Modified local ternary patterns technique for brain tumour segmentation and volume estimation from MRI multi-sequence scans with GPU CUDA machine

• Autorzy: Sriramakrishnan Padmanaban , Kalaiselvi Thiruvenkadam , Rajeswaran Rangasami

Identyfikatory

DOI

10.1016/j.bbe.2019.02.002

• Języki publikacji: EN

Abstrakty

EN

The proposed work develops a rapid and automatic method for brain tumour detection and segmentation using multi-sequence magnetic resonance imaging (MRI) datasets available from BraTS. The proposed method consists of three phases: tumourous slice detection, tumour extraction and tumour substructures segmentation. In phase 1, feature blocks and SVM classifier are used to classify the MRI slices into normal or tumourous. Phase 2 contains fuzzy c means (FCM) algorithm to extract the tumour region from slices identified by phase 1. In addition, graphics processing unit (GPU) based FCM method has been implemented for reducing the processing time which is major overhead with FCM processing of MRI volumes. For phase 3, a novel probabilistic local ternary patterns (PLTP) technique is used to segment the tumour substructures based on the probability density value of histogram bins. Quantitative measures such as sensitivity, specificity, accuracy and dice values are used to analyses the performance of the proposed method and compare with state-of-art-methods. As post processing, the tumour volume estimation and 3D visualization were done for analyzing the nature and location of the tumour to the medical experts. Further, the availability of the GPU reduces the processing time up to 18 than serial CPU processing.

Słowa kluczowe

EN

tumour detection; tumour segmentation; support vector machine; fuzzy c means; local ternary patterns; graphics processing unit

PL

wykrywanie guza; segmentacja guza; maszyna wektorów wsparcia; grupowanie rozmyte; programowalny procesor graficzny

• 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. 2
• Strony: 470--487
• Opis fizyczny: Bibliogr. 62 poz., rys., tab., wykr.

Twórcy

autor

Sriramakrishnan Padmanaban

• Department of Computer Applications, Kalasalingam Academy of Research and Education (Deemed to be University), Krishnankovil, Tamil Nadu, India

autor

Kalaiselvi Thiruvenkadam

• Department of Computer Science and Applications, The Gandhigram Rural Institute (Deemed to be University) Tamil Nadu, India

autor

Rajeswaran Rangasami

• Department of Radiology and Imaging Sciences, Sri Ramachandra Medical College, Tamil Nadu, India

