{"title":"Fully Automated Coronary Artery Calcium Quantification on ECG-gated Non-contrast Cardiac CT Using Deep-learning with Novel Heart-labeling Method","authors":"Daigo Takahashi, Shinichiro Fujimoto, Yui O Nozaki, Ayako Kudo, Yuko O Kawaguchi, Kazuhisa Takamura, Makoto Hiki, Eisuke Sato, Nobuo Tomizawa, Hiroyuki Daida, Tohru Minamino","doi":"10.1093/ehjopen/oead113","DOIUrl":null,"url":null,"abstract":"Abstract Aims To develop an artificial intelligence (AI)-model which enables fully automated accurate quantification of coronary artery calcium (CAC), using deep learning (DL) on electrocardiogram (ECG)-gated non-contrast cardiac computed tomography (gated CCT) images. Methods and Results Retrospectively, 560 gated CCT images (including 60 synthetic images) performed at our institution were used to train AI-model, which can automatically divide heart region into 5 areas belonging to left main (LM), left anterior descending (LAD), circumflex (LCX), right coronary artery (RCA), and other. Total and vessel-specific CAC score (CACS) in each scan were manually evaluated. AI-model was trained with novel Heart-labeling method via DL according to the manual-derived results. Then, another 409 gated CCT images obtained in our institution were used for model validation. The performance of present AI-model was tested using another external cohort of 400 gated CCT images of Stanford Center for Artificial Intelligence of Medical Imaging by comparing with the ground truth. The overall accuracy of the AI-model for total CACS classification was excellent with Cohen’s kappa of k=0.89 and 0.95 (validation and test, respectively), which surpasses previous research of k=0.89. Bland-Altman analysis showed little difference in individual total and vessel-specific CACS between AI-derived CACS and ground truth in test cohort (mean difference [95% confidence interval] were 1.5 [-42.6, 45.6], -1.5 [-100.5, 97.5], 6.6 [-60.2, 73.5], 0.96 [-59.2, 61.1], and 7.6[-134.1, 149.2] for LM, LAD, LCX, RCA, and total CACS, respectively). Conclusion Present Heart-labeling method provides a further improvement in fully automated, total and vessel-specific CAC quantification on gated CCT.","PeriodicalId":93995,"journal":{"name":"European heart journal open","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"European heart journal open","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1093/ehjopen/oead113","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Abstract Aims To develop an artificial intelligence (AI)-model which enables fully automated accurate quantification of coronary artery calcium (CAC), using deep learning (DL) on electrocardiogram (ECG)-gated non-contrast cardiac computed tomography (gated CCT) images. Methods and Results Retrospectively, 560 gated CCT images (including 60 synthetic images) performed at our institution were used to train AI-model, which can automatically divide heart region into 5 areas belonging to left main (LM), left anterior descending (LAD), circumflex (LCX), right coronary artery (RCA), and other. Total and vessel-specific CAC score (CACS) in each scan were manually evaluated. AI-model was trained with novel Heart-labeling method via DL according to the manual-derived results. Then, another 409 gated CCT images obtained in our institution were used for model validation. The performance of present AI-model was tested using another external cohort of 400 gated CCT images of Stanford Center for Artificial Intelligence of Medical Imaging by comparing with the ground truth. The overall accuracy of the AI-model for total CACS classification was excellent with Cohen’s kappa of k=0.89 and 0.95 (validation and test, respectively), which surpasses previous research of k=0.89. Bland-Altman analysis showed little difference in individual total and vessel-specific CACS between AI-derived CACS and ground truth in test cohort (mean difference [95% confidence interval] were 1.5 [-42.6, 45.6], -1.5 [-100.5, 97.5], 6.6 [-60.2, 73.5], 0.96 [-59.2, 61.1], and 7.6[-134.1, 149.2] for LM, LAD, LCX, RCA, and total CACS, respectively). Conclusion Present Heart-labeling method provides a further improvement in fully automated, total and vessel-specific CAC quantification on gated CCT.