Multi-channeled MR brain image segmentation: A new automated approach combining BAT and clustering technique for better identification of heterogeneous tumors

• Autorzy: Alagarsamy Saravanan , Kamatchi Kartheeban , Govindaraj Vishnuvarthanan , Zhang Y. D. , Thiyagarajan Arunprasath

Identyfikatory

DOI

10.1016/j.bbe.2019.05.007

• Języki publikacji: EN

Abstrakty

EN

Segregation of tumor region in brain MR image is a prominent task that instantly provides easier tumor diagnosis, which leads to effective radiotherapy planning. For decades together, several segmentation methods for a brain tumor have been presented and until now, enhanced tumor segmentation procedure tends to be a challenging task because, MR images are mostly inbred with varied tumor dimensions of disproportioned boundaries. To address this issue, we develop an improved brain image segmentation technique called BAT based Interval Type-2 Fuzzy C-Means (BAT-IT2FCM) clustering. The BAT algorithm is utilized to find out the optimal cluster location from which the clustering operation by Interval Type-2 Fuzzy C-Means (IT2FCM) is performed. The optimal cluster location pointed/identified by the BAT algorithm helps in easing the clustering operation performed by IT2FCM algorithm, and thereby reducing computational complexity. The efficient outcome from BAT-IT2FCM methodology was affirmed using the performance metrics such as computational time, Peak Signal to Noise Ratio, Mean Squared Error, Jaccard Tanimoto Co-efficient Index and Dice Overlap Index. Also, segmentation results of clinical brain MR images produced by the proposed methodology were evaluated with the support from radiologists (Gold Standard). The suggested BAT based fuzzy related clustering produces sensitivity and specificity values of 98.56 ± 1.2 and 97.67 ± 1.3, respectively, which are better than the existing techniques used for brain image segmentation. Heterogeneous tumor types of different grade levels and tissue structures present in the brain MR slices of three different axes are precisely segmented by the proposed methodology for better visualization of oncologists.

Słowa kluczowe

EN

magnetic resonance imaging; bat algorithm; Interval Type-2 Fuzzy C-Means; tumor identification; tissue segmentation

PL

rezonans magnetyczny; algorytm BAT; rozpoznanie guza; segmentacja tkanki

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2019
• Tom: Vol. 39, no. 4
• Strony: 1005--1035
• Opis fizyczny: Bibliogr. 84 poz., rys., tab., wykr.

Twórcy

autor

Alagarsamy Saravanan

• Department of Computer Science and Engineering, Kalasalingam Academy of Research and Education, Anand Nagar, Krishnankoil, Srivilliputur Post-626126, Virudhunagar District, Tamilnadu, India

autor

Kamatchi Kartheeban

• Department of Computer Science and Engineering, Kalasalingam Academy of Research and Education, Anand Nagar, Tamilnadu, India

autor

Govindaraj Vishnuvarthanan

• Department of Biomedical Engineering, Kalasalingam Academy of Research and Education, Anand Nagar, Tamilnadu, India

autor

Zhang Y. D.

• Department of Informatics, University of Leicester, Leicester , United Kingdom

autor

Thiyagarajan Arunprasath

• Department of Electrical and Electronics Engineering, Kalasalingam Academy of Research and Education, Anand Nagar, Krishnankoil, Srivilliputur Post-626126, Virudhunagar District, Tamilnadu, India

