This study introduces POUR-Net, a population-prior-aided over-under-representation network for generating high-quality attenuation maps from low-dose PET scans. The aim is to minimize radiation exposure in PET imaging, which is a prevalent concern. The POUR-Net model incorporates an over-under-representation network (OUR-Net) for efficient feature extraction and a population prior generation machine (PPGM) that provides additional prior information. This method shows promising results for accurate CT-free low-count PET attenuation correction, surpassing previous methods.
Publication date: 26 Jan 2024
Project Page: Not provided
Paper: https://arxiv.org/pdf/2401.14285
