Optimization driven Deep Convolution Neural Network for brain tumor classification

• Autorzy: Kumar Sharan , Mankame Dattatreya P.

Identyfikatory

DOI

10.1016/j.bbe.2020.05.009

• Języki publikacji: EN

Abstrakty

EN

The classification and segmentation of the tumor is an interesting area that differentiates the tumorous cells and the non-tumorous cells to identify the tumor level. The segmentation from MRI is a challenge because of its varying sizes of images and huge datasets. Different techniques were developed in the literature for brain tumor classification but due to accuracy and ineffective decision making, the existing techniques failed to provide improved classification. This work introduces an optimized deep learning mechanism; named Dolphin-SCA based Deep CNN, to improve the accuracy and to make effective decisions in classification. Initially, the input MRI images are given to the pre-processing and then, subjected to the segmentation process. The segmentation process is carried out using a fuzzy deformable fusion model with Dolphin Echolocation based Sine Cosine Algorithm (Dolphin-SCA). Then, the feature extraction process is performed based on power LDP and statistical features, like mean, variance, and skewness. The extracted features are used in the Deep Convolution Neural Network (Deep CNN) for performing the brain tumor classification with Dolphin-SCA as the training algorithm. The experimentation is performed using the MRI images taken from the BRATS database and SimBRATS, and the proposed technique has shown superior performance with a maximum accuracy of 0.963.

Słowa kluczowe

EN

tumorous cell; MRI images; brain tumor classification; deep convolution neural network; Dolphin-Sine cosine algorithm

PL

komórka nowotworowa; obraz MRI; klasyfikacja guza mózgu; sieć neuronowa konwolucyjna

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2020
• Tom: Vol. 40, no. 3
• Strony: 1190--1204
• Opis fizyczny: Bibliogr. 35 poz., rys., tab., wykr.

Twórcy

autor

Kumar Sharan

• Electronics and Communication Engineering Department, Smt. Kamala & Sri Venkappa M. Agadi College of Engineering & Technology, Lakshmeshwar, VTU-Belagavi

autor

Mankame Dattatreya P.

• Information Science Engineering Department, Smt. Kamala & Sri Venkappa M. Agadi College of Engineering & Technology, Lakshmeshwar, VTU-Belagavi