Bibliografia

• [1] Abdel-Maksoud E, Elmogy M, Al-Awadi R. Brain tumor segmentation based on a hybrid clustering technique. Egypt Inform J 2015;16(1):71–81.
• [2] Adhikari SK, Sing JK, Basu DK, Nasipuri M. Conditional spatial fuzzy C-means clustering algorithm for segmentation of MRI images. Appl Soft Comput 2015;34 (2):758–69.
• [3] Ahmadvand A, Daliri MR. Improving the runtime of MRF based method for MRI brain segmentation. Appl Math Comput 2015;256(1):808–18.
• [4] Ain Q, Jaffar MA, Choi TS. Fuzzy anisotropic diffusion based segmentation and texture based ensemble classification of brain tumor. Appl Soft Comput 2014;21:330–40.
• [5] Alagarsamy S, Kamatchi K, Govindaraj V, Thiyagarajan A. A Fully automated hybrid methodology using cuckoo-based fuzzy clustering technique for magnetic resonance brain image segmentation. Int J Imaging Syst Technol 2017;27 (4):317–32.
• [6] Anbeek P, Vincken KL, Van Bochove GS, Matthias JP, Osch V, Van der Ground J. Probabilistic segmentation of brain tissue in MR imaging. J Neuro Image 2005;27(4):795–804.
• [7] Andac H, Godze U, Kutlay K, Kayihan E, Nadir K. Tumor-cut: segmentation of brain tumors on contrast enhanced MR images for radio surgery applications. IEEE Trans Med Imaging 2011;31(3):790–804.
• [8] Bezdek JC. Pattern recognition with fuzzy object function algorithm. New York: Springer; 1981.
• [9] Boudraa AO, Bao YG, Dehakb SMR, Grimaud J, Pachai C, Zhu YM. Automated segmentation of multiple sclerosis lesions in multispectral MR imaging using fuzzy clustering. Comput Biol Med 2000;30(1):23–40.
• [10] Cabria I, Gondra I. MRI segmentation fusion for brain tumor detection. Inform Fusion 2017;36:1–9.
• [11] Cerrolaza JJ, Villanueva V, Cabeza R. Hierarchical statistical shape models of multi object anatomical structures: application to brain MRI. IEEE Trans Med Imaging 2012;31 (3):713–23.
• [12] Chen RM, Yang SC, Wang CM. MRI brain tissue classification using unsupervised optimized extenics-based methods. Comput Electr Eng 2017;58:489–501.
• [13] Chen Y, Zhang J, Wang S, Zheng Y. Brain magnetic resonance image segmentation based on an adapted non- local fuzzy c-means method. IET Comput Vis 2012;6 (6):610–25.
• [14] Chinnadurai V, Chandrasekhar GD. Neuro-level set system based segmentation in dynamic susceptibility contrast enhanced and diffusion weighted magnetic resonance images. Pattern Recogn 2012;45(9):3501–11.
• [15] Damodaram R, Valarmathi ML. Phishing website detection and optimization using modified bat algorithm. Int J Eng Res Appl 2012;2(1):870–6.
• [16] De S, Bhattacharyya S, Dutta P. Automatic magnetic resonance image segmentation by fuzzy inter cluster hostility index based genetic algorithm: an application. Appl Soft Comput 2016;47:669–83.
• [17] Demirhan A, Guler I. Combining stationary wavelet transform and self-organizing maps for brain MR image segmentation. Eng Appl Artif Intell 2011;24(2):358–67.
• [18] Demirhan A, Toru M, Guler I. Segmentation of tumor and edema along with healthy tissues of brain using wavelets and neural networks. IEEE J Biomed Health Inform 2015;19 (4):1451–8.
• [19] Egger C, Opfer R, Wang C, Kepp T, Sormani MP, Spies I, et al. MRI FLAIR lesion segmentation in multiple sclerosis: does automated segmentation hold up with manual annotation. Neuro Image: Clin 2017;13:264–70.
• [20] EI-Dahshan ESA, Mohsen HM, Revett K, Abdel-Badeeh Salem M. Computer-aided diagnosis of human brain tumor through MRI: a survey and a new algorithm. Expert Syst Appl 2014;41(11):5526–45.
• [21] Farhi L, Yusuf L, Raza RH. Adaptive stochastic segmentation via energy-convergence for brain tumor in MR images. J Visual Commun Image 2017;46:303–11.
• [22] Faritha Banu A, Chandrasekar C. An optimized approach of modified BAT algorithm to record deduplication. Int J Comput Appl 2013;62(1):10–5.
