neighborhood size k and the fuzzy strength parameter m are adaptively specified by the PFree BAT optimization approach. Integrating PFree BAT with FKNN enhances the classification capability of the FKNN. The diagnostic system is rigorously evaluated on four MR images datasets including images from BRATS 2012 database and the Harvard repository using classification performance metrics. The empirical results illustrate that the diagnostic system reached to ceiling level of accuracy on the test MR image dataset via 5-fold cross-validation mechanism. Additionally, the proposed PFree BAT enhanced FKNN is evaluated on the Parkinson dataset (PD) from the UCI repository having the pre-extracted feature space. The proposed PFree BAT enhanced FKNN reached to an average accuracy of 98% and 97.45%. with and without feature selection on PD dataset. Moreover, solely to contrast, the performance of the proposed PFree BAT enhanced FKNN with the existing FKNN variants the experimentations were also done on six other standard datasets from KEEL repository. The results indicate that the proposed learning strategy achieves the best value of accuracy in contrast to the existing FKNN variants.


Fuzzy K-nearest neighbor PFree BAT optimization Diagnosis system Model parameters 



This research received no specific grant from any funding agency in the public, commercial, or not-for-profit sectors.

Compliance with ethical standards

Conflict of interest

‘None Declared’.


  1. 1.
    Amadasun M, King R (1989) Texural features corresponding to textural properties. IEEE Trans Syst Man Cybern 19:1264–1274CrossRefGoogle Scholar
  2. 2.
    Arif M, Akram MU, others (2010) Pruned fuzzy K-nearest neighbor classifier for beat classification. J Biomed Sci Eng 3:380.Google Scholar
  3. 3.
    Astrom F, Koker R (2011) A parallel neural network approach to prediction of Parkinson’s disease. Expert Syst Appl 38:12470–12474CrossRefGoogle Scholar
  4. 4.
    Bahadure NB, Ray AK, Thethi HP (2018) Comparative approach of MRI-based brain tumor segmentation and classification using genetic algorithm. J Digit Imaging 31:477–489CrossRefGoogle Scholar
  5. 5.
    Bakwad KM, Pattnaik SSSS, Sohi BS, et al (2009) Hybrid bacterial foraging with parameter free PSO. In: Nat. Biol. Inspired Comput. 2009. NaBIC 2009. World Congr. Ieee, pp 1077–1081Google Scholar
  6. 6.
    Cai Z, Gu J, Wen C et al (2018) An intelligent Parkinson’s disease diagnostic system based on a chaotic bacterial foraging optimization enhanced fuzzy KNN approach. Comput Math Methods Med 2018:1–24CrossRefGoogle Scholar
  7. 7.
    Chen H-L, Yang B, Wang G et al (2011) A novel bankruptcy prediction model based on an adaptive fuzzy k-nearest neighbor method. Knowledge-Based Syst 24:1348–1359CrossRefGoogle Scholar
  8. 8.
    Chen H-L, Huang C-C, Yu X-G et al (2013) An efficient diagnosis system for detection of Parkinson’s disease using fuzzy k-nearest neighbor approach. Expert Syst Appl 40:263–271CrossRefGoogle Scholar
  9. 9.
    Chen H-L, Wang G, Ma C et al (2016) An efficient hybrid kernel extreme learning machine approach for early diagnosis of Parkinson′s disease. Neurocomputing 184:131–144CrossRefGoogle Scholar
  10. 10.
    Cheng M, Hoang N (2014) Groutability estimation of grouting processes with microfine cements using an evolutionary instance-based learning approach. J Comput Civ Eng 28:04014014CrossRefGoogle Scholar
  11. 11.
    Colominas MA, Schlotthauer G, Torres ME (2014) Improved complete ensemble EMD: a suitable tool for biomedical signal processing. Biomed Sign Proc Control 14:19–29CrossRefGoogle Scholar
  12. 12.
    Costa AF, Humpire-mamani G, Juci A, et al (2012) An Efficient Algorithm for Fractal Analysis of Textures. In: 25th SIBGRAPI Conf. Graph. Patterns Images. IEEE, Ouro Preto, Brazil, pp 39–46Google Scholar
  13. 13.
    Cover T, Hart P (1967) Nearest neighbor pattern classification. IEEE Trans Inf Theory 13:21–27CrossRefGoogle Scholar
  14. 14.
    Das R (2010) A comparison of multiple classification methods for diagnosis of Parkinson disease. Expert Syst Appl 37:1568–1572CrossRefGoogle Scholar
  15. 15.
