# Artificial Intelligence-Guided PET Image Reconstruction and Multi-Tracer Imaging: Novel Methods, Challenges, And Opportunities

**Authors:** Movindu Dassanayake, Alejandro Lopez, Andrew Reader, Gary J.R. Cook, Clemens Mingels, Arman Rahmim, Robert Seifert, Ian Alberts, Fereshteh Yousefirizi

arXiv: 2509.00304 · 2025-09-05

## TL;DR

This paper discusses the potential of LAFOV PET/CT combined with AI techniques to improve image quality, enable new imaging applications, and address current limitations for clinical use.

## Contribution

It introduces novel AI-guided methods for PET image reconstruction and multi-tracer imaging, highlighting challenges and future opportunities.

## Key findings

- AI can enhance PET image resolution
- LAFOV PET/CT enables ultra-low dose imaging
- Potential for multiplexed and faster imaging

## Abstract

LAFOV PET/CT has the potential to unlock new applications such as ultra-low dose PET/CT imaging, multiplexed imaging, for biomarker development and for faster AI-driven reconstruction, but further work is required before these can be deployed in clinical routine. LAFOV PET/CT has unrivalled sensitivity but has a spatial resolution of an equivalent scanner with a shorter axial field of view. AI approaches are increasingly explored as potential avenues to enhance image resolution.

---
Source: https://tomesphere.com/paper/2509.00304