Purpose: During deep brain stimulation and ablative therapies, subcortical structures are targeted by transferring a stereotactical atlas onto the patients 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).