Artificial intelligence to generate synthetic CT for adaptive particle therapy

Abstract

Recently, Artificial Intelligence (AI) methods for the generation of synthetic computed tomography (sCT) have received significant research attention as an alternative to classical ones (e.g. bulk density assignment, atlas based virtual CT). We present here an overview of these methods for particle therapy (PT) applications, including strategies to replace CT in magnetic resonance imaging (MRI)-based treatment planning and to facilitate cone beam CT (CBCT)-based image-guided adaptive PT.