    Denoeux T (1995) A k-nearest neighbor classification rule based on Dempster-Shafer theory. IEEE Trans Syst Man Cybern 25:804–813CrossRefGoogle Scholar
  16. 16.
    Derrac J, Chiclana F, García S, Herrera F (2016) Evolutionary fuzzy k -nearest neighbors algorithm using interval-valued fuzzy sets. Inf Sci (Ny) 329:144–163CrossRefGoogle Scholar
  17. 17.
    Emblem KE, Nedregaard B, Hald JK et al (2009) Automatic glioma characterization from dynamic susceptibility contrast imaging: brain tumor segmentation using knowledge-based fuzzy clustering. J Magn Reson Imaging 30:1–10CrossRefGoogle Scholar
  18. 18.
    Fawcett T (2004) ROC graphs: notes and practical considerations for researchers. Mach Learn 31:1–38MathSciNetGoogle Scholar
  19. 19.
    Georgiadis P, Cavouras D, Kalatzis I et al (2008) Improving brain tumor characterization on MRI by probabilistic neural networks and non-linear transformation of textural features. Comput Methods Prog Biomed 89:24–32CrossRefGoogle Scholar
  20. 20.
    Gibbs P, Turnbull LW (2003) Textural analysis of contrast-enhanced MR images of the breast. Magn Reson Med 50:92–98CrossRefGoogle Scholar
  21. 21.
    Guo P-F, Bhattacharya P, Kharma N (2010) Advances in detecting Parkinson’s disease. In: Int. Conf. Med. Biometrics. pp 306–314Google Scholar
  22. 22.
    Gupta N, Bhatele P, Khanna P (2019) Glioma detection on brain MRIs using texture and morphological features with ensemble learning. Biomed Sign Proc Control 47:115–125CrossRefGoogle Scholar
  23. 23.
    Guyon I, Weston J, Barnhill S, Vapnik V (2002) Gene selection for cancer classification using support vector machines. Mach Learn 46:389–422CrossRefGoogle Scholar
  24. 24.
    Haralick RM, Shanmugam K, Dinstein I (1973) Textural features for image classification. IEEE Trans Syst Man Cybern SMC-3:610–621CrossRefGoogle Scholar
  25. 25.
    Harvard Medical School. Accessed 2 Apr 2016
  26. 26.
    Hemanth JD, Anitha J (2019) Modified genetic algorithm approaches for classification. Appl Soft Comput J 75:21–28CrossRefGoogle Scholar
  27. 27.
    Hemanth DJ, Vijila CKS, Selvakumar AI, Anitha J (2011) Performance Enhanced Hybrid Kohonen-Hopfield Neural Network for Abnormal Brain Image Classification. In: Signal Process. Image Process. Pattern Recognit. Springer, pp 356–365Google Scholar
  28. 28.
    Herlidou-Meme S, Constans J, Carsin B et al (2003) MRI texture analysis on texture test objects, normal brain and intracranial tumors. Magn Reson Imaging 21:989–993CrossRefGoogle Scholar
  29. 29.
    Hong L, Wan Y, Jain A (1998) Fingerprint image enhancement: algorithm and performance evaluation. IEEE Trans Pattern Anal Mach Intell 20:777–789CrossRefGoogle Scholar
  30. 30.
    Hu X, Xie C (2005) Improving fuzzy k-NN by using genetic algorithm. J Comput Inf Syst 1:203–213Google Scholar
  31. 31.
    Hui LY, Muftah M, Das T et al (2012) Classification of MR tumor images based on Gabor wavelet analysis. J Med Biol Eng 32:22–28CrossRefGoogle Scholar
  32. 32.
    Iftekharuddin KM, Zheng J, Islam MA, Ogg RJ (2009) Fractal-based brain tumor detection in multimodal MRI. Appl Math Comput 207:23–41MathSciNetzbMATHGoogle Scholar
  33. 33.
    Kaur T, Saini B, Gupta S (2017) Quantitative metric for MR brain tumor grade classification using sample space density measure of analytic intrinsic mode function representation. IET Image Process 11:620–632CrossRefGoogle Scholar
  34. 34.
    Kaur T, Saini BS, Gupta S (2018) A joint intensity and edge magnitude-based multilevel thresholding algorithm for the automatic segmentation of pathological MR brain images. Neural Comput Appl 30:1317–1340CrossRefGoogle Scholar
  35. 35.
    Kaur T, Saini BS, Gupta S (2018) A novel feature selection method for brain tumor MR image classification based on the fisher criterion and parameter-free bat optimization. Neural Comput Appl 29:193–206CrossRefGoogle Scholar
  36. 36.
