Automated brain tumor segmentation from multimodal MRI data based on Tamura texture feature and an ensemble SVM classifier

Abstract

Purpose The precise segmentation of brain tumors is the most important and crucial step in their diagnosis and treatment. Due to the presence of noise, uneven gray levels, blurred boundaries and edema around the brain tumor region, the brain tumor image has indistinct features in the tumor region, which pose a problem for diagnostics. The paper aims to discuss these issues. Design/methodology/approach In this paper, the authors propose an original solution for segmentation using Tamura Texture and ensemble Support Vector Machine (SVM) structure. In the proposed technique, 124 features of each voxel are extracted, including Tamura texture features and grayscale features. Then, these features are ranked using the SVM-Recursive Feature Elimination method, which is also adopted to optimize the parameters of the Radial Basis Function kernel of SVMs. Finally, the bagging random sampling method is utilized to construct the ensemble SVM classifier based on a weighted voting mechanism to classify the types of voxel. Findings The experiments are conducted over a sample data set to be called BraTS2015. The experiments demonstrate that Tamura texture is very useful in the segmentation of brain tumors, especially the feature of line-likeness. The superior performance of the proposed ensemble SVM classifier is demonstrated by comparison with single SVM classifiers as well as other methods. Originality/value The authors propose an original solution for segmentation using Tamura Texture and ensemble SVM structure.

An assessment of noise variance estimations in Bayes threshold denoising under stationary wavelet domain on brain lesions and tumor MRIs

“…Hill et al (2015) presented a segmentation method of Multiple Sclerosis lesions (MS lesions) in MRI, using an information theoretic approach known as the improved jump method to estimate the transformed distortion rate curve for revealing a distinct signature of the cluster configuration. The work Na et al (2019) employed Tamura texture feature and an ensemble Support Vector Machines (SVM) classifier to automatically segment brain tumor from multimodal MRI data. Deep learning techniques, 2D convolutional neural network (2D-CNN) (Havaei et al, 2017;Zhao et al, 2018) and (Guerrero et al, 2018;Castellazzi et al, 2018) were adopted to build brain lesions/tumor MRIs segmentation.…”