• [23] Govindaraj V, Murugan PR. A complete automated algorithm for segmentation of tissues and identification of tumor region in T1, T2, and FLAIR brain images using optimization and clustering techniques. Int J Imaging Syst Technol 2014;24(4):313–25.
• [24] Guo P. Brain tissue classification method for clinical decision-support system. Eng Appl Artif Intell 2017;64:232–41.
• [25] Huang GQ, Zhao WJ, Lu QQ. Bat algorithm with global convergence for solving large-scale optimization problem. Appl Res Comput 2013;30(5):1323–8.
• [26] Huang M, Yang W, Wu Y, Jiang J, Chen W, Feng Q. Brain tumor segmentation based on local independent projection-based classification. IEEE Trans Biomed Eng 2014;61(10):2633–45.
• [27] Ilunga-Mbuyamba E, Avina-Cervantes J, Lindner D, Cruz- Aceves I, Arlt F, Chalopin C. Vascular structure identification in intraoperative 3D contrast-enhanced ultrasound data. Sensors 2016;16(4):497.
• [28] Ilunga-Mbuyamba E, Avina-Cervantes JG, Garcia-Perez A, Romero-Troncoso RDA, Aguirre-Ramos H, Cruz-Aceves I, et al. Localized active contour model with background intensity compensation applied on automatic MR brain tumor segmentation. Neuro Comput 2017;220:84–97.
• [29] Ilunga-Mbuyamba E, Cruz-Duarte JM, Avina-Cervantes J, Correa-Cely CR, Lindner D, Chalopin C. Active contours driven by Cuckoo search strategy for brain tumor images segmentation. Expert Syst Appl 2016;56(1):59–68.
• [30] Johnston B, Atkins MS, Anderson M, Mackiewich B. Segmentation of multiple sclerosis lesions in intensity corrected multispectral MRI. IEEE Trans Med Imaging 1996;15(2):154–69.
• [31] Jothi G, Hannah Inbarani H. Hybrid tolerance rough set- firefly for MRI brain based supervised feature selection tumor image classification. Appl Soft Comput 2016;46:639–51.
• [32] Jui SL, Zhang S, Xiong W, Yu F, Fu M, Wang D, et al. Image tumor segmentation with 3-dimensional intracranial structure deformation features. IEEE Intell Syst 2015;11 (2):66–76.
• [33] Kaur N, Sharma N. Medical tumour image segmentation by BAT optimization. Int J Adv Res Ideas Innov Technol 2016;3 (1):662–8.
• [34] Kaur T, Saini BS, Gupta S. A novel feature selection method for brain tumor MR image classification based on the Fisher criterion and parameter-free Bat optimization. Neural Comput Appl 2018;29(8):193–206.
• [35] Kaur T, Saini BS, Gupta S. An optimal spectroscopic feature fusion strategy for MR brain tumor classification using Fisher criteria and parameter-free BAT optimization algorithm. Biocybern Biomed Eng 2018;38(2):409–24.
• [36] Kaya IE, Pehlivanli AC, Sehizhardes EG, Ibrikci T. PCA based clustering for brain tumor segmentation of T1w MRI images. Comput Methods Prog Bio-Med 2017;140:19–28.
• [37] Khan K, Nikov A, Sahai A. A fuzzy bat clustering method for ergonomic screening of office workplaces. Adv Intell Soft Comput 2011;101:59–66.
• [38] Khan K, Ashok S. A comparison of ba, ga, pso, bp and lm for training feed forward neural networks in e-learning context. Int J Intell Syst Appl 2012;7:23–9.
• [39] Khayati R, Vafadusta M, Towhidkhaha F, Nabavi M. Fully automatic segmentation of multiple sclerosis lesions in MRFLAIR brain images using adaptive mixtures method and Markov random field model. Comput Biol Med 2008;38 (3):379–90.
• [40] Khotanlou H, Afrasiabi M. Segmentation of multiple sclerosis lesions in brain MR images using spatially constrained possibility fuzzy C-means classification. J Med Signals Sens 2011;1(3):149–55.
• [41] Kim J, Lenglet C, Duchin Y, Sapiro G, Harel M. Semi automatic segmentation of brain sub cortical structures from high-field MR. IEEE J Biomed Health Inform 2014;18 (5):1678–94.
• [42] Kwan RKS, Evans AC, Pike GB. MRI simulation-based evaluation of image-processing and classification methods. IEEE Trans Med Imaging 1999;18(11):1085–97.
