Image-derived Prediction of Response to Chemo-radiation in Glioblastoma

Image-derived Prediction of Response to Chemo-radiation in Patients With Glioblastoma

This study seeks to investigate if advanced image-analysis of diagnostic scans, can be used to predict how aggressive brain tumors (glioblastoma) respond to standard chemo- and radiation treatment.

Generally, response prediction models seeks to predict time to an event, e.g. time-to-progression and/or overall survival. The aim of this study is to explore the feasibility of establishing an individualized response model, that, based on several morphologic, physiologic and metabolic parameters extracted from computed tomography (CT), positron emission tomography (PET) and magnetic resonance imaging (MRI), is able to predict the tumor response at the level of an imaging voxel, using machine learning techniques.

Imaging modalities include MRI, PET/CT with 18F-fluroethyltyrosine (18F-FET), and PET/MRI with 64Cu-diacetyl-bis(N4-methylthiosemicarbazone) (64Cu-ATSM).

Inclusion Criteria:

• Histologically confirmed, primary supratentorial glioblastoma (WHO grade IV).

Exclusion Criteria:

• No informed consent can be obtained
• Inability to undergo MRI examination, due to metal implants, pacemaker etc.
• Not eligible for Stupp-regimen