Direct3{\gamma}: A Pipeline for Direct Three-gamma PET Image Reconstruction

TL;DR

This paper introduces Direct3γ, a new pipeline for 3-γ PET image reconstruction that improves spatial resolution and noise reduction by combining Monte Carlo simulations, CNN refinement, and adversarial training.

Contribution

It presents a novel reconstruction pipeline that determines photon interaction order and enhances image quality using deep learning, outperforming conventional PET methods.

Findings

Outperforms conventional 200-ps TOF PET in SSIM and PSNR.

Uses a model trained on Monte Carlo simulations to determine interaction order.

Employs a 3-D CNN with adversarial loss for image refinement.

Abstract

This paper presents a novel image reconstruction pipeline for three-gamma (3-{\gamma}) positron emission tomography (PET) aimed at improving spatial resolution and reducing noise in nuclear medicine; the proposed Direct3{\gamma} pipeline addresses the inherent challenges in 3-{\gamma} PET systems, such as detector imperfections and uncertainty in photon interaction points, with a key feature being its ability to determine the order of interactions through a model trained on Monte Carlo (MC) simulations using the Geant4 Application for Tomography Emission (GATE) toolkit, thus providing the necessary information to construct Compton cones which intersect with the line of response (LOR) to estimate the emission point; the pipeline processes 3-{\gamma} PET raw data, reconstructs histoimages by propagating energy and spatial uncertainties along the LOR, and applies a 3-D convolutional neural network (CNN) to refine these intermediate images into high-quality reconstructions, further enhancing image quality through supervised learning and adversarial losses that preserve fine structural details; experimental results show that Direct3{\gamma} consistently outperforms conventional 200-ps time-of-flight (TOF) PET in terms of structural similarity index measure (SSIM) and peak signal-to-noise ratio (PSNR).