Pathological Brain Detection Using Weiner Filtering, 2D-Discrete Wavelet Transform, Probabilistic PCA, and Random Subspace Ensemble Classifier

• Published in: Computational Intelligence and Neuroscience Vol. 2017; no. 2017; pp. 1 - 11
• Main Authors: Kwon, Goo-Rak, Choi, Moo-Rak, Kim, Ji-In, Jha, Debesh
• Format: Journal Article
• Language: English
• Published: Cairo, Egypt Hindawi Limiteds 01.01.2017; Hindawi Publishing Corporation; Hindawi; Hindawi Limited; John Wiley & Sons, Inc
• Subjects: Accuracy; Algorithms; Automation; Biomarkers; Brain; Brain - diagnostic imaging; Brain - pathology; Brain Diseases; Brain Diseases - diagnostic imaging; Brain Diseases - pathology; Brain research; Classification; Classifiers; Computer-aided medical diagnosis; Datasets; Diagnosis; Diagnostic systems; Discrete Wavelet Transform; Disease; Engineering; Feature extraction; Fourier transforms; Humans; Image classification; Image enhancement; Image Interpretation, Computer-Assisted; Image Interpretation, Computer-Assisted - methods; Learning algorithms; Machine learning; Magnetic Resonance Imaging; Magnetic Resonance Imaging - methods; Medical examination; Medical imaging; Medical research; Medicine, Experimental; Methods; Neural networks; Neuroimaging; Neuroimaging - methods; Neurology; NMR; Noise reduction; Nuclear magnetic resonance; Principal Component Analysis; Principal components analysis; Probability; Research Article; Sensitivity and Specificity; Soft tissues; Two dimensional models; Wavelet Analysis; Wavelet transforms; Wiener filtering; South Korea
• ISSN: 1687-5265; 1687-5273; 1687-5273
• DOI: 10.1155/2017/4205141

Accurate diagnosis of pathological brain images is important for patient care, particularly in the early phase of the disease. Although numerous studies have used machine-learning techniques for the computer-aided diagnosis (CAD) of pathological brain, previous methods encountered challenges in terms of the diagnostic efficiency owing to deficiencies in the choice of proper filtering techniques, neuroimaging biomarkers, and limited learning models. Magnetic resonance imaging (MRI) is capable of providing enhanced information regarding the soft tissues, and therefore MR images are included in the proposed approach. In this study, we propose a new model that includes Wiener filtering for noise reduction, 2D-discrete wavelet transform (2D-DWT) for feature extraction, probabilistic principal component analysis (PPCA) for dimensionality reduction, and a random subspace ensemble (RSE) classifier along with the K-nearest neighbors (KNN) algorithm as a base classifier to classify brain images as pathological or normal ones. The proposed methods provide a significant improvement in classification results when compared to other studies. Based on 5×5 cross-validation (CV), the proposed method outperforms 21 state-of-the-art algorithms in terms of classification accuracy, sensitivity, and specificity for all four datasets used in the study.