Enhancing 18F-FDG PET image quality and lesion diagnostic performance across different body mass index using the deep progressive learning reconstruction algorithm

TL;DR

This study shows that a new AI-based PET image reconstruction method improves image quality and lesion detection in patients of all body types.

Contribution

The novel deep progressive learning algorithm maintains PET image quality and diagnostic accuracy across varying body mass indexes.

Findings

DPL outperformed OSEM in PET image quality and lesion detection across all BMI categories.

DPL maintained stable signal-to-noise ratios in the liver and lesions even with increasing BMI.

Quantitative metrics like SUVmax and contrast ratios were significantly higher with DPL compared to OSEM.

Abstract

As body mass index (BMI) increases, the quality of 2-deoxy-2-[fluorine-18]fluoro-D-glucose (18F-FDG) positron emission tomography (PET) images reconstructed with ordered subset expectation maximization (OSEM) declines, negatively impacting lesion diagnostics. It is crucial to identify methods that ensure consistent diagnostic accuracy and maintain image quality. Deep progressive learning (DPL) algorithm, an Artificial Intelligence(AI)-based PET reconstruction technique, offers a promising solution.

150 patients underwent 18F-FDG PET/CT scans and were categorized by BMI into underweight, normal, and overweight groups. PET images were reconstructed using both OSEM and DPL and their image quality was assessed both visually and quantitatively. Visual assessment employed a 5-point Likert scale to evaluate overall score, image sharpness, image noise, and diagnostic confidence. Quantitative assessment parameters included the background liver image-uniformity-index (\documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\:{\text{I}\text{U}\text{I}}_{\text{L}\text{i}\text{v}\text{e}\text{r}}$$\end{document}) and signal-to-noise ratio (\documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\:{\text{S}\text{N}\text{R}}_{\text{L}\text{i}\text{v}\text{e}\text{r}}$$\end{document}). Additionally, 466 identifiable lesions were categorized by size: sub-centimeter and larger. We compared maximum standard uptake value (\documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\:{\text{S}\text{U}\text{V}}_{\text{m}\text{a}\text{x}}^{\text{L}\text{e}\text{s}\text{i}\text{o}\text{n}}$$\end{document}), signal-to-background ratio (\documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\:{\text{S}\text{B}\text{R}}_{\text{L}\text{e}\text{s}\text{i}\text{o}\text{n}}$$\end{document}), \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\:{\text{S}\text{N}\text{R}}_{\text{L}\text{e}\text{s}\text{i}\text{o}\text{n}}$$\end{document}, contrast-to-background ratio (\documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\:{\text{C}\text{B}\text{R}}_{\text{L}\text{e}\text{s}\text{i}\text{o}\text{n}}$$\end{document}), and contrast-to-noise ratio (\documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\:{\text{C}\text{N}\text{R}}_{\text{L}\text{e}\text{s}\text{i}\text{o}\text{n}}$$\end{document}) of these lesions to evaluate the diagnostic performance of the DPL and OSEM algorithms across different lesion sizes and BMI categories.

DPL produced superior PET image quality compared to OSEM across all BMI groups. The visual quality of DPL showed a slight decline with increasing BMI, while OSEM exhibited a more significant decline. DPL maintained a stable \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\:{\text{S}\text{N}\text{R}}_{\text{L}\text{i}\text{v}\text{e}\text{r}}$$\end{document} across BMI increases, whereas OSEM exhibited increased noise. In the DPL group, quantitative image quality for overweight patients matched that of normal patients with minimal variance from underweight patients. In contrast, OSEM demonstrated significant declines in quantitative image quality with rising BMI. DPL yielded significantly higher contrast (\documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\:{\text{S}\text{B}\text{R}}_{\text{L}\text{e}\text{s}\text{i}\text{o}\text{n}}\:,\:{\text{S}\text{N}\text{R}}_{\text{L}\text{e}\text{s}\text{i}\text{o}\text{n}}$$\end{document}, \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\:{\text{C}\text{B}\text{R}}_{\text{L}\text{e}\text{s}\text{i}\text{o}\text{n}}$$\end{document},\documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\:\:{\text{C}\text{N}\text{R}}_{\text{L}\text{e}\text{s}\text{i}\text{o}\text{n}}$$\end{document}) and \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\:{\text{S}\text{U}\text{V}}_{\text{m}\text{a}\text{x}}^{\text{L}\text{e}\text{s}\text{i}\text{o}\text{n}}$$\end{document} than OSEM for all lesions across all BMI categories.

DPL consistently provided superior image quality and lesion diagnostic performance compared to OSEM across all BMI categories in 18F-FDG PET/CT scans. Therefore, we recommend using the DPL algorithm for 18F-FDG PET/CT image reconstruction in all BMI patients.

Figures