TY  - JOUR
T1  - Corpus Callosum Classification Using Case Based Reasoning and
Genetic Classifier for the Prediction of Epilepsy from 2D Medical Images
AU - Tamijeselvy, P. AU - Palanisamy, V. AU - Elakkiya, S. 
JO  - Asian Journal of Information Technology
VL  - 12
IS  - 4
SP  - 117
EP  - 125
PY  - 2013
DA  - 2001/08/19
SN  - 1682-3915
DO  - ajit.2013.117.125
UR  - https://makhillpublications.co/view-article.php?doi=ajit.2013.117.125
KW  - Corpus callosum
KW  -epilepsy
KW  -multiscale segmentation
KW  -genetic classification
KW  -shape features
KW  -case based reasoning
AB  - Corpus callosum is a highly visible structure in brain imaging 
  whose function is to connect the left and right hemisphere of the brain. Epilepsy 
  is the sudden alterations in human behavior caused by an electrical discharge 
  from the brain. Such electrical activity that starts from one side of the brain 
  spread to the other side through the corpus callosum. Epilepsy occurs in 2% 
  of the general population and it is the oldest known brain disorder. The traditional 
  classification methods have less average prediction accuracy of 84.15% in diagnosing 
  epilepsy. The proposed technique includes the improved classification approach 
  for the diagnosis of epilepsy. The technique includes the following phases: 
  pre-processing the 2D MR Brain Image using Threshold Interval Method and Min.-Max. 
  Normalization Segmentation of brain image using multiscale segmentation method 
  to obtain the segments of corpus callosum. Multiscale segmentation proves to 
  be better in curvature segmentation with less execution time and 91% of accuracy 
  based on entropy shape features such as corpus callosum bending angle, Genu 
  thickness and Intelligent Quotient (IQ) are extracted from the segmented corpus 
  callosum diagnosis of epilepsy using Case Based Reasoning (CBR) and genetic 
  classification. The performance of the proposed optimized CBR classification 
  reduces the false positive rate. The CBR classification model results in 96.7% 
  of prediction accuracy and the optimized classification approach results in 
  97.3% of prediction accuracy.
ER  -