Impact of AI-Based Post-Processing on Image Quality of Non-Contrast Computed Tomography of the Chest and Abdomen
Non-contrast computed tomography (CT) is commonly used for the evaluation of various pathologies including pulmonary infections or urolithiasis but, especially in low-dose protocols, image quality is reduced. To improve this, deep learning-based post-processing approaches are being developed. Theref...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2024-03-01
|
Series: | Diagnostics |
Subjects: | |
Online Access: | https://www.mdpi.com/2075-4418/14/6/612 |
_version_ | 1797241466834124800 |
---|---|
author | Marcel A. Drews Aydin Demircioğlu Julia Neuhoff Johannes Haubold Sebastian Zensen Marcel K. Opitz Michael Forsting Kai Nassenstein Denise Bos |
author_facet | Marcel A. Drews Aydin Demircioğlu Julia Neuhoff Johannes Haubold Sebastian Zensen Marcel K. Opitz Michael Forsting Kai Nassenstein Denise Bos |
author_sort | Marcel A. Drews |
collection | DOAJ |
description | Non-contrast computed tomography (CT) is commonly used for the evaluation of various pathologies including pulmonary infections or urolithiasis but, especially in low-dose protocols, image quality is reduced. To improve this, deep learning-based post-processing approaches are being developed. Therefore, we aimed to compare the objective and subjective image quality of different reconstruction techniques and a deep learning-based software on non-contrast chest and low-dose abdominal CTs. In this retrospective study, non-contrast chest CTs of patients suspected of COVID-19 pneumonia and low-dose abdominal CTs suspected of urolithiasis were analysed. All images were reconstructed using filtered back-projection (FBP) and were post-processed using an artificial intelligence (AI)-based commercial software (PixelShine (PS)). Additional iterative reconstruction (IR) was performed for abdominal CTs. Objective and subjective image quality were evaluated. AI-based post-processing led to an overall significant noise reduction independent of the protocol (chest or abdomen) while maintaining image information (max. difference in SNR 2.59 ± 2.9 and CNR 15.92 ± 8.9, <i>p</i> < 0.001). Post-processing of FBP-reconstructed abdominal images was even superior to IR alone (max. difference in SNR 0.76 ± 0.5, <i>p</i> ≤ 0.001). Subjective assessments verified these results, partly suggesting benefits, especially in soft-tissue imaging (<i>p</i> < 0.001). All in all, the deep learning-based denoising—which was non-inferior to IR—offers an opportunity for image quality improvement especially in institutions using older scanners without IR availability. Further studies are necessary to evaluate potential effects on dose reduction benefits. |
first_indexed | 2024-04-24T18:23:47Z |
format | Article |
id | doaj.art-aa9e5e70d132434aa23ad0e59f113beb |
institution | Directory Open Access Journal |
issn | 2075-4418 |
language | English |
last_indexed | 2024-04-24T18:23:47Z |
publishDate | 2024-03-01 |
publisher | MDPI AG |
record_format | Article |
series | Diagnostics |
spelling | doaj.art-aa9e5e70d132434aa23ad0e59f113beb2024-03-27T13:33:19ZengMDPI AGDiagnostics2075-44182024-03-0114661210.3390/diagnostics14060612Impact of AI-Based Post-Processing on Image Quality of Non-Contrast Computed Tomography of the Chest and AbdomenMarcel A. Drews0Aydin Demircioğlu1Julia Neuhoff2Johannes Haubold3Sebastian Zensen4Marcel K. Opitz5Michael Forsting6Kai Nassenstein7Denise Bos8Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Hufelandstraße 55, 45147 Essen, GermanyInstitute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Hufelandstraße 55, 45147 Essen, GermanyFaculty of Medicine, University Duisburg-Essen, Hufelandstraße 55, 45122 Essen, GermanyInstitute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Hufelandstraße 55, 45147 Essen, GermanyInstitute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Hufelandstraße 55, 45147 Essen, GermanyInstitute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Hufelandstraße 55, 45147 Essen, GermanyInstitute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Hufelandstraße 55, 45147 Essen, GermanyInstitute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Hufelandstraße 55, 45147 