Glioblastoma Multiforme (GBM) is the most lethal and common brain cancer in adult. Our goal is to quantitatively extract the infiltrating tumor information from imaging. Infiltrative tumor is with low Gd-enhancement and is difficult to identify. To investigate the prevalence and extent of low Gd-enhancement tumor in GBM, we developed an algorithm to automatically segment the low Gd-enhancement region. The method is applied to the GBM collection in The Cancer Imaging Archive (TCIA). The proposed algorithm can robustly segment different components of the tumor including low Gd-enhancement region.
|Original language||English (US)|
|Title of host publication||Proceeding of International Society of Magnetic Resonance in Medicine|
|State||Published - 2015|