• [43] Lahmiri S. Glioma detection based on multi-fractal features of segmented brain MRI by particle swarm optimization techniques. Biomed Signal Process Control 2017;31:148–55.
• [44] Le M, Delingette H, Kalpathy-Cramer J, Elizabeth Gerstner R, Batchelor T, Unkelbach N, et al. MRI based Bayesian personalization of a tumor growth model. IEEE Trans Med Imaging 2016;35(10):2329–39.
• [45] Ledig C, Heckemann RA, Hammers A, Lopez JA, Virginia FJ, Makropoulos NA, et al. Robust whole-brain segmentation: application to traumatic brain injury. Med Image Anal 2015;21(1):40–58.
• [46] Leemput KV, Colchester A, Maes F, Suetens P, Vandmeulen D. Automated model based tissue classification of MR images of the brain. IEEE Trans Med Imaging 1999;18 (10):897–908.
• [47] Li CL, Goldgof DB, Hall LO. Knowledge based classification and tissue labeling of MR images of human brain. IEEE Trans Med Imaging 1993;12(4):740–50.
• [48] Li Y, Jia F, Qin J. Brain tumor segmentation from multimodal magnetic resonance images via sparse representation. Artif Intell Med 2016;73:1–13.
• [49] Lin JH, Chao CW, Yang CH, Tsai HL. A chaotic levy flight bat algorithm for parameter estimation in nonlinear dynamic biological systems. J Comput Inform Technol 2012;2(2):56–63.
• [50] Liu X, Chen F. Automatic segmentation of 3-D brain MR images by using global tissue spatial structure information. IEEE Trans Appl Super Conduct 2014;24(5):1558–89.
• [51] Lu S, Qiu X, Shi J, Li N, Lu ZH, Chen P, et al. A pathological brain detection system based on extreme learning machine optimized by Bat algorithm. CNS Neurol Disord Drug Targets 2017;16(1):23–9.
• [52] Mahmood Q, Chodorowski A, Persson M. Automated MRI brain tissue segmentation based on mean shift and fuzzy c-means using a priori tissue probability maps. IRBM 2015;36 (3):185–96.
• [53] Manikandan S, Ramar K, Willjuice Iruthayarajan M, Srinivasagan KG. Multilevel thresholding for segmentation of medical brain images using real coded genetic algorithm. Measurement 2014;47:558–68.
• [54] Marichelvam MK, Prabaharam T. A bat algorithm for realistic hybrid flow shop scheduling problems to minimize make span and mean flow time. ICTACT Int J Soft Comput 2012;3(1):428–33.
• [55] Markopoulos A, Gousias IS, Ledig C. Automatic whole brain MRI segmentation of the developing neonatal brain. IEEE Trans Med Imaging 2014;33(9):1818–31.
• [56] Mehmood I, Ejaz N, Sajjad M, Baik SW. Prioritization of brain MRI volumes using medical image perception model and tumor region segmentation. Comput Biol Med 2013;43 (10):1471–2148.
• [57] Moeskops P, Benders MJNL, Chita SM, Kersbergen KJ, Groenendaal F, Linda de Vries S, et al. Automatic segmentation of MR brain images of preterm infants using supervised classification. Neuro Image 2015;118(5):628–41.
• [58] Moreno JC, Prasath VBS, Proença H, Palaniappan K. Fast and globally convex multiphase active contours for brain MRI segmentation. Comput Vis Image Understand 2014;125:237–50.
• [59] Nabizadeh N, Kubat M. Automatic tumor segmentation in single-spectral MRI using a texture-based and contour-based algorithm. Expert Syst Appl 2017;77:1–10.
• [60] Nabizadeh N, Kubat M. Brain tumors detection and segmentation in MR images: Gabor wavelet vs. statistical features. Comput Electr Eng 2015;45:286–301.
• [61] Nan Z, Su R, Stephane L, Qingmin L, Yuemin Z. Kernel feature selection to fuse multispectral MRI images for brain tumor segmentation. Comput Vis Image Understand 2011;115(2):256–69.
• [62] Pereira S, Pinto A, Alves V, Carlos Silva A. Brain tumor segmentation using convolutional neural networks in MRI images. IEEE Trans Med Imaging 2016;5(5):1240–51.
• [63] Perez J, Valdez F, Castillo O. Bat algorithm with parameter adaptation using interval type-2 fuzzy logic for benchmark mathematical function. IEEE Int Conf Intell Syst 2016;16:120–7.
• [64] Puonti O, Iglesias JE, Van Leemput K. Fast and sequence-adaptive whole-brain segmentation using parametric Bayesian modeling. Neuro Image 2016;143:235–49.
