Abstract #0873

Automatic Classification of High Grade Brain Tumour MRI for Improved Resection & Therapy Planning

Yaniv Gal¹, Stephen Rose², Pierrick Bourgeat³, Nicholas Dowson³, Zeike Taylor⁴, Michael Fay⁵, Paul Thomas⁵, Olivier Salvado³, Stuart Crozier¹

¹School of Information Technology and Electrical Engineering, University of Queensland, Brisbane, Queensland, Australia; ²Centre of Clinical Research, University of Queensland, Brisbane, Queensland, Australia; ³CSIRO, Brisbane, Queensland, Australia; ⁴Department of Mechanical Engineering, The University of Sheffield, Sheffield, Sheffield, United Kingdom; ⁵Royal Brisbane and Womens Hospital, Brisbane, Brisbane, Queensland, Australia

A method for automatic classification of high grade brain tumour MRI for improved resection and therapy planning is proposed. The method is validated qualitatively and quantitatively on MRI and FDOPA PET images and is found to increase the sensitivity of contrast enhanced MRI to high grade brain tumours.