A new method for IVUS-based coronary artery disease risk stratification: A link between coronary & carotid ultrasound plaque burdens

•Coronary risk stratification.•Machine learning to link two arteries.•56 grayscale features.•Coronary tissue characterization.•Classification accuracy 94.95% and AUC 0.95. Interventional cardiologists have a deep interest in risk stratification prior to stenting and percutaneous coronary interventio...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Computer Methods and Programs in Biomedicine Jg. 124; S. 161 - 179
Hauptverfasser:	Araki, Tadashi, Ikeda, Nobutaka, Shukla, Devarshi, Londhe, Narendra D., Shrivastava, Vimal K., Banchhor, Sumit K., Saba, Luca, Nicolaides, Andrew, Shafique, Shoaib, Laird, John R., Suri, Jasjit S.
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Ireland Elsevier Ireland Ltd 01.02.2016 Elsevier BV
Schlagworte:	Adult Aged Aged, 80 and over Atherosclerosis B-mode ultrasound B-mode ultrasound; Carotid disease; Coronary artery; IVUS; Machine learning; Risk assessment; Computer Science Applications1707 Computer Vision and Pattern Recognition; Software; Health Informatics Carotid Artery Diseases Carotid Artery Diseases - complications Carotid Artery Diseases - diagnostic imaging Carotid disease Carotid Intima-Media Thickness Coronary artery Coronary Artery Disease Coronary Artery Disease - diagnostic imaging Coronary Artery Disease - etiology Female Humans Image Interpretation, Computer-Assisted Image Interpretation, Computer-Assisted - methods Internal Medicine IVUS Links Machine Learning Male Middle Aged Morphology Other Patients Pattern Recognition, Automated Pattern Recognition, Automated - methods Reproducibility of Results Risk Risk Assessment Risk Assessment - methods Sensitivity and Specificity Stratification Support vector machines Ultrasonography, Interventional Ultrasonography, Interventional - methods Ultrasound IVUS B-mode ultrasound Risk assessment Coronary artery Carotid disease Machine learning
ISSN:	0169-2607, 1872-7565
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!