Cargando…

Influence of computed tomography slice thickness on deep learning-based, automatic coronary artery calcium scoring software performance

BACKGROUND: The influence of computed tomography (CT) slice thickness on the accuracy of deep learning (DL)-based, automatic coronary artery calcium (CAC) scoring software has not been explored yet. METHODS: This retrospective study included 844 subjects (477 men, mean age of 58.9±10.7 years) who un...

Descripción completa

Detalles Bibliográficos
Autores principales: Kim, Suh Young, Suh, Young Joo, Lee, Hye-Jeong, Kim, Hwiyoung, Seo, Hyungi, Park, Hee Jun, Yang, Dong Hyun
Formato: Online Artículo Texto
Lenguaje:English
Publicado: AME Publishing Company 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10347342/
https://www.ncbi.nlm.nih.gov/pubmed/37456306
http://dx.doi.org/10.21037/qims-22-835
_version_ 1785073527689314304
author Kim, Suh Young
Suh, Young Joo
Lee, Hye-Jeong
Kim, Hwiyoung
Seo, Hyungi
Park, Hee Jun
Yang, Dong Hyun
author_facet Kim, Suh Young
Suh, Young Joo
Lee, Hye-Jeong
Kim, Hwiyoung
Seo, Hyungi
Park, Hee Jun
Yang, Dong Hyun
author_sort Kim, Suh Young
collection PubMed
description BACKGROUND: The influence of computed tomography (CT) slice thickness on the accuracy of deep learning (DL)-based, automatic coronary artery calcium (CAC) scoring software has not been explored yet. METHODS: This retrospective study included 844 subjects (477 men, mean age of 58.9±10.7 years) who underwent electrocardiogram (ECG)-gated CAC scoring CT scans with 1.5 and 3 mm slice thickness values between September 2013 and October 2020. Automatic CAC scoring was performed using DL-based software (3D patch-based U-Net architectures). Manual CAC scoring was set as the reference standard. The reliability of automatic CAC scoring was evaluated using intraclass correlation coefficients (ICCs) for both the 1.5 and 3 mm datasets. The agreement of CAC severity categories [Agatston score (AS) 0, 1–100, 101–400, >400] between automatic CAC scoring and the reference standard was analyzed using weighted kappa (κ) statistics for both 1.5 and 3 mm datasets. RESULTS: The CAC scoring agreement between the automatic CAC scoring and reference standard was excellent (ICC 0.982 for 1.5 mm, 0.969 for 3 mm, respectively). The categorical agreement of CAC severity between two methods was excellent for both 1.5 and 3 mm scans, with better agreement for 3 mm scans (weighted κ: 0.851 and 0.961, 95% confidence intervals: 0.823–0.879 and 0.945–0.974, respectively). CONCLUSIONS: Automatic CAC scoring shows excellent agreement with the reference standard for both 1.5 and 3 mm scans but results in lower agreement in the CAC severity category for 1.5 mm scans.
format Online
Article
Text
id pubmed-10347342
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher AME Publishing Company
record_format MEDLINE/PubMed
spelling pubmed-103473422023-07-15 Influence of computed tomography slice thickness on deep learning-based, automatic coronary artery calcium scoring software performance Kim, Suh Young Suh, Young Joo Lee, Hye-Jeong Kim, Hwiyoung Seo, Hyungi Park, Hee Jun Yang, Dong Hyun Quant Imaging Med Surg Original Article BACKGROUND: The influence of computed tomography (CT) slice thickness on the accuracy of deep learning (DL)-based, automatic coronary artery calcium (CAC) scoring software has not been explored yet. METHODS: This retrospective study included 844 subjects (477 men, mean age of 58.9±10.7 years) who underwent electrocardiogram (ECG)-gated CAC scoring CT scans with 1.5 and 3 mm slice thickness values between September 2013 and October 2020. Automatic CAC scoring was performed using DL-based software (3D patch-based U-Net architectures). Manual CAC scoring was set as the reference standard. The reliability of automatic CAC scoring was evaluated using intraclass correlation coefficients (ICCs) for both the 1.5 and 3 mm