Diffusion Tensor Imaging Tractography in Decision Making of Extra Temporal Resective Epilepsy Surgery

Abstract

The main purpose of this paper is to assess the utility of diffusion tensor imaging tractography (DTIT) in decision making in patients considered for extra temporal resective epilepsy surgery. A supervised learning technique is used for the automatic registration and segmentation of white matter tractographies which is extracted from the brain DT-MRI. The supporting structure provides direct registration between the fibers without requiring any intensity based registration algorithms. For the registration purpose Iterative Closest Fiber (ICF) algorithm is used. To improve the precision of the target tract segmentation Probabilistic Boosting Tree (PBT) algorithm is proposed. It acts an important role in predicting postoperative neurological outcomes and assists in surgical decision making and used in pro operative counseling of patients with extra temporal epilepsies.