Bibliografia

• [1] Rajesh T, Malar RSM, Geetha MR. Brain tumor detection using optimization classification based on rough set theory. Cluster Comput 2018;1–7.
• [2] Raju AR, Suresh P, Rao RR. Bayesian HCS-based multi- SVNN: a classification approach for brain tumor segmentation and classification using Bayesian fuzzy clustering. Biocybern Biomed Eng 2018;38(3):646–60.
• [3] Shree NV, Kumar TNR. Identification and classification of brain tumor MRI images with feature extraction using DWT and probabilistic neural network. Brain Inf 2018;5(1):23–30.
• [4] Byale H, Lingaraju GM, Sivasubramanian S. Automatic segmentation and classification of brain tumor using machine learning techniques. Int J Appl Eng Res Dev 2018;13(14):11686–92.
• [5] Saha Sriparna, Alok Abhay Kumar, Ekbal Asif. Brain image segmentation using semi-supervised clustering. Expert Syst Appl 2016;52:50–63.
• [6] Moeskops Pim, Viergever Max A, Mendrik Adriënne M, de Vries Linda S, Benders Manon JNL, Isgum Ivana. Automatic segmentation of MR brain images with a convolutional neural network. IEEE Trans Med Imaging 2016;35(5):1252–61.
• [7] Mekhmoukh Abdenour, Mokrani Karim. Improved fuzzy C-means based Particle Swarm Optimization (PSO) initialization and outlier rejection with level set methods for MR brain image segmentation. Comput Methods Programs Biomed 2015;122(2):266–81.
• [8] Aparajeeta Jeetashree, Nanda Pradipta Kumar, Das Niva. Modified possibilistic fuzzy C-means algorithms for segmentation of magnetic resonance image. Appl Soft Comput 2016;41:104–19.
• [9] Rao CR, Kumar MNVSS, Rao GSB. A novel segmentation algorithm for feature extraction of brain MRI tumor. Information and decision sciences. Springer; 2018. p. 455–63.
• [10] Selvaraj D, Dhanasekaran R. MRI brain image segmentation techniques a review. Indian J Comput Sci Eng 2013;4(5).
• [11] Jayachandran A, KharmegaSundararaj G. Abnormality segmentation and classification of multi-class brain tumor in MR images using fuzzy logic-based hybrid kernel SVM. Int J Fuzzy Syst Appl 2017;3(September):434–43.
• [12] Bahadure NB, Ray AK, Thethi HP. Comparative approach of MRI-based brain tumor segmentation and classification using genetic algorithm. J Digit Imaging 2018;1–13.
• [13] 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 Inf 2015;19:1451–8.
• [14] El-Melegy MT, Mokhtar HM. Tumor segmentation in brain MRI using a fuzzy approach with class center priors. J Image Video Process 2014;21(1):1–14.
• [15] Mirjalili Seyedali. SCA: a sine cosine algorithm for solving optimization problems. Knowledge Based Syst 2016;96 (March):120–33.
• [16] Juan-Albarracín J, Fuster-Garcia E, Manjón JV, Robles M, Aparici F, Martí-Bonmatí L. Automated glioblastoma segmentation based on a multiparametric structured unsupervised classification. PLoS One 2015;10(5).
• [17] Nie J, Xue Z, Liu T, Young GS, Setayesh K, Guo L. Automated brain tumor segmentation using spatial accuracy-weighted hidden markov random field. Comput Med Imaging Graphics 2009;33(6):431–41.
• [18] Pandey P, Singh R, Vatsa M. Face recognition using scattering wavelet under illicit drug abuse variations. Proceedings of the International Conference on Biometrics; 2016. p. 1–6.
• [19] Sauwen N, Acou M, Sima DM, Veraart J, Maes F, Himmelreich U. Semi-automated brain tumor segmentation on multi-parametric MRI using regularized non-negative matrix factorization. BMC Med Imaging 2017;17(1):1–14.
• [20] Dora L, Agrawal S, Panda R, Abraham A. Nested cross-validation based adaptive sparse representation algorithm and its application to pathological brain classification. Expert Syst Appl 2018;114:313–21.
• [21] Li Y, Jia F, Qin J. Brain tumor segmentation from multimodal magnetic resonance images via sparse representation. Artif Intell Med 2016;73:1–13.
• [22] Pourreza R, Zhuge Y, Ning H, Miller R. Brainlesion: glioma multiple sclerosis stroke and traumatic brain injuries, 10670. 2018;p. 320–31.
• [23] St Orr Hans-Peter. A compact fuzzy extension of the naive bayesian classification algorithm. Proceedings on Technology/VJFuzzy; 2002. p. 172–7.
• [24] Borkar Gautam M, Mahajan AR. A secure and trust based on-demand multipath routing scheme for self-organized mobile ad-hoc networks. Wirel Network 2017;23(November (8)):2455–72.
• [25] Menze Bjoern H, Jakab Andras, Bauer Stefan, Kalpathy- Cramer Jayashree, Farahani Keyvan, Kirby Justin, et al. The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Trans Med Imaging 2014;PP(99):1.
• [26] BRATS database. http://www2.imm.dtu.dk/projects/BRATS2012/data.html. [Accessed on April 2018].
• [27] Dahl Anders Bjorholm, Dahl Vedrana Andersen. Dictionary snakes. Proceedings of 22nd IEEE International Conference on Pattern Recognition (ICPR); 2014. p. 142–7.
• [28] Smolka Bogdan, Nurzynska Karolina. Power LBP: a novel texture operator for smiling and neutral facial display classification. Procedia Comput Sci 2015;51:1555–64.
• [29] Sergyan S. Color histogram features based image classification in content-based image retrieval systems. Proceedings of 6th International Symposium on Applied Machine Intelligence and Informatics; 2008. p. 221–4.
• [30] Tu F, Yin S, Ouyang P, Tang S, Liu L, Wei S. Deep convolutional neural network architecture with reconfigurable computation patterns. IEEE Trans Very Large Scale Integr Syst 2017;25(8):2220–33.
• [31] Ferrera Giuseppe, Mortellaro Gianluca, Mannino Mariella, Caminiti Giovanni, Spera Antonio, Figlia Vanessa, et al. Moderate hypofractionation and simultaneous integrated boost by helical tomotherapy in prostate cancer: monoinstitutional report of acute tolerability assessment with different toxicity scales. Radiol Med 2015;120 (December (12)):1170–6.
• [32] Figlia Vanessa, Mazzola Rosario, Cuccia Francesco, Alongi Filippo, Mortellaro Gianluca, Cespuglio Daniela, et al. Hypo- fractionated stereotactic radiation therapy for lung malignancies by means of helical tomotherapy: report of feasibility by a single-center experience. Radiol Med 2018;123(June (6)):406–14.
• [33] Vinolin V. Breast cancer detection by optimal classification using GWO algorithm. Multimedia Res (MR) 2019;2(March (2)):10–8.
• [34] Ghosal Palash, Nandanwar Lokesh, Kanchan Swati, Bhadra Ashok, Chakraborty Jayasree, Nandi Debashis. Brain tumor classification using ResNet-101 based squeeze and excitation deep neural network. The Proceeding of Second International Conference on Advanced Computational and Communication Paradigms (ICACCP); 2019.
• [35] Abiwinanda Nyoman, Hanif Muhammad, Tafwida Hesaputra S, Handayani Astri, Mengko Tati Rajab. Brain tumor classification using convolutional neural network. The Proceeding of World Congress on Medical Physics and Biomedical Engineering 2018;68(1).

Uwagi

PL

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2020).