    Keller JM, Gray MR (1985) A fuzzy K-nearest neighbor algorithm. IEEE Trans Syst Man Cybern SMC-15:580–585CrossRefGoogle Scholar
  37. 37.
    Kucnehva LI (1995) An intuitionistic fuzzy k-nearest neighbors rule.Google Scholar
  38. 38.
    Lahmiri S (2017) Glioma detection based on multi-fractal features of segmented brain MRI by particle swarm optimization techniques. Biomed Sign Proc Control 31:148–155CrossRefGoogle Scholar
  39. 39.
    Lee S-H (2015) Feature selection based on the center of gravity of BSWFMs using NEWFM. Eng Appl Artif Intell 45:482–487CrossRefGoogle Scholar
  40. 40.
    Lee MC, Nelson SJ (2008) Supervised pattern recognition for the prediction of contrast-enhancement appearance in brain tumors from multivariate magnetic resonance imaging and spectroscopy. Artif Intell Med 43:61–74CrossRefGoogle Scholar
  41. 41.
    Leng L, Zhang J, Xu J, et al (2010) Dynamic weighted discrimination power analysis in DCT domain for face and palmprint recognition. In: Inf. Commun. Technol. Converg. (ICTC), 2010 Int. Conf. pp 467–471Google Scholar
  42. 42.
    Leng L, Zhang J, Xu J, et al (2010) Dynamic weighted discrimination power analysis: A novel approach for face and palmprint recognition in DCT domain. In: Int. J. Phys. Sci. pp 467–471Google Scholar
  43. 43.
    Leng L, Zhang J, Chen G, et al (2011) Two-directional two-dimensional random projection and its variations for face and palmprint recognition. In: Int. Conf. Comput. Sci. Its Appl. pp 458–470Google Scholar
  44. 44.
    Leng L, Zhang S, Bi X, Khan MK (2012) Two-dimensional cancelable biometric scheme. In: 2012 Int. Conf. Wavelet Anal. Pattern Recognit. pp 164–169Google Scholar
  45. 45.
    Leng L, Li M, Teoh ABJ 2013) Conjugate 2D palmhash code for secure palm-print-vein verification. In: Image Signal Process. (CISP), 2013 6th Int. Congr. pp 1705–1710Google Scholar
  46. 46.
    Leng L, Li M, Kim C, Bi X (2017) Dual-source discrimination power analysis for multi-instance contactless palmprint recognition. Multimed Tools Appl 76:333–354CrossRefGoogle Scholar
  47. 47.
    Li Z, Tang J (2015) Unsupervised feature selection via nonnegative spectral analysis and redundancy control. IEEE Trans Image Process 24:5343–5355MathSciNetCrossRefGoogle Scholar
  48. 48.
    Li D-C, Liu C-W, Hu SC (2011) A fuzzy-based data transformation for feature extraction to increase classification performance with small medical data sets. Artif Intell Med 52:45–52CrossRefGoogle Scholar
  49. 49.
    Little MA, McSharry PE, Hunter EJ et al (2009) Suitability of dysphonia measurements for telemonitoring of Parkinson’s disease. IEEE Trans Biomed Eng 56:1015–1022CrossRefGoogle Scholar
  50. 50.
    Liu DY, Chen HL, Yang B et al (2012) Design of an enhanced fuzzy k-nearest neighbor classifier based computer aided diagnostic system for thyroid disease. J Med Syst 36:3243–3254CrossRefGoogle Scholar
  51. 51.
    Liu Y, Nie L, Han L, et al (2015) Action2Activity: Recognizing Complex Activities from Sensor Data. In: IJCAI. pp 1617–1623Google Scholar
  52. 52.
    Lu S, Qiu X, Shi J et al (2017) A pathological brain detection system based on extreme learning machine optimized by bat algorithm. CNS Neurol Disord Targets (Formerly Curr Drug Targets-CNS Neurol Disord) 16:23–29CrossRefGoogle Scholar
  53. 53.
    Luukka P (2011) Feature selection using fuzzy entropy measures with similarity classifier. Expert Syst Appl 38:4600–4607CrossRefGoogle Scholar
  54. 54.
    Mahdavi M, Fesanghary M, Damangir E (2007) An improved harmony search algorithm for solving optimization problems. Appl Math Comput 188:1567–1579MathSciNetzbMATHGoogle Scholar
  55. 55.
