MR-based attenuation correction methods for clinical PET/MR brain imaging

My research interest lies in the application of machine learning for attenuation correction methods in combined Positron Emission Tomography (PET) and Magnetic Resonance Imaging (MRI) for brain imaging.

Attenuation correction is an important challenge in combined PET/MRI. Bone structures, which are prominent in the anatomy of the human head, contribute significantly to the attenuation of the PET photons. Their accurate identification is therefore essential for quantitative brain PET imaging. However, bone is invisible in conventional MRI sequences. Several MR-based attenuation correction methods have been published for PET/MR brain imaging. This project studies the effect of MR-based attenuation correction methods using data acquired on a combined PET/MRI scanner, the Siemens BrainPET.