Multi-Sectional Views Textural Based SVM for MS Lesion Segmentation in Multi-Channels MRIs

Abstract

Abstract:In this paper, a new technique is proposed for automatic segmentation of multiple sclerosis (MS) lesions from brain magnetic resonance imaging (MRI) data. The technique uses a trained support vector machine (SVM) to discriminate between the blocks in regions of MS lesions and the blocks in non-MS lesion regions mainly based on the textural features with aid of the other features. The classification is done on each of the axial, sagittal and coronal sectional brain view independently and the resultant segmentations are aggregated to provide more accurate output segmentation. The main contribution of the proposed technique described in this paper is the use of textural features to detect MS lesions in a fully automated approach that does not rely on manually delineating the MS lesions. In addition, the technique introduces the concept of the multi-sectional view segmentation to produce verified segmentation. The proposed textural-based SVM technique was evaluated using three simulated datasets and more than fifty real MRI datasets. The results were compared with state of the art methods. The obtained results indicate that the proposed method would be viable for use in clinical practice for the detection of MS lesions in MRI.

A Bibliography of Multiple Sclerosis Lesions Detection Methods using Brain MRIs

“…Bassem et al [135] proposed the automatic segmentation of MS by using T1 and T2 images. The preprocessing step consists of intensity correction and registration of MRI.…”

“…Khayati et al [25] 2008 Bayesian FLAIR MSL Harmouche et al [98] 2015 MRF T1, T2, PD, FLAIR T1-HL, T2-HL Shiee et al [97] 2010 FCM T1, T2, PD WHL Harmouche et al [87] 2006 Bayesian + MRF T2-w, PD-w T2 HL Bricq et al [88] 2008 HMM + TLE T1-w, FLAIR MSL Prastawa et al [90] 2008 PDF + MCD T1-w, T2-w, FLAIR MSL At-Ali et al [91] 2005 TLE T1-w, T2-w PD-w T1-HL, T2-HL Gao et al [94] 2013 EnM T1-w, T2-w, FLAIR WML Gong et al [101] 2015 EnM FLAIR MSL Tomas-Fernandez et al [103] 2015 GMM T1, T2, FLAIR MSL Elliott et al [104] 2013 Bayesian + RF FLAIR MSL Gao et al [105] 2014 EnM + BFE T1-w, T2-w, FLAIR MSL Zangeneh et al [113] 2016 GMM + ANN T1-w, T2-w, FLAIR MSL Zhao et al [118] 2017 EnM T1-w, FLAIR MSL Supervised Roy et al [4] 2013 SVM T1-w, T2-w, FLAIR MSL Deshpande et al [128] 2015 ADL T1-w MPRAGE, T2-w, PD, FLAIR MSL, WM, GM Tissues Zhang et al [130] 2007 ANN + KNN T2-w MSL, WM Tissues Cabezas et al [131] 2013 Gentleboost Algorithm PD-w, T2-w HL Cabezas et al [132] 2014 Gentleboost Algorithm T1-w, T2-w, PD-w, FLAIR MSL Guizard et al [146] 2015 RMNMS T1-w, T2-w, FLAIR MSL Jesson et al [133] 2015 MRF + RF T1, T2, FLAIR GML Kuwazuru et al [134] 2012 ANN + levelSet method T1, T2, FLAIR MSL Abdullah et al [135] 2012 SVM T1, T2 MSL Khastavaneh et al [137] 2015 MTANN + FIS T1-w, T2-w, FLAIR HL Veronese et al [138] 2014 SVM DIR GML…”