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

Keywords

accuracy acknowledgment agent aided alone applied approximately assessing assist assisted automatic background benign better biology boundary brain bright characteristic classification classifier clearly clinically collected computer contrast contributing correlation correspond corresponds creating curve dataset datasets defined delineated delineation detecting differentiating electrical engineering england enhanced enhancement equal error evaluation experienced extent extracted extraction feature features findings fitted five gold grade grant health hypothesis imposed improved included independently indicate induced infiltration injury journal kinetic leave limitation limitations manual maps mechanical medicine model months mortality noise nuclear null often operating orange patient patients performance phenylalanine planning poor positron post potential predict preliminary prior probability project qualitative qualitatively quantitative quantitatively radiation radiology radiotherapy rank received receiver recurrence registered regrowth relatively resection resolution risk rose sample samples school selected selection sensitivity sets significance smart stage statistical strategy suggest supervised survival tagged technology therapy tissue tomography tool trained training useful validated validation wash weeks women world years yield