Brain Tumor MRI Image Classification with Feature Selection and Extraction using Linear Discriminant Analysis

Abstract

Feature extraction is a method of capturing visual content of an image. The feature extraction is the process to represent raw image in its reduced form to facilitate decision making such as pattern classification. We have tried to address the problem of classification MRI brain images by creating a robust and more accurate classifier which can act as an expert assistant to medical practitioners. The objective of this paper is to present a novel method of feature selection and extraction. This approach combines the Intensity, Texture, shape based features and classifies the tumor as white matter, Gray matter, CSF, abnormal and normal area. The experiment is performed on 140 tumor contained brain MR images from the Internet Brain Segmentation Repository. The proposed technique has been carried out over a larger database as compare to any previous work and is more robust and effective. PCA and Linear Discriminant Analysis (LDA) were applied on the training sets. The Support Vector Machine (SVM) classifier served as a comparison of nonlinear techniques Vs linear ones. PCA and LDA methods are used to reduce the number of features used. The feature selection using the proposed technique is more beneficial as it analyses the data according to grouping class variable and gives reduced feature set with high classification accuracy.

Big data simulation software for breast cancer growth repository system

“…In addition, a successful method for feature extractions was developed by [21] using en-hanced stochastic learning. Also, another effective method of selection and extraction was presented by [22] and [23] and it identifies cancer into five features namely: white matter, Gary matter, CSF, abnormal and normal area using Linear Discriminant Analysis (LDA). It has been argued that wavelet transform is the best method that can be used for image feature extraction [24].…”

“…It has been argued that wavelet transform is the best method that can be used for image feature extraction [24]. As for the latter, feature selection, it refers to the process of selecting a subsection of relevant features and enhancing the learning process in terms of speed by removing redundant features [22].…”

Automated brain tumor segmentation and classification for MRI analysis system

“…Brain tumor is one of the main leading diseases which causes human death. It has become the second most important cause of death related to children and young adults [1]. Central Brain Tumor Registry of the United States (CBTRUS) reported 64,530 cases of primary brain and central nervous system tumors at the end of 2011 [1].…”

“…It has become the second most important cause of death related to children and young adults [1]. Central Brain Tumor Registry of the United States (CBTRUS) reported 64,530 cases of primary brain and central nervous system tumors at the end of 2011 [1]. This brain tumor is known as a mass that is formed by the accumulation of abnormal cells [2] that grow out of control.…”

The Use of Principal Component Analysis and Logistic Regression in Prediction of Infertility Treatment Outcome

“…Age was significantly correlated with the first two principal components (Zuendorf et al, Analysis and Logistic Regression... 2003). Additionally, the PCA method allows for the selection of characteristics in the magnetic resonance picture study of brain tumors (Pushpa Rathi et al, 2012) or, in conjunction with the 3TP method, in breast cancer diagnostics (Furman-Haran et al, 2014). The technique was used for dimensionality reduction in diagnostics of atherosclerosis from Carotid Artery Doppler Signals (Latifoglu et al, 2008) and in the analysis of electrocardiogram (ECG) signals to diagnose cardiac arrhythmia (Martis et al, 2013).…”