Preclinical Diagnosis of Magnetic Resonance (MR) Brain Images via Discrete Wavelet Packet Transform with Tsallis Entropy and Generalized Eigenvalue Proximal Support Vector Machine (GEPSVM)

Abstract

Abstract:Background: Developing an accurate computer-aided diagnosis (CAD) system of MR brain images is essential for medical interpretation and analysis. In this study, we propose a novel automatic CAD system to distinguish abnormal brains from normal brains in MRI scanning. Methods: The proposed method simplifies the task to a binary classification problem. We used discrete wavelet packet transform (DWPT) to extract wavelet packet coefficients from MR brain images. Next, Shannon entropy (SE) and Tsallis entropy (TE) were harnessed to obtain entropy features from DWPT coefficients. Finally, generalized eigenvalue proximal support vector machine (GEPSVM), and GEPSVM with radial basis function (RBF) kernel, were employed as classifier. We tested the four proposed diagnosis methods (DWPT + SE + GEPSVM, DWPT + TE + GEPSVM, DWPT + SE + GEPSVM + RBF, and DWPT + TE + GEPSVM + RBF) on three benchmark datasets of Dataset-66, Dataset-160, and Dataset-255. Results: The 10 repetition of K-fold stratified cross validation results showed the proposed DWPT + TE + OPEN ACCESSEntropy 2015, 17 1796 GEPSVM + RBF method excelled not only other three proposed classifiers but also existing state-of-the-art methods in terms of classification accuracy. In addition, the DWPT + TE + GEPSVM + RBF method achieved accuracy of 100%, 100%, and 99.53% on , the offline learning cost 8.4430s and online prediction cost merely 0.1059s. Conclusions: We have proved the effectiveness of the proposed method, which achieved nearly 100% accuracy over three benchmark datasets.

Review of Computational Methods on Brain Symmetric and Asymmetric Analysis from Neuroimaging Techniques

“…The morphological asymmetry is associated with functional variations in human brain populations, and some pathology is also strongly linked with abnormalities of brain symmetry/asymmetry [43]. In general, the human brain presents a high level of symmetry, but it is not perfectly symmetrical.…”

A Comparison Study of Kernel Functions in the Support Vector Machine and Its Application for Termite Detection

“…One of the obstacles in the classification process is the dispersion of data tending diversely, so it will be difficult to be separated linearly [33,34]. In this case, SVM introduces the kernel function [35], K(x n , x i ), which transforms the original data space into a new space with a higher dimension; this process includes the transformation function with dot product φ(x) (Equation (6)).…”

Pathological Brain Detection in Magnetic Resonance Imaging Scanning by Wavelet Entropy and Hybridization of Biogeography-Based Optimization and Particle Swarm Optimization

“…Entropy S was a statistical measure of randomness, associated with the order of irreversible processes from a traditional point of view. It was then redefined as as a measure of uncertainty regarding the information content of a system as Shannon entropy [18] as S = − p i log 2 (p i ), where i represents the greylevel of reconstructed coefficient, p i the probability of greylevel of i. Here we treated the subband coefficients as a grayscale image.…”

“…The classification accuracy on both training and test images is 99%, which was significantly good. Zhang et al [18] used discrete wavelet packet transform (DWPT), and harnessed Tsallis entropy (TE) to replace traditional Shannon entropy (SE) with the aim of obtaining features from DWPT coefficients. Then, they used a generalized eigenvalue proximal SVM (GEPSVM).…”

“…We compared the proposed HBP with BP [37], MBP [38], GA [39], SA [40], 2.4.1 [41], BBO [42], PSO [43], and BPSO [50] III. We compared the proposed HBP-FNN with fourteen state-of-the-art classification methods as DWT + PCA + FP-ANN [7], DWT + PCA + KNN [7], DWT + PCA + SCABC-FNN [8], DWT + PCA + SVM + HPOL [11], DWT + PCA + SVM + IPOL [11], DWT + PCA + SVM + GRB [11], WE + SWP + PNN [12], RT + PCA + LS-SVM [14], PCNN + DWT + PCA + BPNN [17], DWPT + SE + GEPSVM [18], DWPT + TE + GEPSVM [18], WE + NBC [19], WEnergy + SVM [22], and SWT + PCA + HPA-FNN [26]. IV.…”