Texture analysis of hippocampus for epilepsy

This paper presents our recent study to evaluate how effectively the image texture information within the hippocampus structure can help the physicians to determine the candidates for epilepsy surgery. First we segment the hippocampus from T1-weighted images using our newly developed knowledge-based segmentation method. To extract the texture features we use multiwavelet, wavelet, and wavelet packet transforms. We calculate the energy and entropy features on each sub-band obtained by the wavelet decomposition. These texture features can be used by themselves or along with other features such as shape and average intensity to classify the hippocampi. The features are calculated on the T1weighted and FLAIR MR images. Using these features, a clustering algorithm is applied to classify each hippocampus. To find the optimal basis, we use several different bases for wavelet and multiwavelet transforms, and compare the final classification performances, which is evaluated by correct classification rate (CCR). We use MRI of 14 epileptic patients along with their EEG results in our study. We use the pre-operative MR images of the patients who have already been determined as candidates for an epilepsy surgery using the gold standard (more costly and painful) methods of EEG phase II study. Experimental results show that the texture features may predict the candidacy for epilepsy surgery. If successful in large population studies, the proposed non-invasive method can replace invasive and costly EEG studies.