Novel Method for Automatic Segmentation of Infiltrative Glioblastoma
Kelvin Wong 1,2 and Stephen Wong 1,2
Department of Systems Medicine and
Bioengineering, Houston Methodist Research Institute,
Houston, TX, United States,
of Radiology, Weill Cornell Medical College, New York,
NY, United States
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.
This abstract and the presentation materials are available to members only;
a login is required.