A Bag-of-Features Approach to Predicting TMS Language Mapping Results from DSI Tractography

Mohammad Khatami, Katrin Sakreida, Georg Neuloh und Thomas Schultz
In proceedings of Medical Image Computing and Computer Assisted Intervention (MICCAI), Springer, 2017
 

Abstract

Transcranial Magnetic Stimulation (TMS) can be used to indicate language-related cortex by highly focal temporary inhibition. Diffusion Spectrum Imaging (DSI) reconstructs fiber tracts that connect specific cortex regions. We present a novel machine learning approach that predicts a functional classification (TMS) from local structural connectivity (DSI), and a formal statistical hypothesis test to detect a significant relationship between brain structure and function. Features are chosen so that their weights in the classifier provide insight into anatomical differences that may underlie specificity in language functions. Results are reported for target sites systematically covering Broca's region, which constitutes a core node in the language network.

Bilder

Zusätzliches Material

Bibtex

@INPROCEEDINGS{Khatami:MICCAI2017,
     author = {Khatami, Mohammad and Sakreida, Katrin and Neuloh, Georg and Schultz, Thomas},
      title = {A Bag-of-Features Approach to Predicting TMS Language Mapping Results from DSI Tractography},
  booktitle = {Medical Image Computing and Computer Assisted Intervention (MICCAI)},
     series = {LNCS},
       year = {2017},
  publisher = {Springer},
   abstract = {Transcranial Magnetic Stimulation (TMS) can be used to indicate language-related cortex by highly
               focal temporary inhibition. Diffusion Spectrum Imaging (DSI) reconstructs fiber tracts that connect
               specific cortex regions. We present a novel machine learning approach that predicts a functional
               classification (TMS) from local structural connectivity (DSI), and a formal statistical hypothesis
               test to detect a significant relationship between brain structure and function. Features are chosen
               so that their weights in the classifier provide insight into anatomical differences that may
               underlie specificity in language functions. Results are reported for target sites systematically
               covering Broca's region, which constitutes a core node in the language network.}
}