Evaluating the generalizability of an automated coronary artery calcium segmentation and scoring algorithm using multi-vendor dataset

Abstract Coronary artery calcification score (CACS), also known as the Agatston score, is a significant prognostic tool for cardiovascular disease (CVD) that utilizes computed tomography (CT). We expand our previously proposed algorithm, Residual-block Inspired Coordinate Attention U-Net (RICAU-Net)...

Full description

Saved in:
Bibliographic Details
Main Authors: Doyoung Park, Jedidiah Ng, Yixin Zhong, Chun Sheng Alvin Tan, Xiaomeng Wang, Gillianne Geet Yi Lai, Liang Zhong, Su Kai Gideon Ooi, Daniel Shao Weng Tan, Lohendran Baskaran
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-05785-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849402596968628224
author Doyoung Park
Jedidiah Ng
Yixin Zhong
Chun Sheng Alvin Tan
Xiaomeng Wang
Gillianne Geet Yi Lai
Liang Zhong
Su Kai Gideon Ooi
Daniel Shao Weng Tan
Lohendran Baskaran
author_facet Doyoung Park
Jedidiah Ng
Yixin Zhong
Chun Sheng Alvin Tan
Xiaomeng Wang
Gillianne Geet Yi Lai
Liang Zhong
Su Kai Gideon Ooi
Daniel Shao Weng Tan
Lohendran Baskaran
author_sort Doyoung Park
collection DOAJ
description Abstract Coronary artery calcification score (CACS), also known as the Agatston score, is a significant prognostic tool for cardiovascular disease (CVD) that utilizes computed tomography (CT). We expand our previously proposed algorithm, Residual-block Inspired Coordinate Attention U-Net (RICAU-Net), to evaluate its generalizability on CT data from previously unseen scanners for lesion-specific CAC segmentation. The multi-vendor datasets were 1,108 CT scans acquired by Siemens, GE, Philips, and Toshiba. We created four groups of datasets, using data from the three scanners as the training and validation sets, while the last one as the test set to evaluate the algorithm on data from previously unseen scanners. RICAU-Net was trained using the datasets for automatic lesion-specific CAC segmentation and calcium scoring. The performance of lesion-specific segmentation and calcium scoring were evaluated using per-lesion Dice scores and intraclass correlation coefficient (ICC). And Bland-Altman plot analysis was conducted to examine the agreement between the CAC score derived from the prediction results and the ground truth. The proposed algorithm exhibited a mean absolute difference of less than 5% between the per-lesion Dice scores of the validation and test sets, indicating good generalizability on test sets comprised of data from unseen scanners during the training and validation phases. ICC analysis demonstrates that the Agatston scores calculated using predictions from RICAU-Net and manual segmentation exhibited excellent reliability at the per-patient level across all groups with ICC and 95% confidence intervals: 0.95 (0.95–0.96), 0.99 (0.99–1.00), 0.99 (0.99–0.99), and 1.00 (0.99–1.00) for group 1, 2, 3, and 4 respectively. Our algorithm demonstrates generalized performance on data from previously unseen scanners, making it potentially more suitable and practical for real-world clinical settings, where it will encounter diverse scanners from various organizations. Furthermore, a feasibility study using non-contrast chest CT scans indicates that the performance of our cardiac CT-trained algorithm on chest CT images was acceptable to a certain extent.
format Article
id doaj-art-57fe2005677b4b18b7c72cd86e013474
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-57fe2005677b4b18b7c72cd86e0134742025-08-20T03:37:30ZengNature PortfolioScientific Reports2045-23222025-07-0115111210.1038/s41598-025-05785-5Evaluating the generalizability of an automated coronary artery calcium segmentation and scoring algorithm using multi-vendor datasetDoyoung Park0Jedidiah Ng1Yixin Zhong2Chun Sheng Alvin Tan3Xiaomeng Wang4Gillianne Geet Yi Lai5Liang Zhong6Su Kai Gideon Ooi7Daniel Shao Weng Tan8Lohendran Baskaran9CVS.AI, National Heart Research Institute of SingaporeDuke-NUS Medical School, National University of SingaporeYong Loo Lin School of Medicine, National University of SingaporeYong Loo Lin School of Medicine, National University of SingaporeCardiovascular and Metabolic Disorders Programme, Duke-National University of SingaporeDuke-NUS Medical School, National University of SingaporeDuke-NUS Medical School, National University of SingaporeDuke-NUS Medical School, National University of SingaporeDuke-NUS Medical School, National University of SingaporeCVS.AI, National Heart Research Institute of SingaporeAbstract Coronary artery calcification score (CACS), also known as the Agatston score, is a significant prognostic tool for cardiovascular disease (CVD) that utilizes computed tomography (CT). We expand our previously proposed algorithm, Residual-block Inspired Coordinate Attention U-Net (RICAU-Net), to evaluate its generalizability on CT data from previously unseen scanners for lesion-specific CAC segmentation. The multi-vendor datasets were 1,108 CT scans acquired by Siemens, GE, Philips, and Toshiba. We created four groups of datasets, using data from the three scanners as the training and validation sets, while the last one as the test set to evaluate the algorithm on data from previously unseen scanners. RICAU-Net was trained using the datasets for automatic lesion-specific CAC segmentation and calcium scoring. The performance of lesion-specific segmentation and calcium scoring were evaluated using per-lesion Dice scores and intraclass correlation coefficient (ICC). And Bland-Altman plot analysis was conducted to examine the agreement between the CAC score derived from the prediction results and the ground truth. The proposed algorithm exhibited a mean absolute difference of less than 5% between the per-lesion Dice scores of the validation and test sets, indicating good generalizability on test sets comprised of data from unseen scanners during the training and validation phases. ICC analysis demonstrates that the Agatston scores calculated using predictions from RICAU-Net and manual segmentation exhibited excellent reliability at the per-patient level across all groups with ICC and 95% confidence intervals: 0.95 (0.95–0.96), 0.99 (0.99–1.00), 0.99 (0.99–0.99), and 1.00 (0.99–1.00) for group 1, 2, 3, and 4 respectively. Our algorithm demonstrates generalized performance on data from previously unseen scanners, making it potentially more suitable and practical for real-world clinical settings, where it will encounter diverse scanners from various organizations. Furthermore, a feasibility study using non-contrast chest CT scans indicates that the performance of our cardiac CT-trained algorithm on chest CT images was acceptable to a certain extent.https://doi.org/10.1038/s41598-025-05785-5
spellingShingle Doyoung Park
Jedidiah Ng
Yixin Zhong
Chun Sheng Alvin Tan
Xiaomeng Wang
Gillianne Geet Yi Lai
Liang Zhong
Su Kai Gideon Ooi
Daniel Shao Weng Tan
Lohendran Baskaran
Evaluating the generalizability of an automated coronary artery calcium segmentation and scoring algorithm using multi-vendor dataset
Scientific Reports
title Evaluating the generalizability of an automated coronary artery calcium segmentation and scoring algorithm using multi-vendor dataset
title_full Evaluating the generalizability of an automated coronary artery calcium segmentation and scoring algorithm using multi-vendor dataset
title_fullStr Evaluating the generalizability of an automated coronary artery calcium segmentation and scoring algorithm using multi-vendor dataset
title_full_unstemmed Evaluating the generalizability of an automated coronary artery calcium segmentation and scoring algorithm using multi-vendor dataset
title_short Evaluating the generalizability of an automated coronary artery calcium segmentation and scoring algorithm using multi-vendor dataset
title_sort evaluating the generalizability of an automated coronary artery calcium segmentation and scoring algorithm using multi vendor dataset
url https://doi.org/10.1038/s41598-025-05785-5
work_keys_str_mv AT doyoungpark evaluatingthegeneralizabilityofanautomatedcoronaryarterycalciumsegmentationandscoringalgorithmusingmultivendordataset
AT jedidiahng evaluatingthegeneralizabilityofanautomatedcoronaryarterycalciumsegmentationandscoringalgorithmusingmultivendordataset
AT yixinzhong evaluatingthegeneralizabilityofanautomatedcoronaryarterycalciumsegmentationandscoringalgorithmusingmultivendordataset
AT chunshengalvintan evaluatingthegeneralizabilityofanautomatedcoronaryarterycalciumsegmentationandscoringalgorithmusingmultivendordataset
AT xiaomengwang evaluatingthegeneralizabilityofanautomatedcoronaryarterycalciumsegmentationandscoringalgorithmusingmultivendordataset
AT gilliannegeetyilai evaluatingthegeneralizabilityofanautomatedcoronaryarterycalciumsegmentationandscoringalgorithmusingmultivendordataset
AT liangzhong evaluatingthegeneralizabilityofanautomatedcoronaryarterycalciumsegmentationandscoringalgorithmusingmultivendordataset
AT sukaigideonooi evaluatingthegeneralizabilityofanautomatedcoronaryarterycalciumsegmentationandscoringalgorithmusingmultivendordataset
AT danielshaowengtan evaluatingthegeneralizabilityofanautomatedcoronaryarterycalciumsegmentationandscoringalgorithmusingmultivendordataset
AT lohendranbaskaran evaluatingthegeneralizabilityofanautomatedcoronaryarterycalciumsegmentationandscoringalgorithmusingmultivendordataset