Deep learning-based image quality improvement of 18F-fluorodeoxyglucose positron emission tomography: a retrospective observational study

Junichi Tsuchiya,Kota Yokoyama,Ukihide Tateishi,Evren Asma,Koichiro Kimura,Chung Chan,Ryosuke Watanabe,Ken Yamagiwa,Mitsuhiro Kishino

doi:10.1186/s40658-021-00377-4

Junichi Tsuchiya, Kota Yokoyama + Show 7 more

Open Access

https://doi.org/10.1186/s40658-021-00377-4

Copy DOI

Abstract

BackgroundDeep learning (DL)-based image quality improvement is a novel technique based on convolutional neural networks. The aim of this study was to compare the clinical value of 18F-fluorodeoxyglucose positron emission tomography (18F-FDG PET) images obtained with the DL method with those obtained using a Gaussian filter.MethodsFifty patients with a mean age of 64.4 (range, 19–88) years who underwent 18F-FDG PET/CT between April 2019 and May 2019 were included in the study. PET images were obtained with the DL method in addition to conventional images reconstructed with three-dimensional time of flight-ordered subset expectation maximization and filtered with a Gaussian filter as a baseline for comparison. The reconstructed images were reviewed by two nuclear medicine physicians and scored from 1 (poor) to 5 (excellent) for tumor delineation, overall image quality, and image noise. For the semi-quantitative analysis, standardized uptake values in tumors and healthy tissues were compared between images obtained using the DL method and those obtained with a Gaussian filter.ResultsImages acquired using the DL method scored significantly higher for tumor delineation, overall image quality, and image noise compared to baseline (P < 0.001). The Fleiss’ kappa value for overall inter-reader agreement was 0.78. The standardized uptake values in tumor obtained by DL were significantly higher than those acquired using a Gaussian filter (P < 0.001).ConclusionsDeep learning method improves the quality of PET images.

Highlights

Deep learning (DL)-based image quality improvement is a novel technique based on convolutional neural networks
Images using DL were scored significantly higher for tumor delineation, overall image quality, and image noise than at baseline (P < 0.001; Table 2)
In most of the healthy tissues, the standardized uptake value (SUV) measured with the DL method were higher than those measured with standard reconstruction (P = 0.456 to < 0.001; Table 3)

Summary

Introduction

Deep learning (DL)-based image quality improvement is a novel technique based on convolutional neural networks. The aim of this study was to compare the clinical value of 18F-fluorodeoxyglucose positron emission tomography (18F-FDG PET) images obtained with the DL method with those obtained using a Gaussian filter. Integrated positron emission tomography (PET) and computed tomography (CT) using 18F-fluorodeoxyglucose (FDG) is a standard method used in oncology [1] and is applied in other conditions, including infectious, ischemic, and degenerative diseases. 18F-FDG PET/CT is useful for differentiation between benign and malignant lesions, cancer staging, assessment of the response to treatment, and planning of radiation therapy. PET images are reconstructed by analytic methods such as filtered back projection [4]. Reconstructions using analytic methods are challenging because noise statistics related to the emission of photons are difficult to model. A statistical model in the maximum likelihood framework has been developed [5]

Objectives

Methods

Results

Discussion

Conclusion