This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Search for Publication

Year(s) from:  to 
Keywords (separated by spaces):

Application of pattern recognition techniques to locate the Vim thalamic nucleus based on thalamocortical tractography

Dimitris Bolis, Andras Jakab, Orcun Goksel, Gabor Székely
European Congress on Radiology (ECR)
Vienna, Austria, March 2012


Purpose: During deep brain stimulation and ablative therapies, subcortical structures are targeted by transferring a stereotactical atlas onto the patient’s anatomical images. We hypothesize that diffusion tensor imaging and mapping of thalamocortical connections can serve as surrogate markers of individual anatomy and can be used to predict specific targets in the thalamus. Here we demonstrate the application of a support vector machine (SVM) based tool that is optimized to predict the location of the ventral intermediate nucleus. Methods and Materials: Previously, a 3D atlas of the thalamus was non-linearly matched with an MR template. Anatomical, diffusion tensor MR imaging and probabilistic thalamocortical tractography to 52 cortical and subcortical areas were performed for 40 subjects. We assumed that the volume of the atlas-based Vim nucleus and the same structure of the subjects’ coincides on standardized images in our population and can be used to train an SVM based classifier to predict the boundaries and volume of the Vim. Results: Using thalamocortical connectivity distributions and the distance from the anterior commissure as features, the classifier was able to reproduce the atlas-based location with 84 % sensitivity and 74 % specificity. The resulting maps were able to reproduce the gross borders of the Vim. Conclusion: We have generated patient specific maps that showed the possible boundaries of the Vim nucleus, this tool can be evaluated for neurosurgical targeting. We demonstrated the applicability of this method in cases when purely atlas-based methods might be insufficient, when the anatomy is disrupted (a tumor case) or unknown (pediatric cases).

Link to publisher's page
  author = {Dimitris Bolis and Andras Jakab and Orcun Goksel and Gabor Székely},
  title = {Application of pattern recognition techniques to locate the Vim thalamic nucleus based on thalamocortical tractography},
  booktitle = {European Congress on Radiology (ECR)},
  year = {2012},
  month = {March},
  pages = {C-1991},
  keywords = {}