Automated segmentation and classification of brain stroke using expectation-maximization and random forest classifier

• Autorzy: Subudhi Asit , Dash Manasa , Sabut Sukanta

Identyfikatory

DOI

10.1016/j.bbe.2019.04.004

• Języki publikacji: EN

Abstrakty

EN

Magnetic resonance imaging (MRI) is effectively used for accurate diagnosis of acute ischemic stroke. This paper presents an automated method based on computer aided decision system to detect the ischemic stroke using diffusion-weighted image (DWI) sequence of MR images. The system consists of segmentation and classification of brain stroke into three types according to The Oxfordshire Community Stroke Project (OCSP) scheme. The stroke is mainly classified into partial anterior circulation syndrome (PACS), lacunar syndrome (LACS) and total anterior circulation stroke (TACS). The affected part of the brain due to stroke was segmented using expectation-maximization (EM) algorithm and the segmented region was then processed further with fractional-order Darwinian particle swarm optimization (FODPSO) technique in order to improve the detection accuracy. A total of 192 scan of MRI were considered for the evaluation. Different morphological and statistical features were extracted from the segmented lesions to form a feature set which was then classified with support vector machine (SVM) and random forest (RF) classifiers. The proposed system efficiently detected the stroke lesions with an accuracy of 93.4% using RF classifier, which was better than the results of the SVM classifier. Hence the proposed method can be used in decision-making process in the treatment of ischemic stroke.

Słowa kluczowe

EN

brain stroke; magnetic resonance imaging; expectation-maximization; OCSP scheme; random forest classifier

PL

udar mózgu; rezonans magnetyczny; algorytm EM; las losowy

• 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. 1
• Strony: 277--289
• Opis fizyczny: Bibliogr. 40 poz., rys., tab., wykr.

Twórcy

autor

Subudhi Asit

• Department of ECE, ITER, SOA Deemed to be University, Odisha, India

autor

Dash Manasa

• Department of Mathematics, Silicon Institute of Technology, Bhubaneswar, Odisha, India

autor

Sabut Sukanta

• School of Electronics Engineering, KIIT Deemed to be University, Bhubaneswar, Odisha 751031, India

