Generic placeholder image

Current Medical Imaging

Author(s): K. Rajesh Babu*, P.V. Nagajaneyulu and K. Satya Prasad

DOI: 10.2174/1573405616666200712180521

DownloadDownload PDF Flyer Cite As
Brain Tumor Segmentation of T1w MRI Images Based on Clustering Using Dimensionality Reduction Random Projection Technique

Page: [331 - 341] Pages: 11

  • * (Excluding Mailing and Handling)

Abstract

Background: Early diagnosis of a brain tumor may increase life expectancy. Magnetic resonance imaging (MRI) accompanied by several segmentation algorithms is preferred as a reliable method for assessment. The availability of high-dimensional medical image data during diagnosis places a heavy computational burden and a suitable pre-processing step is required for lower- dimensional representation. The storage requirement and complexity of image data are also a concern. To address this concern, the random projection technique (RPT) is widely used as a multivariate approach for data reduction.

Aim: This study mainly focuses on T1-weighted MRI image clustering for brain tumor segmentation with dimension reduction by using the conventional principal component analysis (PCA) and RPT.

Methods: Two clustering algorithms, K-means and fuzzy c-means (FCM) were used for brain tumor detection. The primary study objective was to present a comparison of the two clustering methods between MRI images subjected to PCA and RPT. In addition to the original dimension of 512 × 512, three other image sizes, 256 × 256, 128 × 128, and 64 × 64, were used to determine the effect of the methods.

Results: In terms of average reconstruction, Euclidean distance, and segmentation distance errors, the RPT produced better results than the PCA method for all the clustered images from clustering techniques.

Conclusion: According to the values of performance metrics, RPT supported fuzzy c-means in achieving the best clustering performance and provided significant results for each new size of the MRI images.

Keywords: Dimension reduction, average reconstruction error, euclidean distance, segmentation distance error, random projection technique, principle component analysis, fuzzy c-means, K-means.