Bibliografia

• [1] Isina A, Direkoglu C, Sahc M. Review of MRI-based brain tumor image segmentation using deep learning methods. Proc Comput Sci 2016;102:317–24.
• [2] Gordillo N, Montseny E, Sobrevilla P. State of the art survey on MRI brain tumor segmentation. Magn Reson Imag 2013;31(8):1426–38.
• [3] Dupont C, Betrouni N, Reyns N, Vermandel M. On image segmentation methods applied to glioblastoma: state of art and new trends. IRBM 2016;37(3):131–43.
• [4] Zhao X, Wu Y, Song G, Li Z, Fan Y, Zhang Y. Brain tumor segmentation using a fully convolutional neural network with conditional random fields. Lect Notes Comput Sci 2016;75–87.
• [5] Angulakshmi M, Lakshmi Priya GG. Automated brain tumor segmentation techniques – a review. Int J Imag Syst Technol 2017;27(1):66–77.
• [6] Despotovic I, Goossens B, Philips W. MRI segmentation of the human brain: challenges methods and applications. Comput Math Methods Med 2014;1–23.
• [7] Dubeya YK, Mushrifa MM, Mitra K. Segmentation of brain MR images using rough set based intuitionistic fuzzy clustering. Biocybern Biomed Eng 2016;36(2):413–26.
• [8] 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.
• [9] Rajini H, Hema N, Bhavani R. Classification of MRI brain images using k-nearest neighbor and artificial neural network. Proc 2011 International Conference on Recent Trends in Information Technology. 2011. pp. 563–8.
• [10] Kapas Z, Lefkovits L, Szilagyi L. Automatic detection and segmentation of brain tumor using random forest approach, modeling decisions for artificial intelligence. Lect Notes Comput Sci 2016;9880.
• [11] Mohsena H, El-Dahshanb EA, El-Horbatyd EM, Salemd AM. Classification using deep learning neural networks for brain tumors. Fut Comput Inform J 2018;3(1):68–71.
• [12] Anitha V, Murugavalli S. Brain tumor classification using two-tier classifier with adaptive segmentation technique. IET Comput Vis 2016;10(1):9–17.
• [13] Pereira S, Pinto A, Alves V, Silva CA. Brain tumor segmentation using convolutional neural networks in MRI images. IEEE Trans Med Imag 2016;35(5):1240–51.
• [14] Sivakumar P, Ganeshkumar P. ANFIS based glioma brain tumor classification and retrieval system for tumor diagnosis. Int J Imag Syst Technol 2017;27(2):109–17.
• [15] Ananthi VP, Balasubramaniam P, Kalaiselvi T. A new fuzzy clustering algorithm for the segmentation of brain tumor. Soft Comput 2016;20(12):4859–79.
• [16] Sharma M, Mukharjee S. Brain tumor segmentation using genetic algorithm and Artificial Neural Network Fuzzy Inference System (ANFIS). Adv Intel Syst Comput 2013;329–39.
• [17] Dubey YK, Mushrif MM. FCM clustering algorithms for segmentation of brain MR images. Adv Fuzzy Syst 2016;2016:1–14.
• [18] Kalaiselvi T, Sriramakrishnan P, Somasundaram K. Survey of using GPU CUDA programming model in medical image analysis. Inform Med Unlock 2017;9:133–44.
• [19] David BK, Kaufmann WH. Praise of programming massively parallel processors: a hands-on approach. 2nd ed. Elsevier; 2012. p. 1–514.
• [20] Kumar R, Rani S, Sarkar A, Talukdar FA. GPU-based level set method for MRI brain tumor segmentation using modified probabilistic clustering. Class Clust Biomed Signal Process 2016;1–26.
• [21] Wang L, Li D, Huang S. An improved parallel fuzzy connected image segmentation method based on CUDA. BioMed Eng Online 2016;15(1).
• [22] Chaplot S, Patnaik LM, Jagannathan NR. Classification of magnetic resonance brain images using wavelets as input to support vector machine and neural network. Biomed Signal Process Control 2006;1(1):86–92.
• [23] Al-Tamimi H, Al-Tamimi ASH, Sulong G. A new abnormality detection approach for T1-weighted magnetic resonance imaging brain slices using three planes. Adv Comput 2016;6(1):6–27.
• [24] Thirumurugan P, Shanthakumar P. Brain tumor detection and diagnosis using ANFIS classifier. Int J Imag Syst Technol 2016;26:157–62.
• [25] Nannia L, Brahnam S, Luminia A. Local ternary patterns from three orthogonal planes for human action classification. Expert Syst Appl 2011;38(5):5125–8.
• [26] Abdel-Maksoud E, Elmogy M, RashidAl-Awadi. Brain tumor segmentation based on a hybrid clustering technique. Egypt Inform J 2015;16(1):71–81.
• [27] Bousselham A, Bouattane O, Youssfi M, Raihani A. 3D brain tumor localization and parameter estimation using thermographic approach on GPU. J Therm Biol 2018;71 (January):52–61.
• [28] Ali NA, Cherradi B, Abbassi E, Bouattane O, Youssfi M. GPU fuzzy c-means algorithm implementations: performance analysis on medical image segmentation. Multimed Tools Appl 2018;1–23.
• [29] Dunn JC. A fuzzy relative of the ISODATA process and its use in detecting compact well-separated clusters. J Cybern 1973;3(3):32–57.
• [30] Bezdek JC. Pattern Recognition with Fuzzy Objective Function Algorithms. New York: Plenum Press; 1981. p. 1–256.
• [31] Wu X, Sun J, Fan G, Wang Z. Improved local ternary patterns for automatic target recognition in infrared imagery. Sensors 2015;15(3):6399–418.
• [32] Kistler M, Bonaretti S, Pfahrer M, Niklaus R, Buchler P. The virtual skeleton database: an open access repository for biomedical research and collaboration. J Med Internet Res 2013;15(11):e245.
• [33] Zhao X, Wu Y, Song G, Li Z, Zhang Y, Fan Y. A deep learning model integrating FCNNs and CRFs for brain tumor segmentation. Med Image Anal 2018;43:98–111.
• [34] Landis JR, Koch GG. The measurement of observer agreement for categorical data. Biometrics 1977;33:159–74.
