EUVIMEDEUVIMED entdecken
Multizentrische Studie

Artificial Intelligence-Enhanced Analysis of Echocardiography-Based Radiomic Features for Myocardial Hypertrophy Detection and Etiology Differentiation

Inki Moon iD, Jina Lee iD, Seung-Ah Lee iD, Dawun Jeong, Jaeik Jeon iD, Yeonggul Jang, Sihyeon Jeong iD, Jiyeon Kim iD, Hong-Mi Choi iD, In-Chang Hwang iD, Youngtaek Hong, Goo-Yeong Cho und 2 weitere

Circulation: Cardiovascular Imaging · 2025-05 · 18 (5)

DOI: 10.1161/circimaging.124.017436 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Circulation: Cardiovascular Imaging, 2025-05. Verfasst von Inki Moon und 13 weiteren Autor:innen. Beteiligte Einrichtung: Division of Cardiology, Department of Internal Medicine, Soonchunhyang University Bucheon Hospital, Republic of Korea (I.M.). Hauptthemen laut MEDLINE: Hypertrophy, Left Ventricular, Echocardiography, Artificial Intelligence, Cardiomyopathy, Hypertrophic. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 40 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: While echocardiography is pivotal for detecting left ventricular hypertrophy (LVH), it struggles with etiology differentiation. To enhance LVH assessment, we aimed to develop an artificial intelligence algorithm using echocardiography-based radiomics. This algorithm is designed to detect LVH and differentiate its common etiologies, such as hypertrophic cardiomyopathy (HCM), cardiac amyloidosis (CA), and hypertensive heart disease (HHD), based on echocardiographic images. METHODS: The developmental data sets from multiple medical centers included 867 subjects, with an independent external test set from a single tertiary medical center containing 619 subjects. Radiomic feature analysis was conducted on 4 echocardiographic views, extracting both conventional and harmonization-driven myocardial textures along with myocardial geographic features. Then, we developed classification models for each condition. Variable contributions were evaluated using Shapley Additive Explanations analysis. RESULTS: The radiomics-based LightGBM model, selected from internal validation, maintained strong performance in the external test set (area under the curve of 0.96 for HCM, 0.89 for CA, and 0.86 for HHD). Compared with the logistic regression model using conventional echocardiographic parameters (left ventricular ejection fraction, left ventricular mass index, left atrial volume index, and E/e′), the final model demonstrated superior sensitivity (0.89 versus 0.80 for HCM, 0.80 versus 0.80 for CA, and 0.75 versus 0.33 for HHD) and F1-score (0.87 versus 0.57 for HCM, 0.84 versus 0.72 for CA, and 0.82 versus 0.50 for HHD). Feature analysis highlighted that harmonization-driven textures played a key role in differentiating HCM, while conventional textures and myocardial thickness were influential in differentiating CA and HHD. CONCLUSIONS: This study confirms that artificial intelligence-enhanced echocardiography-based radiomics effectively differentiate the etiology of LVH, highlighting the potential of artificial intelligence-driven texture and geographic analysis in LVH evaluation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Hypertrophy, Left VentricularEchocardiographyArtificial IntelligenceCardiomyopathy, HypertrophicAmyloidosisHumansMaleFemaleMiddle AgedDiagnosis, DifferentialAgedAlgorithmsPredictive Value of TestsVentricular Function, LeftRadiomics

Stichwörter der Autor:innen

artificial intelligenceechocardiographyhypertrophy, left ventricularradiomics

Autor:innen und Institutionen

  • Division of Cardiology, Department of Internal Medicine, Soonchunhyang University Bucheon Hospital, Republic of Korea (I.M.).
  • Department of Internal Medicine, Yonsei University College of Medicine, Seoul, Republic of Korea (I.M.).
  • Department of Internal Medicine, Graduate School of Medical Science, Brain Korea 21 Project, Yonsei University College of Medicine, Seoul, Republic of Korea (J.L., D.J., S.J., J.K.).
  • CONNECT-AI Research Center, Yonsei University College of Medicine, Seoul, Republic of Korea (J.L., S.-A.L., D.J., S.J., J.K., H.-J.C.).
  • Ontact Health, Seoul, Republic of Korea (S.-A.L., J.J., Y.J., Y.H., H.-J.C.).
  • Cardiovascular Center and Division of Cardiology, Department of Internal Medicine, Seoul National University Bundang Hospital, Seongnam, Gyeonggi, Republic of Korea (H.-M.C., I.-C.H., G.-Y.C., Y.E.Y.).

ORCID-Profile: Inki Moon, Jina Lee, Seung-Ah Lee, Jaeik Jeon, Sihyeon Jeong, Jiyeon Kim, Hong-Mi Choi, In-Chang Hwang, Hyuk-Jae Chang

Zitieren

APA

Moon, I., Lee, J., Lee, S. A., Jeong, D., Jeon, J., Jang, Y., Jeong, S., Kim, J., Choi, H. M., Hwang, I. C., Hong, Y., Cho, G. Y., Yoon, Y. E., & Chang, H. J. (2025). Artificial Intelligence-Enhanced Analysis of Echocardiography-Based Radiomic Features for Myocardial Hypertrophy Detection and Etiology Differentiation. Circulation: Cardiovascular Imaging, 18(5). https://doi.org/10.1161/circimaging.124.017436

Vancouver

Moon I, Lee J, Lee SA, Jeong D, Jeon J, Jang Y, et al. Artificial Intelligence-Enhanced Analysis of Echocardiography-Based Radiomic Features for Myocardial Hypertrophy Detection and Etiology Differentiation. Circulation: Cardiovascular Imaging. 2025;18(5). doi:10.1161/circimaging.124.017436

BibTeX
@article{Moon2025,
  author = {Moon, Inki and Lee, Jina and Lee, Seung-Ah and Jeong, Dawun and Jeon, Jaeik and Jang, Yeonggul and Jeong, Sihyeon and Kim, Jiyeon and Choi, Hong-Mi and Hwang, In-Chang and Hong, Youngtaek and Cho, Goo-Yeong and Yoon, Yeonyee E and Chang, Hyuk-Jae},
  title = {Artificial Intelligence-Enhanced Analysis of Echocardiography-Based Radiomic Features for Myocardial Hypertrophy Detection and Etiology Differentiation},
  journal = {Circulation: Cardiovascular Imaging},
  year = {2025},
  volume = {18},
  number = {5},
  doi = {10.1161/circimaging.124.017436}
}
Kostenlos starten →