Graphical Abstract

[1]
Liu J, Li M, Wang J, Wu F, Liu T, Pan Y. A survey of MRI-based brain tumor segmentation methods. Tsinghua Sci Technol 2014; 19(6): 578-95.
[http://dx.doi.org/10.1109/TST.2014.6961028]
[2]
Masood S, Sharif M, Masood A, Yasmin M, Mudassar A. A survey on medical image segmentation. Curr Med Imaging Rev 2015; 11(1): 3-14.
[http://dx.doi.org/10.2174/157340561101150423103441]
[3]
Harchaoui NE, Ait Kerroum M, Hammouch A, Ouadou M, Aboutajdine D. Unsupervised approach data analysis based on fuzzy possibilistic clustering: application to medical image MRI. Comput Intell Neurosci 2013; 3: 1-12.
[4]
Kaya IE, Pehlivanli AC, Sekizkardes EG, Ibrikci T. PCA based clustering for brain tumor segmentation of T1w MRI images. Comput Meth Prog Biomed 2017; 140: 19-28.
[http://dx.doi.org/10.1016/j.cmpb.2016.11.011]
[5]
Majid A, Khan MA, Yasmin M, Rehman A, Yousafzai A, Tariq U. Classification of stomach infections: A paradigm of convolutional neural network along with classical features fusion and selection. Microsc Res Tech 2020; 83(5): 562-76.
[http://dx.doi.org/10.1002/jemt.23447] [PMID: 31984630]
[6]
Sharif MI, Jian PL, Khan MA, Saleem MA. Active deep neural network features selection for segmentation and recognition of brain tumors using MRI images. Pattern Recogn Lett 2020; 129: 181-9.
[http://dx.doi.org/10.1016/j.patrec.2019.11.019]
[7]
Attique Khan M, Rubab S. Lungs cancer classification from CT images: An integrated design of contrast based classical features fusion and selection. Pattern Recogn Lett 2020; 129: 77-85.
[8]
Rehman A, Khan MA, Mehmood Z, Saba T, Sardaraz M, Rashid M. Microscopic melanoma detection and classification: A framework of pixel-based fusion and multilevel features reduction. Microsc Res Tech 2020; 83(4): 410-23.
[http://dx.doi.org/10.1002/jemt.23429] [PMID: 31898863]
[9]
Khan MA, Sharif M, Akram T, Yasmin M, Nayak RS. Stomach deformities recognition using rank-based deep features selection. J Med Syst 2019; 43(12): 329.
[http://dx.doi.org/10.1007/s10916-019-1466-3] [PMID: 31676931]
[10]
Khan MA, Lali IU, Rehman A, et al. Brain tumor detection and classification: A framework of marker-based watershed algorithm and multilevel priority features selection. Microsc Res Tech 2019; 82(6): 909-22.
[http://dx.doi.org/10.1002/jemt.23238] [PMID: 30801840]
[11]
Nazir M, Khan MA, Saba T. Brain Tumor Detection from MRI images using Multilevel Wavelets. International Conference on Computer and Information Sciences (ICCIS) IEEE. 1-5.
[12]
Sharif M, Tanvir U, Munir EU, Khan MA, Yasmin M. Brain tumor segmentation and classification by improved binomial thresholding and multi-features selection. J Ambient Intell Human Comput 2018; 1-20.
[13]
Majumder S, Anand SA, Javid KA, Katarwar V. Brain tumor segmentation mechanism by using K mean and FCM. IJIRCCE 2016; 4(4): 512-25.
[14]
Madhukumar S, Santhiyakumari N. Evaluation of K-means and fuzzy C-means segmentation on MR images of brain. Egypt J Radiol Nucl Med 2015; 46(2): 475-9.
[15]
Yousefi S, Goldbaum MH, Zangwill LM, Medeiros FA, Bowd C. Recognizing patterns of visual field loss using unsupervised machine learning. Proc SPIE Int Soc Opt Eng 2014; 2014: 90342M.
[http://dx.doi.org/10.1117/12.2043145] [PMID: 25593676]
[16]
Ng SC. Principle Component Analysis to reduce dimension on digital images. Proceeding of the 8th International Conference on Advances in Information Technology. 2016 Dec 19-22; Macau, China. 113-9.
[17]
Jolliffe IT, Cadima J. Principal component analysis: a review and recent developments. Phil Trans R Soc A 2016.
[http://dx.doi.org/10.1098/rsta.2015.0202]
[18]
Bingham E, Mannila H. Random projection in dimensionality reduction: Applications to image and text data. Proceeding of the 7th international conference on knowledge discovery and data mining. 2001 Oct 15-19; 245-50.
[http://dx.doi.org/10.1145/502512.502546]
[19]
Mane DS, Gite BB. Brain tumor segmentation using fuzzy C-Means and K-Means Clustering and its area calculation and disease prediction using naive-bayes algorithm. Proceedings of the conference. In: Chicago: Elsevier ; 2018.
[20]
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: 758-69.
[http://dx.doi.org/10.1016/j.asoc.2015.05.038]
[21]
Brain Web, Simulated Brain Database, McConnell Brain Imaging Centre, Montreal Neurological Institute, McGill 2015. Available from: http://www.bic.mni.mcgill.ca/brainweb
[22]
Menze BJ, Jakab A, Bauer S, et al. The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Trans Med Imaging 2015; 34(10): 1993-2024. Available from: https://www.med.upenn.edu/sbia/brats2015/registration.html-BRaTS
[23]
Subhani SK, Suresh B, Ghali VS. Orthonormal projection approach for depth-resolvable subsurface analysis in non-stationary thermal wave imaging. NDT Int 2016; 58(1): 42-5.
[24]
Cheng Z, Zhixiong LA. Novel efficient feature dimensionality reduction method and its application in engineering. COMPFS 2018; 23: 1-14.
[25]
Viswanath SE, Tiwari P, Lee G, Madabhushi A. Dimensionality reduction-based fusion approaches for imaging and non-imaging biomedical data: concepts, workflow, and use-cases. BMC Med Imaging 2017; 17(1): 1-17.
[PMID: 28056868]
[26]
Zeng G, Zhang B, Yao F, Chai S. Modified bidirectional extreme learning machine with Gram–Schmidt orthogonalization method. Neurocomputing 2018; 316: 405-14.
[http://dx.doi.org/10.1016/j.neucom.2018.08.029]
[27]
Stewart GW. Block Gram–Schmidt orthogonalization. SIAM J Sci Comput 2008; 31(1): 761-75.
[http://dx.doi.org/10.1137/070682563]
[28]
Saunders C, Ed. Random Projection, Margins, Kernels, and Feature-Selection. SLSFS Springer-Verlag Berlin Heidelberg 2006; pp. 52-68.
[29]
Karuna Y, Saladi S, Bhattacharyya B. Brain tissue classification using PCA with hybrid clustering algorithms. Proc Int Conf Res Devel Eng Sci Technol 2018; 2(2.24): 537-41.
[30]
Parsi A, Sorkhi AG, Zahedi M. Improving the unsupervised LBG clustering algorithm performance in image segmentation using principal component analysis. Signal Image Video Process 2016; 10(2): 301-9.
[31]
Sanghamitra T. Brain tumour segmentation using k-means clustering algorithm. Int J Curr 2015; 5(3): 413-22.
[32]
Rodríguez-Méndez IA, Ureña R, Herrera-Viedma E. Fuzzy clustering approach for brain tumor tissue segmentation in magnetic resonance images. Soft Computing 2019; 23(20): 10105-7.
[33]
Kapoor L, Thakur S. A Survey on Brain Tumor Detection Using Image Processing Techniques. Proceedings of 7th international conference on Cloud Computing, Data Science and Engineering - Confluence IEEE, Noida.
[http://dx.doi.org/10.1109/CONFLUENCE.2017.7943218]
[34]
Aslam HA, Ramashri T, Mohammed IAA. A New Approach to Image Segmentation for Brain Tumor detection using Pillar K-means Algorithm. Proceeding of 10th international conference on Computer science. India. 2013; pp. 1429-36.
[35]
Guo L, Chen L, Wu Y, Chen CLP. Image-guided fuzzy C-Means for image segmentation. Proceedings of 2016 International Conference on Fuzzy Theory and Its Applications (iFuzzy) 2016 Nov 9-11; Taichung, Taiwan. 1-6.
[36]
Kumar D, Verma H, Mehra A, Agrawal RK. A modified intuitionistic fuzzy c-means clustering approach to segment human brain MRI image. Multimedia Tools Appl 2019; 78: 12663-87.
[http://dx.doi.org/10.1007/s11042-018-5954-0]