Dynamic PET Image Prediction Using a Network Combining Reversible and Irreversible Modules

TL;DR

This paper introduces a deep learning network combining reversible and irreversible modules to predict full dynamic PET images from early frames, reducing scan time and maintaining high image quality for clinical use.

Contribution

A novel multi-module deep learning framework that predicts complete dynamic PET images from early frames, enhancing efficiency and clinical applicability.

Findings

Accurately predicts kinetic parameters from early PET frames

Reconstructs high-quality dynamic PET images in validation

Demonstrates good generalization on clinical data

Abstract

Dynamic positron emission tomography (PET) images can reveal the distribution of tracers in the organism and the dynamic processes involved in biochemical reactions, and it is widely used in clinical practice. Despite the high effectiveness of dynamic PET imaging in studying the kinetics and metabolic processes of radiotracers. Pro-longed scan times can cause discomfort for both patients and medical personnel. This study proposes a dynamic frame prediction method for dynamic PET imaging, reduc-ing dynamic PET scanning time by applying a multi-module deep learning framework composed of reversible and irreversible modules. The network can predict kinetic parameter images based on the early frames of dynamic PET images, and then generate complete dynamic PET images. In validation experiments with simulated data, our network demonstrated good predictive performance for kinetic parameters and was able to reconstruct high-quality dynamic PET images. Additionally, in clinical data experiments, the network exhibited good generalization performance and attached that the proposed method has promising clinical application prospects.