Literature DB >> 34493475

Comparison of two deep learning image reconstruction algorithms in chest CT images: A task-based image quality assessment on phantom data.

Joël Greffier1, Julien Frandon2, Salim Si-Mohamed3, Djamel Dabli2, Aymeric Hamard2, Asmaa Belaouni2, Philippe Akessoul2, Francis Besse4, Boris Guiu5, Jean-Paul Beregi2.   

Abstract

PURPOSE: The purpose of this study was to compare the effect of two deep learning image reconstruction (DLR) algorithms in chest computed tomography (CT) with different clinical indications.
MATERIAL AND METHODS: Acquisitions on image quality and anthropomorphic phantoms were performed at six dose levels (CTDIvol: 10/7.5/5/2.5/1/0.5mGy) on two CT scanners equipped with two different DLR algorithms (TrueFidelityTM and AiCE). Raw data were reconstructed using the filtered back-projection (FBP) and the lowest/intermediate/highest DLR levels (L-DLR/M-DLR/H-DLR) of each algorithm. Noise power spectrum, task-based transfer function (TTF) and detectability index (d') were computed: d' modelled detection of a soft tissue mediastinal nodule, ground-glass opacity, or high-contrast pulmonary lesion. Subjective image quality of anthropomorphic phantom images was analyzed by two radiologists.
RESULTS: For the L-DLR/M-DLR levels, the noise magnitude was lower with TrueFidelityTM than with AiCE from 2.5 to 10 mGy. For H-DLR, noise magnitude was lower with AiCE . For L-DLR and M-DLR, the average NPS spatial frequency (fav) values were greater for AiCE except for 0.5 mGy. For H-DLR levels, fav was greater for TrueFidelityTM than for AiCE. TTF50% values were greater with AiCE for the air insert, and lower than TrueFidelityTM for the polyethylene insert. From 2.5 to10 mGy, d' was greater for AiCE than for TrueFidelityTM for H-DLR for all lesions, but similar for L-DLR and M-DLR. Image quality was rated clinically appropriate for all levels of both algorithms, for dose from 2.5 to 10 mGy, except for L-DLR of AiCE.
CONCLUSION: DLR algorithms reduce the image-noise and improve lesion detectability. Their operations and properties impacted both noise-texture and spatial resolution.
Copyright © 2021 Société française de radiologie. Published by Elsevier Masson SAS. All rights reserved.

Entities:  

Keywords:  Deep learning image reconstruction; Multidetector computed tomography; Task-based image quality assessment

Mesh:

Year:  2021        PMID: 34493475     DOI: 10.1016/j.diii.2021.08.001

Source DB:  PubMed          Journal:  Diagn Interv Imaging        ISSN: 2211-5684            Impact factor:   4.026


  2 in total

1.  Evaluation of resolution characteristics of digital intraoral radiographic images using a task transfer function.

Authors:  Taku Kuramoto; Shinya Takarabe; Hiroki Tsuru; Yusuke Shibayama; Toyoyuki Kato; Kazunori Yoshiura
Journal:  Oral Radiol       Date:  2022-06-29       Impact factor: 1.882

2.  Impact of an artificial intelligence deep-learning reconstruction algorithm for CT on image quality and potential dose reduction: A phantom study.

Authors:  Joël Greffier; Salim Si-Mohamed; Julien Frandon; Maeliss Loisy; Fabien de Oliveira; Jean Paul Beregi; Djamel Dabli
Journal:  Med Phys       Date:  2022-06-24       Impact factor: 4.506

  2 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.