Identification and classification of brain tumor through mixture model based on magnetic resonance imaging segmentation and artificial neural network

Abstract

Detection of brain tumor in Magnetic Resonance Imaging (MRI) is vital as it delivers data about unusual tissues which is essential for planning treatment. Automating this method is challenging due to the high variety in appearance of tumor tissue among dissimilar patients and in many circumstances, comparison between tumor and normal tissue. In this article, we presented a mixture model based segmentation and classification of brain MRI for tumor identification. The proposed robust mixture estimator combining trimming of the outliers is based on component wise confidence level ordering of observations. The proposed method consists of three stages. In the first stage, the brain MRI is segmented into white matter (WM), gray matter (GM), Cerebrospinal fluid (CSF), and outliers by ordering of observations. In second stage, outliers consists of tumor cells in which eight type of features Contrast, Correlation, Homogeneity, Energy, Entropy, Standard deviation, Skewness, and Kurtosis are extracted. In the third stage, the extracted features are trained by Artificial Neural Network (ANN)and based on this a brain tumor identification scheme is established to examine those features to judge whether brain tumor is present in the given image or not. Experimental results indicate that the proposed classification method has achieved 93.47% in sensitivity, 100% in specificity, and 96.34% accuracy with less computational time based on the number of extracted features when compared to earlier classification methods.

from # All Medicine by Alexandros G. Sfakianakis via Alexandros G.Sfakianakis on Inoreader http://ift.tt/2tz6JUc
via IFTTT