Detection of vulnerable plaque in virtual histology intravascular ultrasound images using SVM
Virtual Histology Intravascular Ultrasound (VH-IVUS) is a clinically available for visualizing color coded of coronary artery plaque. However, current VH-IVUS image processing techniques have not considered the combinations of features to identify vulnerable plaque. This paper presents a new method...
Saved in:
Main Authors: | , , , , |
---|---|
Format: | Article |
Published: |
IOS Press
2015
|
Subjects: | |
Online Access: | http://eprints.utm.my/id/eprint/59219/ https://doi.org/10.3233/978-1-61499-522-7-149 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Summary: | Virtual Histology Intravascular Ultrasound (VH-IVUS) is a clinically available for visualizing color coded of coronary artery plaque. However, current VH-IVUS image processing techniques have not considered the combinations of features to identify vulnerable plaque. This paper presents a new method for classification of TCFA (thin-cap fibroatheromas) and Non-TCFA plaque based on combined features using the VH-IVUS images using support vector machine (SVM). The proposed method is applied to 546 in-vivo VH-IVUS images. Results proved the dominance of our proposed method with accuracy rates of 98.15% for TCFA. |
---|