Study of Techniques used for Medical Image Segmentation and Computation of Statistical Test for Region Classification of Brain MRI

Abstract

This paper explores the possibility of applying techniques for segmenting the regions of med ical image. For this we need to investigate the use of different techniques which helps for detection and classification of image regions. We also discuss some segmentation methods classified by researchers. Region classification is an essential process in the visualizat ion of brain t issues of MRI. Brain image is basically classified into three regions; WM, GM and CSF. The forth region can be called as the tumor region, if the image is not normal. In the paper; Segmentation and characterization of Brain M R image regions using SOM and neuro fuzzy techniques, we integrate Self Organizing Map(SOM) and Neu ro Fu zzy scheme to automatically extract WM, GM , CSF and tumor reg ion of brain MRI image tested on three normal and three abnormal brain M RI images. Now in this paper this scheme is further tested on axial v iew images to classify the regions of brain M RI and compare the results fro m the Keith"s database. Using some statistical tests like accuracy, precision, sensitivity, specificity, positive predictive value, negative predictive value, false positive rate, false negative rate, likelihood ratio positive, likelihood ratio negative and prevalence of disease we calculate the effectiveness of the scheme.

An Amalgam Method To Detect And Classify Brain Tumor Using MRI Images By Fuzzy C Means, Discrete Wavelet Transform and Artificial Neural Network

“…Although the conventional FCM algorithm works well on most noise-free images. It allows gradual memberships of data points to clusters measured as degrees in [0,1]. This gives the flexibility to express that data points can belong to more than one cluster.…”

“…This paper concerns segmentation algorithm based on fuzzy c-means clustering approach an unsupervised pixel classification technique based on iterative approximation to local minima of global objective functions. The statistical test data for the brain MRI image is used for the classification of any brain tumor categories the region growing algorithm introduced in [1]. The Fuzzy C-means algorithm is introduced in [2]- [3] performs segmentation, and then introduces an expert system with defined membership and clustered centroid to locate a landmark tissue by matching them with a prior model.…”

A New Approach for Enhancing Image Retrieval using Neutrosophic Sets

“…This approach is used for finding the local threshold to statistically examine the intensity values of the local neighborhood of each pixel. This method is simple, fast and less computationally intensive and produces good results for segment images [15], and the following algorithm shows the steps of the proposed approach for segmentation in details. Calculate I(i, j) from the homogeneity value of T using the absolute value of difference between intensity g(i, j) and its local mean value.…”

An Advanced Algorithm Combining SVM and ANN Classifiers to Categorize Tumor with Position from Brain MRI Images

“…The segmentation of an MRI image describes notable image regions to attain region(s) of interest (ROI's) like as tumors, edema, legions, necrotic tissues, etc. from brain MRI images [4].…”

“…The primary limitation of this method is finding seed points through manual interaction. The principal component analysis (PCA) algorithm with K-means discussed in [4] can be used to define the tumor class on the basis of some correlated pixel of the MRI images. The increased number of features and samples cause more time to consume and increase inaccuracy in results of PCA based K-means algorithm [5].…”