Skip to main navigation Skip to search Skip to main content

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
  • , Sehyun Hong
  • , Hangseok Choi
  • , Won Seok Yoo
  • , Jin Young Kim
  • , Suyon Chang
  • , Chan Ho Park
  • , Su Jin Hong
  • , Dong Hyun Yang
  • , Hwan Seok Yong
  • , Marly van Assen
  • , Carlo N. De Cecco
  • , Young Joo Suh
  • Korea University
  • Coreline Soft
  • Yonsei University
  • Keimyung University
  • Soonchunhyang University
  • Hanyang University
  • University of Ulsan
  • Emory University

Research output: Contribution to journal › Article › peer-review

5 Scopus citations

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.

Original languageEnglish
Article numbere61
JournalKorean Journal of Radiology
Volume26
Issue number6
DOIs
StatePublished - Jun 2025

Bibliographical note

Publisher Copyright:
© 2025 The Korean Society of Radiology.

Keywords

  • Artificial intelligence
  • Calcium
  • Coronary vessels
  • Thorax
  • Tomography, X-ray computed

Fingerprint

Dive into the research topics of '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'. Together they form a unique fingerprint.

Cite this