Conference Paper

Atlas-based segmentation of brain MR images using least square support vector machines

Dept. of Electr. & Electron. Eng., Shiraz Univ. of Technol., Shiraz, Iran
DOI: 10.1109/IPTA.2010.5586779 Conference: Image Processing Theory Tools and Applications (IPTA), 2010 2nd International Conference on
Source: IEEE Xplore

ABSTRACT

This study presents an automatic model based technique for brain tissue segmentation from cerebral magnetic resonance (MR) images. In this paper, support vector machine (SVM) based classifier, as a new and powerful kind of supervised machine learning with high generalization characteristics, is employed. Here, least-square SVM (LS-SVM) in conjunction with brain probabilistic atlas as a priori information is applied to obtain class probabilities for three tissues of cerebrospinal fluid (CSF), white matter (WM) and grey matter (GM). The entire process of brain segmentation is performed in an iterative procedure, so that the probabilistic maps of brain tissues will be updated at any iteration. The quantitative and qualitative results indicate excellent performance of the applied method.

0 Followers
 · 
19 Reads
  • Source
    • "Recent studies show that SVM has been widely used in pattern recognition applications due to its computational efficiency and good generalization performance [6]. Examples of these are classifying and analysis applications in financial study [9]-[10], industry application [11]-[12] and biomedical study [13]-[15]. "
    [Show abstract] [Hide abstract]
    ABSTRACT: One of the primary diagnostic and treatment evaluation tools for brain interpretation has been magnetic resonance imaging (MRI). It has been a widely-used method of high quality medical imaging, especially in brain imaging where MR’s soft tissue contrast and non invasiveness are clear advantages. MR images can also be used to determine a normal and abnormal types of brain. Moreover, the MRI characteristics will help the doctor to avoid the human error in manual interpretation of medical content. Computer-based classification has remained largely experimental work with approaches, one of them is, Support vector machine (SVM). SVM is a pattern recognition algorithm which learns to assign labels to objects through examples. This research paper is an attempt to use SVM to automatically classify brain MRI images under two categories, either normal or abnormal brain which refers to brain tumor. The determination of normal and abnormal brain image is based on symmetry which is exhibited in the axial and coronal images. Using feature vector gained from the MRI images, SVM classifiers are use to classify the images. The process consists of two components which are training phase and a testing phase. Percentage of accuracy on each parameter in SVM will give the idea to choose the best one to be used in further works. Other than that, value of percentage will give the first interpretation either the brain image has the possibility of brain tumor or normal. After all, we are using LabView Advanced Signal Processing Toolkit as the software in our experimental work. We believe with the easiness of this graphical programming and the capabilities of SVM will give a very good result.
    Full-text · Article · May 2011
  • [Show abstract] [Hide abstract]
    ABSTRACT: Magnetic Resonant Image segmentation is an indispensable process in the visualization of human tissues, particularly during clinical analysis. In this paper, we describe a method for segmentation of White matter and Gray matter from real MR images using a LM-k-means technique. After preprocessing, a simple unsupervised clustering system like k-means is taken and made into a supervised system by using Levenberg-Marquardt optimization technique. It was inferred that a k-means system does not arrive on its own at the means which will give a good segmentation. Hence the LM algorithm trains it for that purpose. The results are compared with that of a k-means system and they show a considerable improvement with a much higher precision.
    No preview · Article · Dec 2011
  • [Show abstract] [Hide abstract]
    ABSTRACT: The field of medical imaging gains its importance with increase in the need of automated and efficient diagnosis in a short period of time. One of the primary diagnostic and treatment evaluation tools for brain interpretation has been magnetic resonance imaging (MRI). It has been a widely-used method of high quality medical imaging, especially in brain imaging where MRI's soft tissue contrast and non invasiveness are clear advantages. Classification is an important part in retrieval system. The classifications of brain MRI data as normal and abnormal are important to prune the normal patient and to consider only those who have the possibility of having abnormalities or tumor. This step was done by using support vector machine (SVM). The aim of this paper is to compare percentage of accuracy in classification data with and without the implementation of principal component analysis (PCA). As a result, we found that by using PCA method, the number of feature vector has been reduced from 17689 to 200 and increase the percentage of accuracy.
    No preview · Article · Nov 2011
Show more