Abstract #3248

Regularized k-means clustering for segmentation of brain tissues using hemodynamic features in DSC-MRI

Jonathan Arvidsson^1,2, Oscar Jalnefjord^1,2, Fredrik Kahl³, Magnus Båth^1,2, and Göran Starck^1,2

¹Department of Radiation Physics, University of Gothenburg, Gothenburg, Sweden, ²Department of Medical Physics and Biomedical Engineering, Sahlgrenska University Hospital, Gothenburg, Sweden, ³Department of Electical Engineering, Chalmers University of Technology, Gothenburg, Sweden

Inclusion of voxels containing CSF and/or blood vessels can bias ROI statistics used in DSC-MRI analysis. In order to address this problem we propose an automatic method for tissue segmentation based on hemodynamic features obtained from DSC-MRI data. Application of the method in test subjects shows promising results.

This abstract and the presentation materials are available to members only; a login is required.

Join Here