datasets. The agreement of CAC severity categories [Agatston score (AS) 0, 1–100, 101–400, >400] between automatic CAC scoring and the reference standard was analyzed using weighted kappa (κ) statistics for both 1.5 and 3 mm datasets. RESULTS: The CAC scoring agreement between the automatic CAC scoring and reference standard was excellent (ICC 0.982 for 1.5 mm, 0.969 for 3 mm, respectively). The categorical agreement of CAC severity between two methods was excellent for both 1.5 and 3 mm scans, with better agreement for 3 mm scans (weighted κ: 0.851 and 0.961, 95% confidence intervals: 0.823–0.879 and 0.945–0.974, respectively). CONCLUSIONS: Automatic CAC scoring shows excellent agreement with the reference standard for both 1.5 and 3 mm scans but results in lower agreement in the CAC severity category for 1.5 mm scans. AME Publishing Company 2023-01-05 2023-07-01 /pmc/articles/PMC10347342/ /pubmed/37456306 http://dx.doi.org/10.21037/qims-22-835 Text en 2023 Quantitative Imaging in Medicine and Surgery. All rights reserved. https://creativecommons.org/licenses/by-nc-nd/4.0/Open Access Statement: This is an Open Access article distributed in accordance with the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International License (CC BY-NC-ND 4.0), which permits the non-commercial replication and distribution of the article with the strict proviso that no changes or edits are made and the original work is properly cited (including links to both the formal publication through the relevant DOI and the license). See: https://creativecommons.org/licenses/by-nc-nd/4.0 (https://creativecommons.org/licenses/by-nc-nd/4.0/) .
spellingShingle Original Article
Kim, Suh Young
Suh, Young Joo
Lee, Hye-Jeong
Kim, Hwiyoung
Seo, Hyungi
Park, Hee Jun
Yang, Dong Hyun
Influence of computed tomography slice thickness on deep learning-based, automatic coronary artery calcium scoring software performance
title Influence of computed tomography slice thickness on deep learning-based, automatic coronary artery calcium scoring software performance
title_full Influence of computed tomography slice thickness on deep learning-based, automatic coronary artery calcium scoring software performance
title_fullStr Influence of computed tomography slice thickness on deep learning-based, automatic coronary artery calcium scoring software performance
title_full_unstemmed Influence of computed tomography slice thickness on deep learning-based, automatic coronary artery calcium scoring software performance
title_short Influence of computed tomography slice thickness on deep learning-based, automatic coronary artery calcium scoring software performance
title_sort influence of computed tomography slice thickness on deep learning-based, automatic coronary artery calcium scoring software performance
topic Original Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10347342/
https://www.ncbi.nlm.nih.gov/pubmed/37456306
http://dx.doi.org/10.21037/qims-22-835
work_keys_str_mv AT kimsuhyoung influenceofcomputedtomographyslicethicknessondeeplearningbasedautomaticcoronaryarterycalciumscoringsoftwareperformance
AT suhyoungjoo influenceofcomputedtomographyslicethicknessondeeplearningbasedautomaticcoronaryarterycalciumscoringsoftwareperformance
AT leehyejeong influenceofcomputedtomographyslicethicknessondeeplearningbasedautomaticcoronaryarterycalciumscoringsoftwareperformance
AT kimhwiyoung influenceofcomputedtomographyslicethicknessondeeplearningbasedautomaticcoronaryarterycalciumscoringsoftwareperformance
AT seohyungi influenceofcomputedtomographyslicethicknessondeeplearningbasedautomaticcoronaryarterycalciumscoringsoftwareperformance
AT parkheejun influenceofcomputedtomographyslicethicknessondeeplearningbasedautomaticcoronaryarterycalciumscoringsoftwareperformance
AT yangdonghyun influenceofcomputedtomographyslicethicknessondeeplearningbasedautomaticcoronaryarterycalciumscoringsoftwareperformance