A combining two ksvm classifiers based on True pixel values and Discrete wavelet transform for mri-based brain tumor detection and Classification

Mohammed, Ali A.; Noaman, Mohammed A.; Azzawi, Hassan M.

doi:10.30684/etj.v40i2.2180

	A combining two ksvm classifiers based on True pixel values and Discrete wavelet transform for mri-based brain tumor detection and Classification
Engineering and Technology Journal
Article 4, Volume 40, Issue 2, 2022, Pages 322-333 PDF (802.5 K)
Document Type: Research Paper
DOI: 10.30684/etj.v40i2.2180
Authors
Ali A. Mohammed^* ¹; Mohammed A. Noaman²; Hassan M. Azzawi¹
¹Electrical Engineering Dept., University of Technology-Iraq, Alsina’a street, 10066 Baghdad, Iraq.
²Electrical Engineering Dept., University of Technology-Iraq, Alsina’a street, 10066 Baghdad, Iraq
Abstract
The studies on brain tumor detection and classification are continuing to improve the specialists’ ability in diagnosis. Magnetic Resonance Imaging (MRI) is one of the most common techniques used to evaluate brain tumors diagnosis. However, brain tumors diagnosis is a difficult process due to congenital malformations and possible errors in diagnosing benign from malignant tumors. Therefore, this research aims to propose an integrated algorithm to classify brain tumors following two stages using the Kernel Support Vector Machine (KSVM) classifier. First stage classifies the tumors as normal and abnormal, and the second classifies abnormal tumors as benign and malignant. The first KSVM employs extraction features by considering the pixel values to classify images as a shape. In contrast, the second KSVM uses the Discrete Wavelet Transform (DWT), followed by the Principal Component Analysis (PCA) technique to extract and reduce features and improve the model performance. Also, K-means clustering algorithm is used to segment, isolate and calculate the tumor area. The KSVM classifiers use two kernels (linear and Radial Basis Function (RBF)). Obtained results showed that the linear kernel achieved 97.5% accuracy and 98.57% accuracy in the first and second classifier, respectively. For all linear classifiers, a 100% sensitivity level is achieved. This work validates the proposed model based on the (K-fold) strategy
Highlights
We have proposed an integrated algorithm to classify brain tumors following two stages. We have used the Kernel Support Vector Machine (KSVM) classifier. The linear kernel achieved 97.5% accuracy and 98.57% accuracy in the first and second classifiers.
Keywords
MRI; SVM; DWT; PCA

