Semiautomatic segmentation of glioblastoma for radiotherapy treatment plannin

Abstract

During the radiation therapy (RT) process, the treatment is planned and simulated with a treatment planning sys-tem (TPS). Contouring identifies the Planning Treatment Volume (PTV), that is the physical RT treatment vol-ume. PTV of Glioblastoma (GB) includes, after expansion, Gross Tumor Volume (GTV, the tumor) and Clinical Target Volume (CTV, tumor plus edema). GlioCAD, a Computer-Assisted Detection software for contouring gliomas in MRI/DTI, was used to delineate GTV. The dataset included the images of 21 patients undergoing RT for GB. For each patient, we co-registered CT-planning images and diagnostic MRI (16 T1-gad, 6 T2 Flair, 13 Flair Fat Sat), which were used for GlioCAD training and validation. CAD outlined the tumor with good accura-cy, after ruling out in post-processing some false positives. We identified reliable GTVs, suitable for RT require-ments. An evolution of GlioCAD will take into account edema for outlining CTV. The method is promising. Together with a further automatic system for the delineation of organs at risk (OAR) in the brain, the procedure may be helpful for standardization of RT-treatment planning.