Feasibility of deep learning-based image reconstruction using TrueFidelity for coronary calcium scoring
- 1Department of Radiology and the Research Institute of Radiological Science, Gangnam Severance Hospital, Yonsei University College of Medicine, Seoul, Republic of Korea
- 2Department of Integrative Medicine, Yonsei University College of Medicine, Seoul, Republic of Korea
Abstract
We evaluated the feasibility of deep learning-based image reconstruction (DLIR) using GE TrueFidelity at high strength for coronary calcium scoring, compared with filtered back projection (FBP) and iterative reconstruction (IR; adaptive statistical iterative reconstruction-V with 80% blending), using a cardiac phantom and clinical data. Calcium scores for FBP, IR, and DLIR were obtained with a cardiac phantom. Subsequently, 113 patients who underwent coronary computed tomography angiography were retrospectively evaluated. The Agatston method was applied to all three techniques to obtain the coronary artery calcium score (CACS). Differences, correlations, and concordance in sectional classification of calcium scores were evaluated across reconstruction methods. In the phantom study, calcium scores were comparable across reconstruction methods. In the clinical study, DLIR had significantly lower scores than FBP (p < 0.001), whereas the comparison between IR and DLIR was statistically non-significant (p = 0.064). Weighted kappa coefficients indicated high agreement in total CACS classification across the reconstruction methods. However, Bland–Altman analysis demonstrated non-negligible individual-level disagreement between FBP and DLIR, with a mean difference of 14.5 and 95% limits of agreement from −52.1 to 81.1. This disagreement may be clinically relevant near established CAC risk-category thresholds, particularly 0, 100, and 300. Among 113 patients, 109 were classified into the same CAC-DRS category by both FBP and DLIR. DLIR underclassified four patients, yielding a false-negative rate of 4.65%. In conclusion, DLIR was feasible for CACS measurement and showed high overall concordance with FBP and IR. However, near-perfect correlation should not be interpreted as interchangeability, because DLIR showed systematic underestimation and non-negligible individual-level disagreement from FBP, particularly in patients with low calcium burden or scores near CAC risk-category thresholds.
Related
- Association between coronary artery calcium score and myocardial ischemia assessed by stress perfusion cardiac magnetic resonance imaging
- Anatomically Guided Deep Learning Reconstruction of Accelerated Snapshot CEST MRI
- Leveraging meteorological legacy effects and machine learning to improve daily gap-free normalized difference vegetation index reconstruction: a critical basis for fine-scale carbon sink capacity monitoring
- Molecular characterization of pathogen-induced SlCBL1-2, a calcium sensor, reveals the structural basis of calcium sensing in tomato
- EverGreen: A Calcium Sensing Fluorescent Protein with Ultra-Slow Response Properties
BibTeX
@article{kim2026feasibility,
title = {{Feasibility of deep learning-based image reconstruction using TrueFidelity for coronary calcium scoring}},
author = {Ji Won Kim and Tae Hoon Kim and Seung Hyun Lee and Ji Eun Nam and Chul Hwan Park},
journal = {PLOS One},
year = {2026},
month = sep,
doi = {10.1371/journal.pone.0358342},
url = {https://doi.org/10.1371/journal.pone.0358342},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Feasibility of deep learning-based image reconstruction using TrueFidelity for coronary calcium scoring
AU - Ji Won Kim
AU - Tae Hoon Kim
AU - Seung Hyun Lee
AU - Ji Eun Nam
AU - Chul Hwan Park
PY - 2026
DA - 2026/09/18
JO - PLOS One
DO - 10.1371/journal.pone.0358342
UR - https://doi.org/10.1371/journal.pone.0358342
AB - We evaluated the feasibility of deep learning-based image reconstruction (DLIR) using GE TrueFidelity at high strength for coronary calcium scoring, compared with filtered back projection (FBP) and iterative reconstruction (IR; adaptive statistical iterative reconstruction-V with 80% blending), using a cardiac phantom and clinical data. Calcium scores for FBP, IR, and DLIR were obtained with a cardiac phantom. Subsequently, 113 patients who underwent coronary computed tomography angiography were retrospectively evaluated. The Agatston method was applied to all three techniques to obtain the coronary artery calcium score (CACS). Differences, correlations, and concordance in sectional classification of calcium scores were evaluated across reconstruction methods. In the phantom study, calcium scores were comparable across reconstruction methods. In the clinical study, DLIR had significantly lower scores than FBP (p < 0.001), whereas the comparison between IR and DLIR was statistically non-significant (p = 0.064). Weighted kappa coefficients indicated high agreement in total CACS classification across the reconstruction methods. However, Bland–Altman analysis demonstrated non-negligible individual-level disagreement between FBP and DLIR, with a mean difference of 14.5 and 95% limits of agreement from −52.1 to 81.1. This disagreement may be clinically relevant near established CAC risk-category thresholds, particularly 0, 100, and 300. Among 113 patients, 109 were classified into the same CAC-DRS category by both FBP and DLIR. DLIR underclassified four patients, yielding a false-negative rate of 4.65%. In conclusion, DLIR was feasible for CACS measurement and showed high overall concordance with FBP and IR. However, near-perfect correlation should not be interpreted as interchangeability, because DLIR showed systematic underestimation and non-negligible individual-level disagreement from FBP, particularly in patients with low calcium burden or scores near CAC risk-category thresholds.
SN - 1932-6203
ER -