• [35] Abdallah M, Blonski M, Wantz-Mézières S, Gaudeau Y, Taillandier L, Moureaux J. On the relevance of two manual tumor volume estimation methods for diffuse low-grade gliomas. Healthc Technol Lett 2017;1–4.
• [36] Ashikaga R, Araki Y, Ishida O. MRI of head injury using FLAIR. Neuroradiology 1997;39:239–42.
• [37] Sriramakrishnan P, Kalaiselvi T, Nagaraja P, Mukila K. Tumorous slices classification from MRI brain volumes using block based features extraction and random forest classifier. Int J Comput Sci Eng May 2018;6(4):191–6.
• [38] Robert M, Haralick K, Shanmugam K, Dinstein I. Texture features for image classification. IEEE Trans Syst Cybern 1973;SMC-3(6):610–21.
• [39] Menze B, Jakab A, Bauer S, Kalpathy-Cramer J, Farahani K, Kirby J, et al. The multimodal Brain Tumor Image Segmentation Benchmark (BRATS). IEEE Trans Med Imag 2015;34(10):1993–2024.
• [40] 3D Doctor, Software purchased under DST project sanction, Principle Investigator, Dr. T. Kalaiselvi. Department of Computer Science and Applications, Gandhigram Rural Institute; 2010.
• [41] Kalaiselvi T, Karthigai selvi S. A novel wavelet based feature selection to classify abnormal images from T2-w axial head scans. Proc Natl Conf New Horiz Comput Intel Inform Syst (NHCIIS) 2015;1:140–5.
• [42] Kalaiselvi T, Sriramakrishnan P. Brain abnormality detection from MRI of human head scans using the bilateral symmetry property and histogram similarity measures.The 20th International Computer Science and Engineering Conference; IEEE Explore 2016.
• [43] Latif G, Iskandar DNFA, Jaffar A, Butt MM. Multimodal brain tumor segmentation using neighboring image features. J Telecommun Electron Comput Eng 2017;9(2–9):37–42.
• [44] Bauer S, Tessier J, Krieter O, Nolte L, Reyes M. Integrated spatio-temporal segmentation of longitudinal brain tumor imaging studies. Proceedings of Workshops and Challenges in MICCAI-MCV; 2013. p. 122–30.
• [45] Buendia P, Taylor T, Ryan M, John N. A grouping artificial immune netowork for segmenatation of tumor images. Proceedings of Workshops and Challenges in NCI-MICCAI; 2013. p. 1–5.
• [46] Cordier N, Menze B, Delingette HN, Ayache. Patch-based segmentation of brain tissues. Proceedings of Workshops and Challenges in NCIMICCAI; 2013. p. 6–17.
• [47] Demirhan A, Toru M, Guler I. Segmentation of tumor and edema long with healthy tissues of brain using wavelets and neural networks. IEEE J Biomed Health Inform 2015;19 (4):1451–8.
• [48] Doyle S, Vasseur F, Dojat M, Forbes F. Fully automatic brain tumor segmentation from multiple MR sequences using hidden Markov fields and variational EM. Proceedings of Workshops and Challenges in NCI-MICCAI BraTS; 2013. p. 18–22.
• [49] Festa J, Pereira S, Mariz JA, Sousa N, Silva C. Automatic brain tumor segmentation of multi-sequence MR images using random decision forests. Proceedings of Workshops and Challenges in NCI-MICCAI; 2013. p. 23–6.
• [50] Geremia E, Menze BH, Ayache N. Spatial decision forests for glioma segmentation in multi-channel MR images. Proceedings of Workshops and Challenges in MICCAI; 2012. p. 14–8.
• [51] Guo X, Schwartz L, Zhao B. Semi-automatic segmentation of multimodal brain tumor using active contours. Multimod Brain Tumor Segment 2013;27.
• [52] Hamamci A, Kucuk N, Karaman K, Engin K, Unal G, Tumorcut:. Segmentation of brain tumors on contrast enhanced MR images for radiosurgery applications. IEEE Trans Med Imag 2012;31(3):790–804.
• [53] Meier R, Bauer S, Slotboom J, Wiest R, Reyes M. Appearance- and context-sensitive features for brain tumor segmentation. Proceedings of MICCAI BRATS Challenge; 2014. p. 20–6.
• [54] Reza S, Iftekharuddin KM. Multi-class abnormal brain tissue segmentation using texture. Multimod Brain Tumor Segment 2013;38.
• [55] Raviv TR, Leemput KV, Menze BH. Multi-modal brain tumor segmentation via latent atlases. Proceeding MICCAIBRATS. 2012. pp. 64–73.
• [56] Shin HC. Hybrid clustering and logistic regression for multi-modal brain tumor segmentation. Proceedings of Workshops and Challenges in MICCAI; 2012. p. 32–5.
• [57] Subbanna NK, Precup D, Collins DL, Arbel T. Hierarchical probabilistic Gabor and MRF segmentation of brain tumours in MRI volumes. International Conference on Medical Image Computing and Computer-assisted Intervention; 2013. pp. 751–8.
• [58] Taylor T, John N, Buendia P, Ryan M. Map-reduce enabled hidden Markov models for high throughput multimodal brain tumor segmentation. Proceedings of Workshops and Challenges in NCI-MICCAI; 2013. p. 43–6.
• [59] Tustison NJ, Johnson HJ, Rohlfing T, Klein A, Ghosh SS, Ibanez L, et al. Instrumentation bias in the use and evaluation of scientific software: recommendations for reproducible practices in the computational sciences. Front Neurosci 2013;7.
• [60] Zhao L, Sarikaya D, Corso JJ. Automatic brain tumor segmentation with MRF on supervoxels. Multimod Brain Tumor Segment 2013;51.
• [61] Zikic D, Glocker B, Konukoglu E, Criminisi A, Demiralp C, Shotton J, et al. Decision forests for tissue-specific segmentation of high-grade gliomas in multi-channel MR. International Conference on Medical Image Computing and Computer-assisted Intervention – MICCAI 2012, vol. 7512. 2012. pp. 369–76.
• [62] Emblem KE, Nedregaard B, Hald JK, Nome T, Due- Tonnessen P, Bjornerud A. Automatic glioma characterization from dynamic susceptibility contrast imaging: brain tumor segmentation using knowledge-based fuzzy clustering. J Magn Reson Imag 2009;30(1):1–10.

Uwagi

PL

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