Essen, GermanyInstitute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Hufelandstraße 55, 45147 Essen, GermanyNon-contrast computed tomography (CT) is commonly used for the evaluation of various pathologies including pulmonary infections or urolithiasis but, especially in low-dose protocols, image quality is reduced. To improve this, deep learning-based post-processing approaches are being developed. Therefore, we aimed to compare the objective and subjective image quality of different reconstruction techniques and a deep learning-based software on non-contrast chest and low-dose abdominal CTs. In this retrospective study, non-contrast chest CTs of patients suspected of COVID-19 pneumonia and low-dose abdominal CTs suspected of urolithiasis were analysed. All images were reconstructed using filtered back-projection (FBP) and were post-processed using an artificial intelligence (AI)-based commercial software (PixelShine (PS)). Additional iterative reconstruction (IR) was performed for abdominal CTs. Objective and subjective image quality were evaluated. AI-based post-processing led to an overall significant noise reduction independent of the protocol (chest or abdomen) while maintaining image information (max. difference in SNR 2.59 ± 2.9 and CNR 15.92 ± 8.9, <i>p</i> < 0.001). Post-processing of FBP-reconstructed abdominal images was even superior to IR alone (max. difference in SNR 0.76 ± 0.5, <i>p</i> ≤ 0.001). Subjective assessments verified these results, partly suggesting benefits, especially in soft-tissue imaging (<i>p</i> < 0.001). All in all, the deep learning-based denoising—which was non-inferior to IR—offers an opportunity for image quality improvement especially in institutions using older scanners without IR availability. Further studies are necessary to evaluate potential effects on dose reduction benefits.https://www.mdpi.com/2075-4418/14/6/612computed tomographyimage reconstructionimage qualitychestabdomenurolithiasis |
spellingShingle | Marcel A. Drews Aydin Demircioğlu Julia Neuhoff Johannes Haubold Sebastian Zensen Marcel K. Opitz Michael Forsting Kai Nassenstein Denise Bos Impact of AI-Based Post-Processing on Image Quality of Non-Contrast Computed Tomography of the Chest and Abdomen Diagnostics computed tomography image reconstruction image quality chest abdomen urolithiasis |
title | Impact of AI-Based Post-Processing on Image Quality of Non-Contrast Computed Tomography of the Chest and Abdomen |
title_full | Impact of AI-Based Post-Processing on Image Quality of Non-Contrast Computed Tomography of the Chest and Abdomen |
title_fullStr | Impact of AI-Based Post-Processing on Image Quality of Non-Contrast Computed Tomography of the Chest and Abdomen |
title_full_unstemmed | Impact of AI-Based Post-Processing on Image Quality of Non-Contrast Computed Tomography of the Chest and Abdomen |
title_short | Impact of AI-Based Post-Processing on Image Quality of Non-Contrast Computed Tomography of the Chest and Abdomen |
title_sort | impact of ai based post processing on image quality of non contrast computed tomography of the chest and abdomen |
topic | computed tomography image reconstruction image quality chest abdomen urolithiasis |
url | https://www.mdpi.com/2075-4418/14/6/612 |
work_keys_str_mv | AT marceladrews impactofaibasedpostprocessingonimagequalityofnoncontrastcomputedtomographyofthechestandabdomen AT aydindemircioglu impactofaibasedpostprocessingonimagequalityofnoncontrastcomputedtomographyofthechestandabdomen AT julianeuhoff impactofaibasedpostprocessingonimagequalityofnoncontrastcomputedtomographyofthechestandabdomen AT johanneshaubold impactofaibasedpostprocessingonimagequalityofnoncontrastcomputedtomographyofthechestandabdomen AT sebastianzensen impactofaibasedpostprocessingonimagequalityofnoncontrastcomputedtomographyofthechestandabdomen AT marcelkopitz impactofaibasedpostprocessingonimagequalityofnoncontrastcomputedtomographyofthechestandabdomen AT michaelforsting impactofaibasedpostprocessingonimagequalityofnoncontrastcomputedtomographyofthechestandabdomen AT kainassenstein impactofaibasedpostprocessingonimagequalityofnoncontrastcomputedtomographyofthechestandabdomen AT denisebos impactofaibasedpostprocessingonimagequalityofnoncontrastcomputedtomographyofthechestandabdomen |