Speaker
Michał Obara
(NCBJ)
Description
Positron Emission Tomography (PET) imaging plays a critical role in clinical diagnostics, including cancer, cardiovascular, and neurological diseases. However, various physical and technical limitations, such as scatter, attenuation, and positron range, require correction to ensure high-quality imaging. Traditional methods, while effective, are computationally intensive, costly, and limited in certain scenarios.
This talk will review different machine learning techniques developed for PET image correction, highlighting their capabilities and potential applications in improving imaging workflows.
