|
The determination of brain tumor margins both during the presurgical planning phase and during surgical resection has long been a challenging task in the therapy of brain tumor patients. I propose a general method of probabilistic margins of the brain tumor. Given n different MRI sequences, I build a voting scheme to determine a probability of a cell to be a tumor cell. It's result provides more realistic view of the patients brain system. Noise and difference of various MRI scans are taken into account. Also it provides a quantitative analysis of the number of tumor cells and the ratio of mutated cells to a healthy cells.
The data for this project was provided by Prof. B. Terwey, Klinikum Mitte, Bremen, Germany as a dataset for IEEE visualization contest.
|