Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Multicenter Study
. 2025 Aug;26(8):759-770.
doi: 10.3348/kjr.2025.0177. Epub 2025 Jun 13.

Impact of Deep Learning-Based Image Conversion on Fully Automated Coronary Artery Calcium Scoring Using Thin-Slice, Sharp-Kernel, Non-Gated, Low-Dose Chest CT Scans: A Multi-Center Study

Cherry Kim  1 , Sehyun Hong  2 , Hangseok Choi  3 , Won-Seok Yoo  4 , Jin Young Kim  5 , Suyon Chang  6 , Chan Ho Park  7 , Su Jin Hong  8 , Dong Hyun Yang  9 , Hwan Seok Yong  10 , Marly van Assen  11   12 , Carlo N De Cecco  12   13 , Young Joo Suh  14
Affiliations
Multicenter Study

Impact of Deep Learning-Based Image Conversion on Fully Automated Coronary Artery Calcium Scoring Using Thin-Slice, Sharp-Kernel, Non-Gated, Low-Dose Chest CT Scans: A Multi-Center Study

Cherry Kim et al. Korean J Radiol. 2025 Aug.

Abstract

Objective: To evaluate the impact of deep learning-based image conversion on the accuracy of automated coronary artery calcium quantification using thin-slice, sharp-kernel, non-gated, low-dose chest computed tomography (LDCT) images collected from multiple institutions.

Materials and methods: A total of 225 pairs of LDCT and calcium scoring CT (CSCT) images scanned at 120 kVp and acquired from the same patient within a 6-month interval were retrospectively collected from four institutions. Image conversion was performed for LDCT images using proprietary software programs to simulate conventional CSCT. This process included 1) deep learning-based kernel conversion of low-dose, high-frequency, sharp kernels to simulate standard-dose, low-frequency kernels, and 2) thickness conversion using the raysum method to convert 1-mm or 1.25-mm thickness images to 3-mm thickness. Automated Agaston scoring was conducted on the LDCT scans before (LDCT-Orgauto) and after the image conversion (LDCT-CONVauto). Manual scoring was performed on the CSCT images (CSCTmanual) and used as a reference standard. The accuracy of automated Agaston scores and risk severity categorization based on the automated scoring on LDCT scans was analyzed compared to the reference standard, using the Bland-Altman analysis, concordance correlation coefficient (CCC), and weighted kappa (κ) statistic.

Results: LDCT-CONVauto demonstrated a reduced bias for Agaston score, compared with CSCTmanual, than LDCT-Orgauto did (-3.45 vs. 206.7). LDCT-CONVauto showed a higher CCC than LDCT-Orgauto did (0.881 [95% confidence interval {CI}, 0.750-0.960] vs. 0.269 [95% CI, 0.129-0.430]). In terms of risk category assignment, LDCT-Orgauto exhibited poor agreement with CSCTmanual (weighted κ = 0.115 [95% CI, 0.082-0.154]), whereas LDCT-CONVauto achieved good agreement (weighted κ = 0.792 [95% CI, 0.731-0.847]).

Conclusion: Deep learning-based conversion of LDCT images originally obtained with thin slices and a sharp kernel can enhance the accuracy of automated coronary artery calcium score measurement using the images.

Keywords: Artificial intelligence; Calcium; Coronary vessels; Thorax; Tomography, X-ray computed.

PubMed Disclaimer

Conflict of interest statement

Dong Hyun Yang, a Section Editor of the Korean Journal of Radiology, was not involved in the editorial evaluation or decision to publish this article.

Figures

Fig. 1
Fig. 1. Participant flowchart. CSCT = calcium scoring computed tomography, LDCT = low-dose computed tomography, CAC = coronary artery calcium
Fig. 2
Fig. 2. Examples of image conversion. Original image without conversion (LDCT-Org), image with kernel conversion only (LDCT-KC), image with slice thickness conversion only (LDCT-TC), and image with both kernel and slice thickness conversion (LDCT-CONV). The Agaston scores of the reference standard (CSCTmanual), LDCT-Orgauto, LDCT-KCauto, LDCT-TCauto, and LDCT-CONVauto were 56, 106, 64, 67, and 58, respectively. LDCT = low-dose chest computed tomography, LDCT-Org = original image without conversion, LDCT-KC = LDCT image with kernel conversion only, LDCT-TC = LDCT image with slice thickness conversion only, LDCT-CONV = LDCT image with both kernel and slice thickness conversion, CSCT = calcium scoring computed tomography, CSCTmanual = manual scoring on calcium scoring CT, LDCT-Orgauto = automatic scoring on original LDCT images without conversion, LDCT-KCauto = automatic scoring on LDCT images with kernel conversion, LDCT-TCauto = automatic scoring on original LDCT images with slice thickness conversion, LDCT-CONVauto = automatic scoring on LDCT images with both kernel and slice thickness conversion
Fig. 3
Fig. 3. Bland–Altman plots for the (A) Agatston score, (B) volume score, and (C) peak density on LDCT-CONVauto compared with CSCTmanual in all participants (n = 225). LDCT = low-dose computed tomography, LDCT-CONVauto = automatic scoring on LDCT images with both kernel and slice thickness conversion, CSCTmanual = manual scoring on calcium scoring computed tomography, SD = standard deviation
Fig. 4
Fig. 4. Confusion matrices of LDCT-CONVauto with CSCTmanual for risk category assignment. LDCT-CONVauto = automatic scoring on LDCT images with both kernel and slice thickness conversion, CSCTmanual = manual scoring on calcium scoring computed tomography
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Detrano R, Guerci AD, Carr JJ, Bild DE, Burke G, Folsom AR, et al. Coronary calcium as a predictor of coronary events in four racial or ethnic groups. N Engl J Med. 2008;358:1336–1345. - PubMed
    1. Greenland P, LaBree L, Azen SP, Doherty TM, Detrano RC. Coronary artery calcium score combined with Framingham score for risk prediction in asymptomatic individuals. JAMA. 2004;291:210–215. - PubMed
    1. Arad Y, Goodman KJ, Roth M, Newstein D, Guerci AD. Coronary calcification, coronary disease risk factors, C-reactive protein, and atherosclerotic cardiovascular disease events: the St. Francis heart study. J Am Coll Cardiol. 2005;46:158–165. - PubMed
    1. Reiter MJ, Nemesure A, Madu E, Reagan L, Plank A. Frequency and distribution of incidental findings deemed appropriate for S modifier designation on low-dose CT in a lung cancer screening program. Lung Cancer. 2018;120:1–6. - PubMed
    1. Jacobs PC, Gondrie MJ, van der Graaf Y, de Koning HJ, Isgum I, van Ginneken B, et al. Coronary artery calcium can predict all-cause mortality and cardiovascular events on low-dose CT screening for lung cancer. AJR Am J Roentgenol. 2012;198:505–511. - PubMed

Publication types