    Mahmoud-Ghoneim D, Toussaint G, Constans J-M, de Certaines JD (2003) Three dimensional texture analysis in MRI: a preliminary evaluation in gliomas. Magn Reson Imaging 21:983–987CrossRefGoogle Scholar
  56. 56.
    Materka A, Strzelecki M (1998) Texture analysis methods--a review. Tech. Univ. lodz, Inst. Electron. COST B11 report, BrusselsGoogle Scholar
  57. 57.
    Meng X-B, Gao XZ, Liu Y, Zhang H (2015) A novel bat algorithm with habitat selection and Doppler effect in echoes for optimization. Expert Syst Appl 42:6350–6364CrossRefGoogle Scholar
  58. 58.
    Menze BH, Jakab A, Bauer S et al (2014) The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Trans Med Imaging 34:1993–2024CrossRefGoogle Scholar
  59. 59.
    Nayak DR, Dash R, Majhi B et al (2016) Brain MR image classification using two-dimensional discrete wavelet transform and AdaBoost with random forests. Neurocomputing 177:188–197CrossRefGoogle Scholar
  60. 60.
    Nayak DR, Dash R, Majhi B (2018) Discrete ripplet-II transform and modified PSO based improved evolutionary extreme learning machine for pathological brain detection. Neurocomputing 282:232–247CrossRefGoogle Scholar
  61. 61.
    Ozcift A, Gulten A (2011) Classifier ensemble construction with rotation forest to improve medical diagnosis performance of machine learning algorithms. Comput Methods Prog Biomed 104:443–451CrossRefGoogle Scholar
  62. 62.
    Psorakis I, Damoulas T, Girolami MA (2010) Multiclass relevance vector machines: sparsity and accuracy. IEEE Trans Neural Netw 21:1588–1598CrossRefGoogle Scholar
  63. 63.
    Rakotomamonjy A (2003) Variable selection using SVM-based criteria. J Mach Learn Res 3:1357–1370MathSciNetzbMATHGoogle Scholar
  64. 64.
    Ramana Murthy G, Senthil Arumugam M, Loo CK (2009) Hybrid particle swarm optimization algorithm with fine tuning operators. Int J Bio-Inspired Comput 1:14–31CrossRefGoogle Scholar
  65. 65.
    Rhee F-H, Hwang C (2003) An interval type-2 fuzzy K-nearest neighbor. In: fuzzy Syst. 2003. FUZZ’03. 12th IEEE Int. Conf. Pp 802–807Google Scholar
  66. 66.
    Sachdeva J, Kumar V, Gupta I et al (2012) A novel content-based active contour model for brain tumor segmentation. Magn Reson Imaging 30:694–715CrossRefGoogle Scholar
  67. 67.
    Sachdeva J, Kumar V, Gupta I et al (2013) Segmentation, feature extraction, and multiclass brain tumor classification. J Digit Imaging 26:1141–1150CrossRefGoogle Scholar
  68. 68.
    Sachdeva J, Kumar V, Gupta I et al (2016) A package-SFERCB-“segmentation, feature extraction, reduction and classification analysis by both SVM and ANN for brain tumors”. Appl Soft Comput 47:151–167CrossRefGoogle Scholar
  69. 69.
    Sakar CO, Kursun O (2010) Telediagnosis of Parkinson’s disease using measurements of dysphonia. J Med Syst 34:591–599CrossRefGoogle Scholar
  70. 70.
    Shahbaba B, Neal R (2009) Nonlinear models using Dirichlet process mixtures. J Mach Learn Res 10:1829–1850MathSciNetzbMATHGoogle Scholar
  71. 71.
    Shrivastava P, Shukla A, Vepakomma P et al (2017) A survey of nature-inspired algorithms for feature selection to identify Parkinson’s disease. Comput Methods Prog Biomed 139:171–179CrossRefGoogle Scholar
  72. 72.
    Skogen K, Schulz A, Dormagen JB et al (2016) Diagnostic performance of texture analysis on MRI in grading cerebral gliomas. Eur J Radiol 85:824–829CrossRefGoogle Scholar
  73. 73.
    Spadoto AA, Guido RC, Carnevali FL, et al (2011) Improving Parkinson’s disease identification through evolutionary-based feature selection. In: 2011 Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. pp 7857–7860Google Scholar
  74. 74.
    Subashini MM, Sahoo SK, Sunil V, Easwaran S (2016) A non-invasive methodology for the grade identification of astrocytoma using image processing and artificial intelligence techniques. Expert Syst Appl 43:186–196CrossRefGoogle Scholar
  75. 75.
