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

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 proximate 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 + 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 Dataset-66, Dataset-160, and Dataset-255, respectively. For Dataset-255, 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.

[1]  Diógenes Campos,et al.  Real and spurious contributions for the Shannon, Rényi and Tsallis entropies , 2010 .

[2]  Yudong Zhang Non-member,et al.  Exponential wavelet iterative shrinkage thresholding algorithm with random shift for compressed sensing magnetic resonance imaging , 2014 .

[3]  Yudong Zhang,et al.  A Novel Demodulation System Based on Continuous Wavelet Transform , 2015 .

[4]  Constantino Tsallis,et al.  Nonadditive entropy: The concept and its use , 2008, 0812.4370.

[5]  Chun Qi,et al.  From Local Geometry to Global Structure: Learning Latent Subspace for Low-resolution Face Image Recognition , 2015, IEEE Signal Processing Letters.

[6]  Yinghui Kong,et al.  Super-resolution reconstruction face recognition based on multi-level FFD registration , 2013 .

[7]  B. Peterson,et al.  Improving the spectral resolution and spectral fitting of 1H MRSI data from human calf muscle by the SPREAD technique , 2014, NMR in biomedicine.

[8]  Yudong Zhang,et al.  MAGNETIC RESONANCE BRAIN IMAGE CLASSIFICATION BY AN IMPROVED ARTIFICIAL BEE COLONY ALGORITHM , 2011 .

[9]  Amitava Chatterjee,et al.  A Slantlet transform based intelligent system for magnetic resonance brain image classification , 2006, Biomed. Signal Process. Control..

[10]  Constantino Tsallis,et al.  An introduction to nonadditive entropies and a thermostatistical approach to inanimate and living matter , 2014, 1403.5425.

[11]  Daren Yu,et al.  Mechanical equipment fault diagnosis based on redundant second generation wavelet packet transform , 2010, Digit. Signal Process..

[12]  S. Dimauro,et al.  Mitochondrial dysfunction as a neurobiological subtype of autism spectrum disorder: evidence from brain imaging. , 2014, JAMA psychiatry.

[13]  Yudong Zhang,et al.  Exponential wavelet iterative shrinkage thresholding algorithm with random shift for compressed sensing magnetic resonance imaging , 2015 .

[14]  Anne L. Martel,et al.  A Vector Machine Formulation with Application to the Computer-Aided Diagnosis of Breast Cancer from DCE-MRI Screening Examinations , 2013, Journal of Digital Imaging.

[15]  Sudeb Das,et al.  Brain Mr Image Classification Using Multiscale Geometric Analysis of Ripplet , 2013 .

[16]  Daniel Schwarz,et al.  Brain morphometry of MR images for automated classification of first-episode schizophrenia , 2014, Inf. Fusion.

[17]  Constantino Tsallis,et al.  The Nonadditive Entropy Sq and Its Applications in Physics and Elsewhere: Some Remarks , 2011, Entropy.

[18]  Genlin Ji,et al.  An improved reconstruction method for CS-MRI based on exponential wavelet transform and iterative shrinkage/thresholding algorithm , 2014 .

[19]  Mahrokh G. Shayesteh,et al.  Robust algorithm for brain magnetic resonance image (MRI) classification based on GARCH variances series , 2013, Biomed. Signal Process. Control..

[20]  Zhigang Liu,et al.  A new detection approach of transient disturbances combining wavelet packet and Tsallis entropy , 2014, Neurocomputing.

[21]  Shu Liao,et al.  A Markov Random Field Groupwise Registration Framework for Face Recognition , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Yudong Zhang,et al.  AN MR BRAIN IMAGES CLASSIFIER VIA PRINCIPAL COMPONENT ANALYSIS AND KERNEL SUPPORT , 2012 .

[23]  Yudong Zhang,et al.  Classification of Alzheimer Disease Based on Structural Magnetic Resonance Imaging by Kernel Support Vector Machine Decision Tree , 2014 .

[24]  Paulo Mazzoncini de Azevedo Marques,et al.  The Superiority of Tsallis Entropy over Traditional Cost Functions for Brain MRI and SPECT Registration , 2014, Entropy.

[25]  Abdel-Badeeh M. Salem,et al.  Hybrid intelligent techniques for MRI brain images classification , 2010, Digit. Signal Process..

[26]  Zizhu Fan,et al.  Weighted sparse representation for face recognition , 2015, Neurocomputing.

[27]  Chengqi Zhang,et al.  Cost Sensitive Classification in Data Mining , 2010, ADMA.

[28]  Yudong Zhang,et al.  Optimal Multi-Level Thresholding Based on Maximum Tsallis Entropy via an Artificial Bee Colony Approach , 2011, Entropy.

[29]  Guoqing Li,et al.  Tsallis Wavelet Entropy and Its Application in Power Signal Analysis , 2014, Entropy.

[30]  Paul K. Joseph,et al.  Classification of MRI brain images using combined wavelet entropy based spider web plots and probabilistic neural network , 2013, Pattern Recognit. Lett..

[31]  M. Sturzbecher,et al.  Non-extensive entropy and the extraction of BOLD spatial information in event-related functional MRI , 2009, Physics in medicine and biology.

[32]  Latha Parthiban,et al.  A Novel Nature Inspired Fuzzy Tsallis Entropy Segmentation of Magnetic Resonance Images , 2014 .

[33]  Olvi L. Mangasarian,et al.  Multisurface proximal support vector machine classification via generalized eigenvalues , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[34]  M. Sturzbecher,et al.  Generalized relative entropy in functional magnetic resonance imaging , 2009 .

[35]  Muhammad Hussain.  Mammogram Enhancement Using Lifting Dyadic Wavelet Transform and Normalized Tsallis Entropy , 2014, Journal of Computer Science and Technology.

[36]  Yudong Zhang,et al.  Binary PSO with mutation operator for feature selection using decision tree applied to spam detection , 2014, Knowl. Based Syst..

[37]  A. Ben Hamza,et al.  Nonrigid Image Registration Using an Entropic Similarity , 2011, IEEE Transactions on Information Technology in Biomedicine.

[38]  Paul Suetens,et al.  Unsupervised Segmentation, Clustering, and Groupwise Registration of Heterogeneous Populations of Brain MR Images , 2014, IEEE Transactions on Medical Imaging.

[39]  Lalit M. Patnaik,et al.  Classification of magnetic resonance brain images using wavelets as input to support vector machine and neural network , 2006, Biomed. Signal Process. Control..

[40]  P. Diniz,et al.  Brain tissue segmentation using q-entropy in multiple sclerosis magnetic resonance images. , 2010, Brazilian journal of medical and biological research = Revista brasileira de pesquisas medicas e biologicas.

[41]  Yudong Zhang,et al.  A hybrid method for MRI brain image classification , 2011, Expert Syst. Appl..

[42]  Rajeswari Ramasamy,et al.  Brain Tissue Classification of MR Images Using Fast Fourier Transform Based Expectation- Maximization Gaussian Mixture Model , 2011 .