Multi-Subject Image Synthesis as a Generative Prior for Single-Subject PET Image Reconstruction

TL;DR

This paper introduces a method to generate diverse pseudo-PET images from multi-subject MRI and PET data, improving image quality and serving as a prior for single-subject PET reconstruction with better detail and noise reduction.

Contribution

The paper presents a novel approach to synthesize realistic pseudo-PET images using deformable registration and averaging, and applies these as a prior in diffusion model-based PET reconstruction.

Findings

Pseudo-PET images have enhanced anatomical detail.

Reconstructed images show reduced noise compared to traditional methods.

Visual quality of PET reconstructions is improved.

Abstract

Large high-quality medical image datasets are difficult to acquire but necessary for many deep learning applications. For positron emission tomography (PET), reconstructed image quality is limited by inherent Poisson noise. We propose a novel method for synthesising diverse and realistic pseudo-PET images with improved signal-to-noise ratio. We also show how our pseudo-PET images may be exploited as a generative prior for single-subject PET image reconstruction. Firstly, we perform deep-learned deformable registration of multi-subject magnetic resonance (MR) images paired to multi-subject PET images. We then use the anatomically-learned deformation fields to transform multiple PET images to the same reference space, before averaging random subsets of the transformed multi-subject data to form a large number of varying pseudo-PET images. We observe that using MR information for registration imbues the resulting pseudo-PET images with improved anatomical detail compared to the originals. We consider applications to PET image reconstruction, by generating pseudo-PET images in the same space as the intended single-subject reconstruction and using them as training data for a diffusion model-based reconstruction method. We show visual improvement and reduced background noise in our 2D reconstructions as compared to OSEM, MAP-EM and an existing state-of-the-art diffusion model-based approach. Our method shows the potential for utilising highly subject-specific prior information within a generative reconstruction framework. Future work may compare the benefits of our approach to explicitly MR-guided reconstruction methodologies.