Comparison of 2D and 3D wavelet features for TLE lateralization

Intensity and volume features of the hippocampus from MR images of the brain are known to be useful in detecting the abnormality and consequently candidacy of the hippocampus for temporal lobe epilepsy surgery. However, currently, intracranial EEG exams are required to determine the abnormal hippocampus. These exams are lengthy, painful and costly. The aim of this study is to evaluate texture characteristics of the hippocampi from MR images to help physicians determine the candidate hippocampus for surgery. We studied the MR images of 20 epileptic patients. Intracranial EEG results as well as surgery outcome were used as gold standard. The hippocampi were manually segmented by an expert from T1-weighted MR images. Then the segmented regions were mapped on the corresponding FLAIR images for texture analysis. We calculate the average energy features from 2D wavelet transform of each slice of hippocampus as well as the energy features produced by 3D wavelet transform of the whole hippocampus volume. The 2D wavelet transform is calculated both from the original slices as well as from the slices perpendicular to the principal axis of the hippocampus. In order to calculate the 3D wavelet transform we first rotate each hippocampus to fit it in a rectangular prism and then fill the empty area by extrapolating the intensity values. We combine the resulting features with volume feature and compare their ability to distinguish between normal and abnormal hippocampi using linear classifier and fuzzy c-means clustering algorithm. Experimental results show that the texture features can correctly classify the hippocampi.

[1]  Grégoire Toussaint,et al.  Three dimensional texture analysis in MRI: a preliminary evaluation in gliomas. , 2003, Magnetic resonance imaging.

[2]  P. Reuze,et al.  Performance evaluation of some textural features for muscle tissue classification , 1994, Proceedings of 16th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[3]  Nick C. Fox,et al.  MR image texture analysis applied to the diagnosis and tracking of Alzheimer's disease , 1998, IEEE Transactions on Medical Imaging.

[4]  O. Yu,et al.  Existence of contralateral abnormalities revealed by texture analysis in unilateral intractable hippocampal epilepsy. , 2001, Magnetic resonance imaging.

[5]  C. Jack,et al.  MR‐based hippocampal volumetry in the diagnosis of Alzheimer's disease , 1992, Neurology.

[6]  D. Louis Collins,et al.  On the classification of temporal lobe epilepsy using MR image appearance , 2002, Object recognition supported by user interaction for service robots.

[7]  Gabriela Castellano,et al.  Texture Analysis of Hippocampal Sclerosis , 2003, Epilepsia.

[8]  J Chambron,et al.  Detection of late epilepsy by the texture analysis of MR brain images in the lithium-pilocarpine rat model. , 2002, Magnetic resonance imaging.

[9]  Hamid Soltanian-Zadeh,et al.  Texture analysis of hippocampus for epilepsy , 2003, SPIE Medical Imaging.

[10]  L. Schad,et al.  MR tissue characterization of intracranial tumors by means of texture analysis. , 1993, Magnetic resonance imaging.

[11]  R. Grebe,et al.  Quantitative evaluation of trabecular bone structure by calcaneus MR images texture analysis of healthy volunteers and osteoporotic subjects , 2001, 2001 Conference Proceedings of the 23rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[12]  M. Petrou,et al.  Texture features that correlate with the mini mental state examination (MMSE) score , 2001, 2001 Conference Proceedings of the 23rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[13]  E Le Rumeur,et al.  MRI texture analysis on texture test objects, normal brain and intracranial tumors. , 2003, Magnetic resonance imaging.

[14]  S. Mallat.  A wavelet tour of signal processing , 1998 .

[15]  P. Gloor,et al.  MRI volumetric measurement of amygdala and hippocampus in temporal lobe epilepsy , 1993, Neurology.

[16]  E Le Rumeur,et al.  Comparison of automated and visual texture analysis in MRI: characterization of normal and diseased skeletal muscle. , 1999, Magnetic resonance imaging.