• [65] Qiu C, Xiao J, Yu L, Han L, Iqbal MN. A modified interval type-2 fuzzy C-means algorithm with application in MR image segmentation. Pattern Recogn Lett 2013;34 (12):1329–38.
• [66] Rajinikanth V, Satapathy SC, Fernandes SL, Nachiappan S. Entropy based segmentation of tumor from brain MR images – a study with teaching learning based optimization. Pattern Recogn Lett 2017;94:87–95.
• [67] Ramesh B, Mohan VCJ, Reddy VCV. Application of bat algorithm for combined economic load and emission dispatch. Int J Electr Electron Eng Telecommun 2013;2(1):1–9.
• [68] Roy S, Bhattacharyya D, Bandyopadhyay SK, Kim TH. An effective method for computerized prediction and segmentation of multiple sclerosis lesions in brain MRI. Comput Methods Prog Biomed 2017;140:307–20.
• [69] Senthilnath J, Sushant Kulkarni J, Benediktsson A. A novel approach for multispectral satellite image classification based on the Bat algorithm. IEEE Geo Sci Remote Sens Lett 2016;13(4):599–603.
• [70] Sikka K, Sinha N, Singh PK, Mishra AK. A fully automated algorithm under modified FCM framework for improved brain MR image segmentation. Magn Reson Imaging 2009;27(7):994–1004.
• [71] Sompong C, Wongthanavasu S. An efficient brain tumor segmentation based on cellular automata and improved tumor-cut algorithm. Expert Syst Appl 2017;72:231–44.
• [72] Subudhi BN, Thangaraj V, Sankaralingam E, Ghosh A. Tumor or abnormality identification from magnetic resonance images using statistical region fusion based segmentation. Magn Reson Imaging 2016;34(9):1292–304.
• [73] Sucharitha M, Geetha KP. Brain tissue segmentation using fuzzy clustering techniques. Technol Health Care 2015;23 (5):571–80.
• [74] Valverde S, Oliver A, Roura E, González-Villa S, Pareto D, Joan CV, et al. Automated tissue segmentation of MR brain images in the presence of white matter lesions. Med Image Anal 2017;35:446–57.
• [75] Vishnuvarthanan A, Rajasekaran MP, Govindaraj V, Zhang Y, Thiyagarajan A. An automated hybrid approach using clustering and nature inspired optimization technique for improved tumor and tissue segmentation in magnetic resonance brain images. Appl Soft Comput 2017;57:399–426.
• [76] Vishnuvarthanan G, Rajasekaran MP, Subbaraj P, Anitha V. An unsupervised learning method with a clustering approach for tumor identification and tissue segmentation in magnetic resonance brain images. Appl Soft Comput 2016;38:190–212.
• [77] Xia Y, Ji Z, Zhang Y. Brain MRI image segmentation based on learning local variational Gaussian mixture models. Neuro Comput 2016;204:189–97.
• [78] Yang XS. Bat algorithm for multi-objective optimization. Int J Bio-Inspired Comput 2012;3(5):267–74.
• [79] Zacharaki EI, Wang S, Chawla S, Yoo DS, Wolf R, Elias R, et al. Classification of brain tumor type and grade using MRI texture and shape in a machine learning scheme. Magn Reson Med 2009;62(6):1609–18.
• [80] Zarandi MHF, Zarinbal M, Izadi M. Systematic image processing for diagnosing brain tumors: a type-II fuzzy expert system approach. Appl Soft Comput 2011;11 (1):285–94.
• [81] Zhan T, Zhan Y, Liu Z, Xiao L, Wei Z. Automatic method for white matter lesion segmentation based on T1-fluid-b attenuated inversion recovery images. IET Comput Vis 2015;9(4):447–55.
• [82] Zhang J, Wang G. Image matching using a bat algorithm with mutation. Appl Mech Mater 2012;203:88–93.
• [83] Zhao Y, Guo S, Luo M, Liu Y, Bilello M, Li C. An energy minimization method for MS lesion segmentation from T1-w and FLAIR images. Magn Reson Imaging 2016;39:1–6.
• [84] Zijdenbos AP, Forghani R, Evans AC. Automatic 'pipeline' analysis of 3-D MRI data for clinical trials: application to multiple sclerosis. IEEE Trans Med Imaging 2002;21 (10):1280–91.

Uwagi

PL

Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2019).