Characterization of Human Hippocampus using Textural Analysis in Epileptics patient
Pages : 66-70Download PDF
Hippocampal sclerosis (HS), characterized by selective neuronal loss and reactive gliosis in the hippocampus and other mesial temporal structures, is a common pathologic finding in temporal lobe epilepsy. Epilepsy affects 1–2% of the population, with temporal lobe epilepsy (TLE) the most common variant in adults. Texture analysis can provide useful information about the microstructure of the organ of interest. The objective of this study was to characterize the hippocampal tissues into two classes normal and epileptic. This is experimental study using MRI scanner, the texture were extracted from spatial gray level dependence matrix using a window of 20×20 pixels of angle zero and distance equal one pixel. The images were collected from MRI brain scans for 18 patients represent the classes of the study. A linear discriminant analysis using stepwise were used to classify the sample into the predefined classes. The stepwise selected number of features out of fifteen features as the most discriminant features for each hippocampal region. The result of this study showed that the total classification accuracy was 83.3%, 80.6%, 91.7%, and 79.6% for body, head, tail and sagittal respectively. The sensitivity was 72.2, 72.2, 94.4% and 79.6. The Specificity was 94.4%, 88.92%, 88.9% and 79.6% respectively. This study confirmed that it’s possible to diagnose and differentiate between normal and epileptic hippocampus body, head, tail and sagittal and coronal texturally. The tail of the hippocampus is the most accurate site to differentiate between the classes when using texture extracted from SGLD matrix, due to its rich texture and the several edges with accuracy of 91.7% versus an accuracy of 83.3% , 80.6% and 79.6% for body, head and sagittal respectively. More studies in the hippocampus textural analysis should be carried out using variable widows and texture to improve the accuracy, follow up the epileptic patients after the surgical or drug treatment to ass the progress texturally.
Keywords: Epilepsy, texture analysis