Bibliografia

• [1] Bonita R. Epidemiology of stroke. Lancet 1992;339:342–4.
• [2] Seghier ML, Ramlackhansingh A, Crinion J, Leff AP, Price CJ. Lesion identification using unified segmentation-normalization models and fuzzy clustering. Neuroimage 2008;41:1253–66.
• [3] Wilke M, de Haan B, Juenger H, Karnath HO. Manual, semi-automated, and automated delineation of chronic brain lesions: a comparison of methods. Neuroimage 2011;56:2038–46.
• [4] Sezgin M, Sankur B. Survey over image thresholding techniques and quantitative performance evaluation. J Electron Imaging 2004;13:146–68.
• [5] Lutsep HL, Albers GW, DeCrespigny A, Kamat GN, Marks MP, Moseley ME. Clinical utility of diffusion-weighted magnetic resonance imaging in the assessment of ischemic stroke. Ann Neurol 1997;41:574–80.
• [6] Alpert S, Galun M, Brandt A, Basri R. Image segmentation by probabilistic bottom-up aggregation and cue integration. IEEE Trans Pattern Anal Mach Intell 2012;34:315–27.
• [7] Carson C, Belongie S, Greenspan H, Malik J. Blobworld: image segmentation using expectation-maximization and its application to image querying. IEEE Trans Pattern Anal Mach Intell 1999;24:1026–38.
• [8] Alipour S, Shanbehzadeh J. Fast automatic medical image segmentation based on spatial kernel fuzzy c-means on level set method. Mach Vision Appl 2014;25(6):1469–88.
• [9] Zotina A, Simonov K, Kurako M, Hamad Y, Kirillova S. Edge detection in MRI brain tumor images based on fuzzy C-means clustering. Procedia Comput Sci 2018;126:1261–70.
• [10] Maier O, Wilms M, von der Gablentz J, Kramer UM, Munte TF, Handels H. Extra tree forests for sub-acute ischemic stroke lesion segmentation in MR sequences. J Neurosci Methods 2015;240:89–100.
• [11] Pustina D, Coslett HB, Turkeltaub PE, Tustison N, Schwartz MF, Avants B. Automated segmentation of chronic stroke lesions using LINDA: lesion identification with neighborhood data analysis. Hum Brain Mapp 2016;37:1405–21.
• [12] Tsai JZ, Peng SJ, Chen YW, et al. Automatic detection and quantification of acute cerebral infarct by fuzzy clustering and histographic characterization on diffusion weighted MR imaging and apparent diffusion coefficient map. BioMed Res Int 2014;1–13.
• [13] Dempster AP, Laird NM, Rubin DB. Maximum likelihood from incomplete data via the EM algorithm. J Royal Stat Soc 1997;39(1):1–38.
• [14] Yoon UC, Kim JS, Kim IY, Kim SI. Adaptable fuzzy C-Means for improved classification as a preprocessing procedure of brain parcellation. J Digit Imaging 2001;14:238–40.
• [15] Lorenzo-Valdes M, Sanchez-Ortiz GI, Elkington AG, Mohiaddin RH, Rueckert D. Segmentation of 4D cardiac MR images using a probabilistic atlas and the EM algorithm. Med Image Anal 2004;8(3):255–65.
• [16] Sundberg R. An iterative method for solution of the likelihood equations for incomplete data from exponential families. Commun Stat Simul Comput 1976;5(1):55–64.
• [17] Niu M, Zhao Q, Li H. Comparison of EM-based algorithms and image segmentation evaluation. In: Huang DS, Jo KH, Wang L, editors. Intelligent computing methodologies. Lecture notes in Computer Science. 2014. p. 8589.
• [18] Huang ZK, Liu DH. Segmentation of color image using EM algorithm in HSV color space. Proc Int Conf on Information Acquisition; 2007.
• [19] Mahjoub MA, Kalti K. Image segmentation by adaptive distance based on EM algorithm. Int J Adv Comp Sci Appl 2011.
• [20] Marroquin JL, Vemuri BC, Botello S, Calderon E, Fernandez- Bouzas A. An accurate and efficient Bayesian method for automatic segmentation of brain MRI. IEEE Trans Med Imaging 2002;21(8):934–45.
• [21] Tian G, Xia Y, Zhang Y, Feng D. Hybrid genetic and variational expectation-maximization algorithm for Gaussian-mixture-model-based brain MR image segmentation. IEEE Trans Inf Technol Biomed 2011;15 (3):373–80.
• [22] Prakash M, Kumari RS. Spatial Fuzzy C means and expectation maximization algorithms with bias correction for segmentation of MR brain images. J Med Syst 2017;41 (1):1–9.
• [23] Kwon GR, Basukala D, Lee SW, Lee KH, Kang M. Brain image segmentation using a combination of expectation-maximization algorithm and watershed transform. Int J Imaging Syst Technol 2016;26(3):225–32.
• [24] Rouainia M, Medjram MS, Doghmane N. Brain MRI segmentation and lesions detection by EM algorithm. Int J Med Health Sci 2008;2(12):379–82.
• [25] Bamford J, Sandercock P, Burn M, Warlow JC. Classification and natural history of clinically identifiable subtypes of cerebral infarction. Lancet 1991;337:1521–6.
• [26] Gupta M, Chen Y. Theory and use of the EM algorithm. Found Trends Signal Process 2010;4(3):223–96.
• [27] Carson C, Belongie S, Greenspan H, Malik J. Blobworld: image segmentation using expectation-maximization and its application to image querying. IEEE Trans Pattern Anal Mach Intell 1999;24(8):1026–38.
• [28] Ghamisi P, Couceiro MS, Benediktsson JA, Ferreira N. An efficient method for segmentation of images based on fractional calculus and natural selection. Expert Syst 2012;39(16):12407–1.
• [29] Subudhi A, Sahoo S, Biswal P, Sabut S. Segmentation and classification of ischemic stroke using optimized features in brain MRI. Biomed Eng: Appl Basis Commun 2018;30 (3):1850011.
• [30] Haralick RM, Shanmugam K, Dinstein I. Textural features for image classification. IEEE Trans Syst Man Cybern 1973; SMC-3(6):610–21.
• [31] Breiman L. Random forests. Mach Learn 2001;45(1):5–32.
• [32] Quinlan JR. Induction of decision trees. Mach Learn 1986;1 (1):81–106.
• [33] Assia C, Yazid C, Said M. Segmentation of brain MRIs by support vector machine: detection and characterization of strokes. J Mech Med Biol 2015;15(5):1–23.
• [34] Subudhi AK, Jena SS, Sabut SK. Delineation of the ischemic stroke lesion based on watershed and relative fuzzy connectedness in brain MRI. Med Biol Eng Comput 2018;56 (5):795–807.
• [35] Muda AF, Saad NM, Abu-Bakar SR, Muda AS, Abdullah AR. Brain lesion segmentation using fuzzy C-means on diffusion-weighted imaging. ARPN J Eng Appl Sci 2015;10 (3):1138–44.
• [36] Griffis JC, Allendorfer JB, Szaflarski JP. Voxel-based Gaussian naive Bayes classification of ischemic stroke lesions in individual T1-weighted MRI scans. J Neurosci Methods 2016;257:97–108.
• [37] Mitra J, Bourgeat P, Fripp J, Ghose S, Rose S, Salvado O, Connelly A, Campbell B, Palmer S, Sharma G, Christensen S, Carey L. Lesion segmentation from multimodal MRI using random forest following ischemic stroke. Neuroimage 2014;98:324–35.
• [38] Kamal H, Lopez V, Sheth SA. Machine learning in acute ischemic stroke neuroimaging. Front Neurol 2018;9:945.
• [39] Raghavendra U, Fujita H, Bhandary SV, Gudigara A, Hong JJ, Tan JH, Acharya UR. Deep convolution neural network for accurate diagnosis of glaucoma using digital fundus images. Inf Sci 2018;441:41–9.
• [40] Maier O, Wilms M, Gablentz J, Kramer U, Handels H. Ischemic stroke lesion segmentation in multi-spectral MR images with support vector machine classifiers. SPIE Medical Imaging Computer-Aided Diagnosis 2014;9035.

Uwagi

PL

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