Does prior knowledge in the form of multiple low-dose PET images (at different dose levels) improve standard-dose PET prediction?

TL;DR

This paper investigates whether using multiple low-dose PET images at different dose levels as prior knowledge can enhance the accuracy of predicting standard-dose PET images, aiming to improve image quality in low-dose PET imaging.

Contribution

It introduces a novel approach that leverages multiple low-dose PET images to improve standard-dose PET prediction, unlike existing methods relying on a single low-dose image.

Findings

Using multiple low-dose images improves prediction accuracy.

The proposed method outperforms single-dose-based models.

Enhanced image quality in low-dose PET prediction.

Abstract

Reducing the injected dose would result in quality degradation and loss of information in PET imaging. To address this issue, deep learning methods have been introduced to predict standard PET images (S-PET) from the corresponding low-dose versions (L-PET). The existing deep learning-based denoising methods solely rely on a single dose level of PET images to predict the S-PET images. In this work, we proposed to exploit the prior knowledge in the form of multiple low-dose levels of PET images (in addition to the target low-dose level) to estimate the S-PET images.