Deep Learning-Based Attenuation and Scatter Correction of Brain 18F-FDG PET Images in the Image Domain

TL;DR

This paper explores deep learning methods for attenuation and scatter correction of brain 18F-FDG PET images directly in the image domain, aiming to improve quantitative accuracy in PET imaging without relying on additional transmission data.

Contribution

It investigates various input configurations for deep learning-based attenuation and scatter correction in the image domain, advancing methods for PET image correction without transmission scans.

Findings

Deep learning can effectively perform AC in the image domain.

Different input settings impact correction accuracy.

Potential for improved PET quantification without additional scans.

Abstract

Attenuation and scatter correction (AC) is crucial for quantitative Positron Emission Tomography (PET) imaging. Recently, direct application of AC in the image domain using deep learning approaches has been proposed for the hybrid PET/MR and dedicated PET systems that lack accompanying transmission or anatomical imaging. This study set out to investigate deep learning-based AC in the image domain using different input settings.