Open AccessMRI Brain Image Segmentation and Detection Using K-NN Classification
Author(s) -
. Venkatesh,
Marco Leo
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1362/1/012073
Subject(s) - artificial intelligence , segmentation , brain tumor , pattern recognition (psychology) , cluster analysis , magnetic resonance imaging , computer science , classifier (uml) , image segmentation , contextual image classification , gray level , image (mathematics) , radiology , medicine , pathology
Detection of brain tumor at an early stage is important to avoid death. Brain tumor arises due to the abnormal growth of the cells. Magnetic Resonance Imaging (MRI) is a computer-based image processing technique used for detecting tumor size, location and shape. In order to classify it is important to segment MRI brain images. In this paper, MRI brain tumor is segmented using k-means clustering algorithm and various features of the segmented tumor was analyzed using Gray level Co-Occurrence matrix (GLCM). These features were used as input for the k-Nearest Neighbour (k-NN) classifier and used for the classification of tumor as Benign or Malignant. The accuracy of the proposed algorithm is 85% respectively.