An MRI brain disease classification system using PDFB-CT and GLCM with kernel-SVM for medical decision support

• Published in: Multimedia tools and applications Vol. 79; no. 43-44; pp. 32195 - 32224
• Main Authors: Gupta, Yubraj, Lama, Ramesh Kumar, Lee, Sang-Woong, Kwon, Goo-Rak
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.11.2020
• Subjects: Computer Communication Networks; Computer Science; Data Structures and Information Theory; Multimedia Information Systems; Special Purpose and Application-Based Systems; Pyramidal directional filter blank contourlet transform; Contrast-limited adaptive histogram equalization (CLAHE); Gray-level co-occurrence matrix; Probabilistic principal component; Multi-kernel support vector machine
• ISSN: 1380-7501; 1573-7721
• DOI: 10.1007/s11042-020-09676-x

The automatic binary classification of normal and abnormal subjects using magnetic resonance (MR) brain images has made remarkable progress in recent years. This automation method plays a central role in the early evaluation of degenerative brain diseases in patients. In recent years, various new robust classification methods have been proposed based on families of the wavelet transform (WT). These transforms are good at capturing edge points but lack smoothness along the contour of an image. Therefore, instead of using WT in our experiment, we used a pyramid directional filter bank contourlet transform (PDFB-CT). The key characteristic of this transform is that it is likely to manage 2D singularities efficiently, i.e., edges, unlike the wavelets, which deal with point singularities exclusively, and it also efficiently implements a wavelet-like structure using iterative filter banks. Moreover, we passed the outcome obtained from the PDFB-CT to the gray-level co-occurrence matrix (GLCM) to obtain 22 texture features from each MR brain image. Furthermore, we passed these extracted features to random tree embedding (RTE) to transform low-dimensional features to high-dimensional features before passing them to probabilistic principal component analysis (PPCA) for dimensionality reduction. Here, the multi-kernel support vector machine classifier with a grid search CV (to find optimal hyperparameters) method was used to perform binary classification of abnormal and normal images. As a result, our proposed system achieved an area under the receiver operating characteristic (AU-ROC) curve and classification accuracy of 100% for abnormal vs. normal group classification using a ten-fold stratified cross-validation technique. This experiment result exemplifies the significance of our proposed method compared with recently published state-of-the-art techniques, and hence our proposed method can be effectively used by a physician as a support tool for examining a patient’s brain.