References
[1] D. N. Louis et al., the 2016 World Health Organization Classification of Tumors of the Central Nervous System: a summary, Acta Neuropathology., 131 (2016) 803–820. doi: 10.1007/s00401-016-1545-1. [2] E. A. S. El-Dahshan, H. M. Mohsen, K. Revett, and A. B. M. Salem, Computer-aided diagnosis of human brain tumor through MRI: A survey and a new algorithm, Expert Syst. Appl., 41 (2014) 5526–5545. doi: 10.1016/j.eswa.2014.01.021. [3] G. Singh and M. A. Ansari, Efficient detection of brain tumor from MRIs using K-means segmentation and normalized histogram, India Int. Conf. Inf. Process. IICIP 2016 - Proc., 1 (2017). doi: 10.1109/IICIP.2016.7975365. [4] S. Suhas and C. R. Venugopal, MRI image preprocessing and noise removal technique using linear and nonlinear filters, Int. Conf. Electr. Electron. Commun. Comput. Technol. Optim. Tech. ICEECCOT 2017, (2018) 709–712, doi: 10.1109/ICEECCOT.2017.8284595. [5] Y. Shil, SK and Polly, FP and Hossain, Mohammad Arif and Ifthekhar, Md Shareef and Uddin, Mohammad Nasir and Jang, An Improved Brain Detection and Classification Mechanism, in 2017 International Conference on Information and Communication Technology Convergence (ICTC), (2017) 54–57. [6] C. Saha and M. F. Hossain, MRI Brain Tumor Images Classification Using K-Means Clustering, NSCT and SVM, 4th IEEE Uttar Pradesh Sect. Int. Conf. Electr. Comput. Electron. GLA Univ. Mathura, (2017) 329–333. [7] G. Birare and V. A. Chakkarwar, Automated Detection of Brain Tumor Cells Using Support Vector Machine, 2018 9th Int. Conf. Comput. Commun. Netw. Technol. ICCCNT (2018) 1–4. doi: 10.1109/ICCCNT.2018.8494133. [8] S. C. Kumar and H. D. Phaneendra, Categorization of Brain Tumors using SVM with Hybridized Local-Global Features, Proc. 4th Int. Conf. Comput. Methodol. Commun. ICCMC (2020) 311–314, doi: 10.1109/ICCMC48092.2020.ICCMC-00058. [9] D. Jude Hemanth and J. Anitha, Image pre-processing and feature extraction techniques for magnetic resonance brain image analysis, Commun. Comput. Inf. Sci., 350 CCIS (2012) 349–356, doi: 10.1007/978-3-642-35594-3_47. [10] S. Kumar, C. Dabas, and S. Godara, Classification of Brain MRI Tumor Images: A Hybrid Approach, Procedia Comput. Sci., 122 (2017) 510–517, doi: 10.1016/j.procs.2017.11.400. [11] J. F. Nunes and P. M. Moreira, Shape based image retrieval and classification, in 5th Iberian Conference on Information Systems and Technologies, (2010) 1–6. [12] N. Arunkumar et al., K-Means clustering and neural network for object detecting and identifying abnormality of brain tumor, Soft Comput., 23 (2019) 9083–9096. doi: 10.1007/s00500-018-3618-7. [13] T. T. Wong, Performance evaluation of classification algorithms by k-fold and leave-one-out cross validation, Pattern Recognit., 48 (2015) 2839–2846, doi: 10.1016/j.patcog.2015.03.009. [14] Y. Zhang and L. Wu, An MR Brain Images Classifier via Principal Component Analysis and Kernel Support Vector Machine, 130 (2012) 369–388. [15] The Canser Imaging Archive (TCIA), (2021). https://www.cancerimagingarchive.net/. [16] Kaggle Inc., (2019). https://www.kaggle.com/. [17] S. AbdulSaleem and T. Abdul Razak, Survey on Color Image Enhancement Techniques using Spatial Filtering, Int. J. Comput. Appl., 94 (2014) 39–45, doi: 10.5120/16374-5837. [18] M. A. Nanda, K. B. Seminar, D. Nandika, and A. Maddu, A comparison study of kernel functions in the support vector machine and its application for termite detection, Inf., 9 (2018), doi: 10.3390/info9010005. [19] R. Ayachi and N. Ben Amor, Brain tumor segmentation using support vector machines, Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), 5590 LNAI (2009) 736–747, doi: 10.1007/978-3-642-02906-6_63. [20] N. B. Bahadure, A. K. Ray, and H. P. Thethi, Image Analysis for MRI Based Brain Tumor Detection and Feature Extraction Using Biologically Inspired BWT and SVM, Int. J. Biomed. Imaging, (2017), doi: 10.1155/2017/9749108. [21] S. H. Wang et al., Multiple Sclerosis Detection Based on Biorthogonal Wavelet Transform, RBF Kernel Principal Component Analysis, and Logistic Regression, IEEE Access, 4 (2016) 7567–7576, doi: 10.1109/ACCESS.2016.2620996. [22] T. Menaka Devi, G. Ramani, and S. Xavier Arockiaraj, MR Brain Tumor Classification and Segmentation Via Wavelets, 2018 Int. Conf. Wirel. Commun. Signal Process. Networking, WiSPNET (2018) 1–4, doi: 10.1109/WiSPNET.2018.8538643. [23] D.Ravichandran, R. Nimmatoori, and M. G. Ahamad, Mathematical Representations of 1D, 2D and 3D Wavelet Transform for Image Coding, Int. J. Adv. Comput. Theory Eng., 5 (2016) 1–8. [24] N. David, H. Mathieu, N. David, and H. Mathieu, Visual quality of printed surfaces: Study of homogeneity, Vis. Qual. Print. surfaces Study Homog. Proc. SPIE Vol. 9016, Image Qual. Syst. Perform. XI , 9016 (2014) 9016–12. [25] D. Nandi, A. S. Ashour, S. Samanta, S. Chakraborty, M. A. M. Salem, and N. Dey, Principal component analysis in medical image processing: a study, Int. J. Image Min., 1 (2015) 65. doi: 10.1504/ijim.2015.070024. [26] K. Nirmalakumari, H. Rajaguru, and P. Rajkumar, PCA and DWT Based Gene Selection Technique for Classification of Microarray Data, Proc. 3rd Int. Conf. Commun. Electron. Syst. ICCES (2018) 850–854. doi: 10.1109/CESYS.2018.8723961.
Statistics Article View: 410 PDF Download: 539