    Subashini MM, Sahoo SK, Sunil V, Easwaran S (2016) A non-invasive methodology for the grade identification of astrocytoma using image processing and artificial intelligence techniques. Expert Syst Appl 43:186–196CrossRefGoogle Scholar
  76. 76.
    Tang X (1998) Texture information in run-length matrices. IEEE Trans Image Process 7:1602–1609CrossRefGoogle Scholar
  77. 77.
    Tencer L, Reznakova M, Cheriet M (2012) A new framework for online sketch-based image retrieval in web environment. In: Inf. Sci. Signal Process. their Appl. Spec. Sess. IEEE, Montreal, QC, pp 1430–1431Google Scholar
  78. 78.
    Tien Bui D, Nguyen QP, Hoang ND, Klempe H (2016) A novel fuzzy K-nearest neighbor inference model with differential evolution for spatial prediction of rainfall-induced shallow landslides in a tropical hilly area using GIS. Landslides 14:1–17CrossRefGoogle Scholar
  79. 79.
    Vidya KS, Ng EY, Acharya UR et al (2015) Computer-aided diagnosis of myocardial infarction using ultrasound images with DWT, GLCM and HOS methods: a comparative study. Comput Biol Med 62:86–93. CrossRefGoogle Scholar
  80. 80.
    Wagner F, Gryanik A, Schulz-Wendtland R et al (2012) 3D characterization of texture: evaluation for the potential application in mammographic mass diagnosis. Biomed Eng (NY) 57:490–493Google Scholar
  81. 81.
    Wang S, Kim S, Chawla S et al (2010) Differentiation between glioblastomas and solitary brain metastases using diffusion tensor imaging. Neuroimage 44:653–660CrossRefGoogle Scholar
  82. 82.
    Wang S, Zhang Y, Dong Z et al (2015) Feed-forward neural network optimized by hybridization of PSO and ABC for abnormal brain detection. Int J Imaging Syst Technol 25:153–164CrossRefGoogle Scholar
  83. 83.
    Xu Y, van Beek EJR, Hwanjo Y et al (2006) Computer-aided classification of interstitial lung diseases via MDCT: 3D adaptive multiple feature method (3D AMFM). Acad Radiol 13:969–978CrossRefGoogle Scholar
  84. 84.
    Yang X-S (2010) A new metaheuristic bat-inspired algorithm. In: Nat. inspired Coop. Strateg. Optim. (NICSO 2010). Springer, pp 65–74Google Scholar
  85. 85.
    Yang M-S, Chen C-H (1998) On the edited fuzzy K-nearest neighbor rule. IEEE Trans Syst Man, Cybern Part B 28:461–466CrossRefGoogle Scholar
  86. 86.
    Yang X-S, Deb S (2009) Cuckoo search via Levy flights. In: Nat. Biol. Inspired Comput. 2009. NaBIC 2009. World Congr. pp 210–214Google Scholar
  87. 87.
    Yang X-S, Deb S (2010) Engineering optimisation by cuckoo search. Int J Math Model Numer Optim 1:330–343zbMATHGoogle Scholar
  88. 88.
    Yang G, Zhang Y, Yang J et al (2016) Automated classification of brain images using wavelet-energy and biogeography-based optimization. Multimed Tools Appl 75:15601–15617CrossRefGoogle Scholar
  89. 89.
    Yilmaz S, Kucuksille EU (2015) A new modification approach on bat algorithm for solving optimization problems. Appl Soft Comput 28:259–275CrossRefGoogle Scholar
  90. 90.
    Zacharaki EI, Wang S, Chawla S, Soo D (2009) Classification of brain tumor type and grade using MRI texture and shape in a machine learning scheme. Magn Reson Med 62:1609–1618CrossRefGoogle Scholar
  91. 91.
    Zhang Y, Wang S, Ji G, Dong Z (2013) An MR brain images classifier system via particle swarm optimization and kernel support vector machine. Sci World J 2013Google Scholar
  92. 92.
    Zhang Y-D, Jiang Y, Zhu W et al (2018) Exploring a smart pathological brain detection method on pseudo Zernike moment. Multimed Tools Appl 77:22589–22604CrossRefGoogle Scholar
  93. 93.
    Zollner FG, Emblem KE, Schad LR (2012) SVM-based glioma grading: optimization by feature reduction analysis. J Med Phys 22:205–214Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Department of Electronics and Communication EngineeringDr B R Ambedkar National Institute of Technology JalandharPunjabIndia
  2. 2.Department of Computer Science and Engineering, University Institute of Engineering and Technology, Sector 25Panjab UniversityChandigarhIndia

Personalised recommendations